diff --git a/packages/plugin-sdk/scripts/generate.mjs b/packages/plugin-sdk/scripts/generate.mjs index 073c4452ed3..32ddb8faede 100644 --- a/packages/plugin-sdk/scripts/generate.mjs +++ b/packages/plugin-sdk/scripts/generate.mjs @@ -160,6 +160,7 @@ const services = Object.fromEntries( 'deploymentManager', 'terminal', 'skillLibrary', + 'workspaceWeb', ].map((service) => [ service, object( diff --git a/packages/plugin-sdk/src/contracts.ts b/packages/plugin-sdk/src/contracts.ts index 57c2c40da4b..26e12f0d27b 100644 --- a/packages/plugin-sdk/src/contracts.ts +++ b/packages/plugin-sdk/src/contracts.ts @@ -65110,11 +65110,11 @@ export const contracts: { source: { $ref: '#/$defs/WebSource', }, - credentialConfigured: { + customAvailable: { type: 'boolean', }, }, - required: ['basis', 'available', 'source', 'credentialConfigured'], + required: ['basis', 'available', 'source', 'customAvailable'], title: 'WebCapture', $schema: 'https://json-schema.org/draft/2020-12/schema', $defs: { @@ -65136,7 +65136,7 @@ export const contracts: { }, WebSource: { type: 'string', - enum: ['model', 'tavily'], + enum: ['model', 'custom'], }, }, }, @@ -65153,6 +65153,12 @@ export const contracts: { format: 'uint64', minimum: 0, }, + settingsRevision: { + type: ['integer', 'null'], + format: 'uint64', + minimum: 0, + default: null, + }, }, title: 'WebKey', $schema: 'https://json-schema.org/draft/2020-12/schema', @@ -65195,6 +65201,20 @@ export const contracts: { required: ['kind'], additionalProperties: false, }, + { + type: 'object', + additionalProperties: false, + properties: { + kind: { + type: 'string', + const: 'invalid_settings', + }, + message: { + type: 'string', + }, + }, + required: ['kind', 'message'], + }, { type: 'object', properties: { @@ -65224,8 +65244,14 @@ export const contracts: { credential: { $ref: '#/$defs/WebCredential', }, + presets: { + type: 'array', + items: { + $ref: '#/$defs/WebSearchPreset', + }, + }, }, - required: ['settings', 'credential'], + required: ['settings', 'credential', 'presets'], }, WebSettings: { type: 'object', @@ -65237,12 +65263,191 @@ export const contracts: { source: { $ref: '#/$defs/WebSource', }, + backend: { + $ref: '#/$defs/WebBackend', + default: { + kind: 'tavily', + }, + }, }, required: ['enabled', 'source'], }, WebSource: { type: 'string', - enum: ['model', 'tavily'], + enum: ['model', 'custom'], + }, + WebBackend: { + oneOf: [ + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'tavily', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'brave', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'exa', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'serper', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + additionalProperties: false, + properties: { + kind: { + type: 'string', + const: 'custom', + }, + endpoint: { + $ref: '#/$defs/WebSearchEndpoint', + }, + }, + required: ['kind', 'endpoint'], + }, + ], + }, + WebSearchEndpoint: { + type: 'object', + additionalProperties: false, + properties: { + url: { + type: 'string', + }, + method: { + $ref: '#/$defs/WebSearchMethod', + }, + query: { + $ref: '#/$defs/WebParameter', + }, + limit: { + anyOf: [ + { + $ref: '#/$defs/WebParameter', + }, + { + type: 'null', + }, + ], + }, + urlParameters: { + type: 'object', + additionalProperties: { + type: 'string', + }, + }, + body: { + type: 'object', + additionalProperties: true, + }, + auth: { + anyOf: [ + { + $ref: '#/$defs/WebAuth', + }, + { + type: 'null', + }, + ], + }, + results: { + $ref: '#/$defs/WebResultMapping', + }, + }, + required: ['url', 'method', 'query', 'urlParameters', 'body', 'results'], + }, + WebSearchMethod: { + type: 'string', + enum: ['get', 'post'], + }, + WebParameter: { + type: 'object', + additionalProperties: false, + properties: { + location: { + $ref: '#/$defs/WebParameterLocation', + }, + name: { + type: 'string', + }, + }, + required: ['location', 'name'], + }, + WebParameterLocation: { + type: 'string', + enum: ['query', 'body'], + }, + WebAuth: { + type: 'object', + additionalProperties: false, + properties: { + location: { + $ref: '#/$defs/WebAuthLocation', + }, + name: { + type: 'string', + }, + prefix: { + type: 'string', + }, + }, + required: ['location', 'name', 'prefix'], + }, + WebAuthLocation: { + type: 'string', + enum: ['header', 'query', 'body'], + }, + WebResultMapping: { + type: 'object', + additionalProperties: false, + properties: { + list: { + type: 'string', + }, + title: { + type: ['string', 'null'], + }, + url: { + type: 'string', + }, + snippet: { + type: ['string', 'null'], + }, + }, + required: ['list', 'url'], + description: + 'JSON pointers, with an empty list pointer selecting the response root.', }, WebCredential: { type: 'object', @@ -65273,20 +65478,38 @@ export const contracts: { additionalProperties: false, properties: { credential_revision: { - type: 'integer', + type: ['integer', 'null'], + format: 'uint64', + minimum: 0, + }, + settings_revision: { + type: ['integer', 'null'], format: 'uint64', minimum: 0, + default: null, }, outcome: { $ref: '#/$defs/WebCheckOutcome', }, }, - required: ['credential_revision', 'outcome'], + required: ['outcome'], }, WebCheckOutcome: { type: 'string', enum: ['valid', 'invalid_credentials', 'rate_limited', 'network_error', 'timeout'], }, + WebSearchPreset: { + type: 'object', + properties: { + id: { + type: 'string', + }, + endpoint: { + $ref: '#/$defs/WebSearchEndpoint', + }, + }, + required: ['id', 'endpoint'], + }, }, }, resources: {}, @@ -65302,6 +65525,12 @@ export const contracts: { format: 'uint64', minimum: 0, }, + settingsRevision: { + type: ['integer', 'null'], + format: 'uint64', + minimum: 0, + default: null, + }, }, title: 'WebKey', $schema: 'https://json-schema.org/draft/2020-12/schema', @@ -65344,6 +65573,20 @@ export const contracts: { required: ['kind'], additionalProperties: false, }, + { + type: 'object', + additionalProperties: false, + properties: { + kind: { + type: 'string', + const: 'invalid_settings', + }, + message: { + type: 'string', + }, + }, + required: ['kind', 'message'], + }, { type: 'object', properties: { @@ -65373,8 +65616,14 @@ export const contracts: { credential: { $ref: '#/$defs/WebCredential', }, + presets: { + type: 'array', + items: { + $ref: '#/$defs/WebSearchPreset', + }, + }, }, - required: ['settings', 'credential'], + required: ['settings', 'credential', 'presets'], }, WebSettings: { type: 'object', @@ -65386,35 +65635,214 @@ export const contracts: { source: { $ref: '#/$defs/WebSource', }, + backend: { + $ref: '#/$defs/WebBackend', + default: { + kind: 'tavily', + }, + }, }, required: ['enabled', 'source'], }, WebSource: { type: 'string', - enum: ['model', 'tavily'], + enum: ['model', 'custom'], }, - WebCredential: { - type: 'object', - properties: { - revision: { - type: ['integer', 'null'], - format: 'uint64', - minimum: 0, + WebBackend: { + oneOf: [ + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'tavily', + }, + }, + required: ['kind'], + additionalProperties: false, }, - configured: { - type: 'boolean', + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'brave', + }, + }, + required: ['kind'], + additionalProperties: false, }, - check: { - anyOf: [ - { - $ref: '#/$defs/WebCheck', + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'exa', }, - { - type: 'null', + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'serper', }, - ], + }, + required: ['kind'], + additionalProperties: false, }, - }, + { + type: 'object', + additionalProperties: false, + properties: { + kind: { + type: 'string', + const: 'custom', + }, + endpoint: { + $ref: '#/$defs/WebSearchEndpoint', + }, + }, + required: ['kind', 'endpoint'], + }, + ], + }, + WebSearchEndpoint: { + type: 'object', + additionalProperties: false, + properties: { + url: { + type: 'string', + }, + method: { + $ref: '#/$defs/WebSearchMethod', + }, + query: { + $ref: '#/$defs/WebParameter', + }, + limit: { + anyOf: [ + { + $ref: '#/$defs/WebParameter', + }, + { + type: 'null', + }, + ], + }, + urlParameters: { + type: 'object', + additionalProperties: { + type: 'string', + }, + }, + body: { + type: 'object', + additionalProperties: true, + }, + auth: { + anyOf: [ + { + $ref: '#/$defs/WebAuth', + }, + { + type: 'null', + }, + ], + }, + results: { + $ref: '#/$defs/WebResultMapping', + }, + }, + required: ['url', 'method', 'query', 'urlParameters', 'body', 'results'], + }, + WebSearchMethod: { + type: 'string', + enum: ['get', 'post'], + }, + WebParameter: { + type: 'object', + additionalProperties: false, + properties: { + location: { + $ref: '#/$defs/WebParameterLocation', + }, + name: { + type: 'string', + }, + }, + required: ['location', 'name'], + }, + WebParameterLocation: { + type: 'string', + enum: ['query', 'body'], + }, + WebAuth: { + type: 'object', + additionalProperties: false, + properties: { + location: { + $ref: '#/$defs/WebAuthLocation', + }, + name: { + type: 'string', + }, + prefix: { + type: 'string', + }, + }, + required: ['location', 'name', 'prefix'], + }, + WebAuthLocation: { + type: 'string', + enum: ['header', 'query', 'body'], + }, + WebResultMapping: { + type: 'object', + additionalProperties: false, + properties: { + list: { + type: 'string', + }, + title: { + type: ['string', 'null'], + }, + url: { + type: 'string', + }, + snippet: { + type: ['string', 'null'], + }, + }, + required: ['list', 'url'], + description: + 'JSON pointers, with an empty list pointer selecting the response root.', + }, + WebCredential: { + type: 'object', + properties: { + revision: { + type: ['integer', 'null'], + format: 'uint64', + minimum: 0, + }, + configured: { + type: 'boolean', + }, + check: { + anyOf: [ + { + $ref: '#/$defs/WebCheck', + }, + { + type: 'null', + }, + ], + }, + }, required: ['configured'], }, WebCheck: { @@ -65422,20 +65850,38 @@ export const contracts: { additionalProperties: false, properties: { credential_revision: { - type: 'integer', + type: ['integer', 'null'], + format: 'uint64', + minimum: 0, + }, + settings_revision: { + type: ['integer', 'null'], format: 'uint64', minimum: 0, + default: null, }, outcome: { $ref: '#/$defs/WebCheckOutcome', }, }, - required: ['credential_revision', 'outcome'], + required: ['outcome'], }, WebCheckOutcome: { type: 'string', enum: ['valid', 'invalid_credentials', 'rate_limited', 'network_error', 'timeout'], }, + WebSearchPreset: { + type: 'object', + properties: { + id: { + type: 'string', + }, + endpoint: { + $ref: '#/$defs/WebSearchEndpoint', + }, + }, + required: ['id', 'endpoint'], + }, }, }, resources: {}, @@ -65598,55 +66044,248 @@ export const contracts: { source: { $ref: '#/$defs/WebSource', }, + backend: { + $ref: '#/$defs/WebBackend', + default: { + kind: 'tavily', + }, + }, }, required: ['enabled', 'source'], }, WebSource: { type: 'string', - enum: ['model', 'tavily'], + enum: ['model', 'custom'], }, - }, - }, - output: { - oneOf: [ - { + WebBackend: { + oneOf: [ + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'tavily', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'brave', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'exa', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'serper', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + additionalProperties: false, + properties: { + kind: { + type: 'string', + const: 'custom', + }, + endpoint: { + $ref: '#/$defs/WebSearchEndpoint', + }, + }, + required: ['kind', 'endpoint'], + }, + ], + }, + WebSearchEndpoint: { type: 'object', additionalProperties: false, properties: { - kind: { + url: { type: 'string', - const: 'updated', }, - snapshot: { - $ref: '#/$defs/WebSnapshot', + method: { + $ref: '#/$defs/WebSearchMethod', + }, + query: { + $ref: '#/$defs/WebParameter', + }, + limit: { + anyOf: [ + { + $ref: '#/$defs/WebParameter', + }, + { + type: 'null', + }, + ], + }, + urlParameters: { + type: 'object', + additionalProperties: { + type: 'string', + }, + }, + body: { + type: 'object', + additionalProperties: true, + }, + auth: { + anyOf: [ + { + $ref: '#/$defs/WebAuth', + }, + { + type: 'null', + }, + ], + }, + results: { + $ref: '#/$defs/WebResultMapping', }, }, - required: ['kind', 'snapshot'], + required: ['url', 'method', 'query', 'urlParameters', 'body', 'results'], }, - { + WebSearchMethod: { + type: 'string', + enum: ['get', 'post'], + }, + WebParameter: { type: 'object', + additionalProperties: false, properties: { - kind: { + location: { + $ref: '#/$defs/WebParameterLocation', + }, + name: { type: 'string', - const: 'changed', }, }, - required: ['kind'], - additionalProperties: false, + required: ['location', 'name'], }, - { + WebParameterLocation: { + type: 'string', + enum: ['query', 'body'], + }, + WebAuth: { type: 'object', + additionalProperties: false, properties: { - kind: { + location: { + $ref: '#/$defs/WebAuthLocation', + }, + name: { + type: 'string', + }, + prefix: { type: 'string', - const: 'invalid_key', }, }, - required: ['kind'], - additionalProperties: false, + required: ['location', 'name', 'prefix'], }, - { - type: 'object', + WebAuthLocation: { + type: 'string', + enum: ['header', 'query', 'body'], + }, + WebResultMapping: { + type: 'object', + additionalProperties: false, + properties: { + list: { + type: 'string', + }, + title: { + type: ['string', 'null'], + }, + url: { + type: 'string', + }, + snippet: { + type: ['string', 'null'], + }, + }, + required: ['list', 'url'], + description: + 'JSON pointers, with an empty list pointer selecting the response root.', + }, + }, + }, + output: { + oneOf: [ + { + type: 'object', + additionalProperties: false, + properties: { + kind: { + type: 'string', + const: 'updated', + }, + snapshot: { + $ref: '#/$defs/WebSnapshot', + }, + }, + required: ['kind', 'snapshot'], + }, + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'changed', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'invalid_key', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + additionalProperties: false, + properties: { + kind: { + type: 'string', + const: 'invalid_settings', + }, + message: { + type: 'string', + }, + }, + required: ['kind', 'message'], + }, + { + type: 'object', properties: { kind: { type: 'string', @@ -65674,8 +66313,14 @@ export const contracts: { credential: { $ref: '#/$defs/WebCredential', }, + presets: { + type: 'array', + items: { + $ref: '#/$defs/WebSearchPreset', + }, + }, }, - required: ['settings', 'credential'], + required: ['settings', 'credential', 'presets'], }, WebSettings: { type: 'object', @@ -65687,12 +66332,191 @@ export const contracts: { source: { $ref: '#/$defs/WebSource', }, + backend: { + $ref: '#/$defs/WebBackend', + default: { + kind: 'tavily', + }, + }, }, required: ['enabled', 'source'], }, WebSource: { type: 'string', - enum: ['model', 'tavily'], + enum: ['model', 'custom'], + }, + WebBackend: { + oneOf: [ + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'tavily', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'brave', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'exa', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'serper', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + additionalProperties: false, + properties: { + kind: { + type: 'string', + const: 'custom', + }, + endpoint: { + $ref: '#/$defs/WebSearchEndpoint', + }, + }, + required: ['kind', 'endpoint'], + }, + ], + }, + WebSearchEndpoint: { + type: 'object', + additionalProperties: false, + properties: { + url: { + type: 'string', + }, + method: { + $ref: '#/$defs/WebSearchMethod', + }, + query: { + $ref: '#/$defs/WebParameter', + }, + limit: { + anyOf: [ + { + $ref: '#/$defs/WebParameter', + }, + { + type: 'null', + }, + ], + }, + urlParameters: { + type: 'object', + additionalProperties: { + type: 'string', + }, + }, + body: { + type: 'object', + additionalProperties: true, + }, + auth: { + anyOf: [ + { + $ref: '#/$defs/WebAuth', + }, + { + type: 'null', + }, + ], + }, + results: { + $ref: '#/$defs/WebResultMapping', + }, + }, + required: ['url', 'method', 'query', 'urlParameters', 'body', 'results'], + }, + WebSearchMethod: { + type: 'string', + enum: ['get', 'post'], + }, + WebParameter: { + type: 'object', + additionalProperties: false, + properties: { + location: { + $ref: '#/$defs/WebParameterLocation', + }, + name: { + type: 'string', + }, + }, + required: ['location', 'name'], + }, + WebParameterLocation: { + type: 'string', + enum: ['query', 'body'], + }, + WebAuth: { + type: 'object', + additionalProperties: false, + properties: { + location: { + $ref: '#/$defs/WebAuthLocation', + }, + name: { + type: 'string', + }, + prefix: { + type: 'string', + }, + }, + required: ['location', 'name', 'prefix'], + }, + WebAuthLocation: { + type: 'string', + enum: ['header', 'query', 'body'], + }, + WebResultMapping: { + type: 'object', + additionalProperties: false, + properties: { + list: { + type: 'string', + }, + title: { + type: ['string', 'null'], + }, + url: { + type: 'string', + }, + snippet: { + type: ['string', 'null'], + }, + }, + required: ['list', 'url'], + description: + 'JSON pointers, with an empty list pointer selecting the response root.', }, WebCredential: { type: 'object', @@ -65723,20 +66547,38 @@ export const contracts: { additionalProperties: false, properties: { credential_revision: { - type: 'integer', + type: ['integer', 'null'], format: 'uint64', minimum: 0, }, + settings_revision: { + type: ['integer', 'null'], + format: 'uint64', + minimum: 0, + default: null, + }, outcome: { $ref: '#/$defs/WebCheckOutcome', }, }, - required: ['credential_revision', 'outcome'], + required: ['outcome'], }, WebCheckOutcome: { type: 'string', enum: ['valid', 'invalid_credentials', 'rate_limited', 'network_error', 'timeout'], }, + WebSearchPreset: { + type: 'object', + properties: { + id: { + type: 'string', + }, + endpoint: { + $ref: '#/$defs/WebSearchEndpoint', + }, + }, + required: ['id', 'endpoint'], + }, }, }, resources: {}, @@ -65752,6 +66594,12 @@ export const contracts: { format: 'uint64', minimum: 0, }, + settingsRevision: { + type: ['integer', 'null'], + format: 'uint64', + minimum: 0, + default: null, + }, }, title: 'WebKey', $schema: 'https://json-schema.org/draft/2020-12/schema', @@ -65766,82 +66614,281 @@ export const contracts: { type: 'string', const: 'updated', }, - snapshot: { - $ref: '#/$defs/WebSnapshot', + snapshot: { + $ref: '#/$defs/WebSnapshot', + }, + }, + required: ['kind', 'snapshot'], + }, + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'changed', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'invalid_key', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + additionalProperties: false, + properties: { + kind: { + type: 'string', + const: 'invalid_settings', + }, + message: { + type: 'string', + }, + }, + required: ['kind', 'message'], + }, + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'check_unavailable', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + ], + title: 'WebUpdate', + $schema: 'https://json-schema.org/draft/2020-12/schema', + $defs: { + WebSnapshot: { + type: 'object', + properties: { + revision: { + type: ['integer', 'null'], + format: 'uint64', + minimum: 0, + }, + settings: { + $ref: '#/$defs/WebSettings', + }, + credential: { + $ref: '#/$defs/WebCredential', + }, + presets: { + type: 'array', + items: { + $ref: '#/$defs/WebSearchPreset', + }, + }, + }, + required: ['settings', 'credential', 'presets'], + }, + WebSettings: { + type: 'object', + additionalProperties: false, + properties: { + enabled: { + type: 'boolean', + }, + source: { + $ref: '#/$defs/WebSource', + }, + backend: { + $ref: '#/$defs/WebBackend', + default: { + kind: 'tavily', + }, + }, + }, + required: ['enabled', 'source'], + }, + WebSource: { + type: 'string', + enum: ['model', 'custom'], + }, + WebBackend: { + oneOf: [ + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'tavily', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'brave', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'exa', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'serper', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + additionalProperties: false, + properties: { + kind: { + type: 'string', + const: 'custom', + }, + endpoint: { + $ref: '#/$defs/WebSearchEndpoint', + }, + }, + required: ['kind', 'endpoint'], + }, + ], + }, + WebSearchEndpoint: { + type: 'object', + additionalProperties: false, + properties: { + url: { + type: 'string', + }, + method: { + $ref: '#/$defs/WebSearchMethod', + }, + query: { + $ref: '#/$defs/WebParameter', + }, + limit: { + anyOf: [ + { + $ref: '#/$defs/WebParameter', + }, + { + type: 'null', + }, + ], + }, + urlParameters: { + type: 'object', + additionalProperties: { + type: 'string', + }, + }, + body: { + type: 'object', + additionalProperties: true, + }, + auth: { + anyOf: [ + { + $ref: '#/$defs/WebAuth', + }, + { + type: 'null', + }, + ], }, - }, - required: ['kind', 'snapshot'], - }, - { - type: 'object', - properties: { - kind: { - type: 'string', - const: 'changed', + results: { + $ref: '#/$defs/WebResultMapping', }, }, - required: ['kind'], - additionalProperties: false, + required: ['url', 'method', 'query', 'urlParameters', 'body', 'results'], }, - { - type: 'object', - properties: { - kind: { - type: 'string', - const: 'invalid_key', - }, - }, - required: ['kind'], - additionalProperties: false, + WebSearchMethod: { + type: 'string', + enum: ['get', 'post'], }, - { + WebParameter: { type: 'object', + additionalProperties: false, properties: { - kind: { + location: { + $ref: '#/$defs/WebParameterLocation', + }, + name: { type: 'string', - const: 'check_unavailable', }, }, - required: ['kind'], - additionalProperties: false, + required: ['location', 'name'], }, - ], - title: 'WebUpdate', - $schema: 'https://json-schema.org/draft/2020-12/schema', - $defs: { - WebSnapshot: { + WebParameterLocation: { + type: 'string', + enum: ['query', 'body'], + }, + WebAuth: { type: 'object', + additionalProperties: false, properties: { - revision: { - type: ['integer', 'null'], - format: 'uint64', - minimum: 0, + location: { + $ref: '#/$defs/WebAuthLocation', }, - settings: { - $ref: '#/$defs/WebSettings', + name: { + type: 'string', }, - credential: { - $ref: '#/$defs/WebCredential', + prefix: { + type: 'string', }, }, - required: ['settings', 'credential'], + required: ['location', 'name', 'prefix'], }, - WebSettings: { + WebAuthLocation: { + type: 'string', + enum: ['header', 'query', 'body'], + }, + WebResultMapping: { type: 'object', additionalProperties: false, properties: { - enabled: { - type: 'boolean', + list: { + type: 'string', }, - source: { - $ref: '#/$defs/WebSource', + title: { + type: ['string', 'null'], + }, + url: { + type: 'string', + }, + snippet: { + type: ['string', 'null'], }, }, - required: ['enabled', 'source'], - }, - WebSource: { - type: 'string', - enum: ['model', 'tavily'], + required: ['list', 'url'], + description: + 'JSON pointers, with an empty list pointer selecting the response root.', }, WebCredential: { type: 'object', @@ -65872,20 +66919,38 @@ export const contracts: { additionalProperties: false, properties: { credential_revision: { - type: 'integer', + type: ['integer', 'null'], + format: 'uint64', + minimum: 0, + }, + settings_revision: { + type: ['integer', 'null'], format: 'uint64', minimum: 0, + default: null, }, outcome: { $ref: '#/$defs/WebCheckOutcome', }, }, - required: ['credential_revision', 'outcome'], + required: ['outcome'], }, WebCheckOutcome: { type: 'string', enum: ['valid', 'invalid_credentials', 'rate_limited', 'network_error', 'timeout'], }, + WebSearchPreset: { + type: 'object', + properties: { + id: { + type: 'string', + }, + endpoint: { + $ref: '#/$defs/WebSearchEndpoint', + }, + }, + required: ['id', 'endpoint'], + }, }, }, resources: { @@ -66005,8 +67070,14 @@ export const contracts: { credential: { $ref: '#/$defs/WebCredential', }, + presets: { + type: 'array', + items: { + $ref: '#/$defs/WebSearchPreset', + }, + }, }, - required: ['settings', 'credential'], + required: ['settings', 'credential', 'presets'], title: 'WebSnapshot', $schema: 'https://json-schema.org/draft/2020-12/schema', $defs: { @@ -66020,12 +67091,191 @@ export const contracts: { source: { $ref: '#/$defs/WebSource', }, + backend: { + $ref: '#/$defs/WebBackend', + default: { + kind: 'tavily', + }, + }, }, required: ['enabled', 'source'], }, WebSource: { type: 'string', - enum: ['model', 'tavily'], + enum: ['model', 'custom'], + }, + WebBackend: { + oneOf: [ + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'tavily', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'brave', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'exa', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + properties: { + kind: { + type: 'string', + const: 'serper', + }, + }, + required: ['kind'], + additionalProperties: false, + }, + { + type: 'object', + additionalProperties: false, + properties: { + kind: { + type: 'string', + const: 'custom', + }, + endpoint: { + $ref: '#/$defs/WebSearchEndpoint', + }, + }, + required: ['kind', 'endpoint'], + }, + ], + }, + WebSearchEndpoint: { + type: 'object', + additionalProperties: false, + properties: { + url: { + type: 'string', + }, + method: { + $ref: '#/$defs/WebSearchMethod', + }, + query: { + $ref: '#/$defs/WebParameter', + }, + limit: { + anyOf: [ + { + $ref: '#/$defs/WebParameter', + }, + { + type: 'null', + }, + ], + }, + urlParameters: { + type: 'object', + additionalProperties: { + type: 'string', + }, + }, + body: { + type: 'object', + additionalProperties: true, + }, + auth: { + anyOf: [ + { + $ref: '#/$defs/WebAuth', + }, + { + type: 'null', + }, + ], + }, + results: { + $ref: '#/$defs/WebResultMapping', + }, + }, + required: ['url', 'method', 'query', 'urlParameters', 'body', 'results'], + }, + WebSearchMethod: { + type: 'string', + enum: ['get', 'post'], + }, + WebParameter: { + type: 'object', + additionalProperties: false, + properties: { + location: { + $ref: '#/$defs/WebParameterLocation', + }, + name: { + type: 'string', + }, + }, + required: ['location', 'name'], + }, + WebParameterLocation: { + type: 'string', + enum: ['query', 'body'], + }, + WebAuth: { + type: 'object', + additionalProperties: false, + properties: { + location: { + $ref: '#/$defs/WebAuthLocation', + }, + name: { + type: 'string', + }, + prefix: { + type: 'string', + }, + }, + required: ['location', 'name', 'prefix'], + }, + WebAuthLocation: { + type: 'string', + enum: ['header', 'query', 'body'], + }, + WebResultMapping: { + type: 'object', + additionalProperties: false, + properties: { + list: { + type: 'string', + }, + title: { + type: ['string', 'null'], + }, + url: { + type: 'string', + }, + snippet: { + type: ['string', 'null'], + }, + }, + required: ['list', 'url'], + description: + 'JSON pointers, with an empty list pointer selecting the response root.', }, WebCredential: { type: 'object', @@ -66056,20 +67306,38 @@ export const contracts: { additionalProperties: false, properties: { credential_revision: { - type: 'integer', + type: ['integer', 'null'], + format: 'uint64', + minimum: 0, + }, + settings_revision: { + type: ['integer', 'null'], format: 'uint64', minimum: 0, + default: null, }, outcome: { $ref: '#/$defs/WebCheckOutcome', }, }, - required: ['credential_revision', 'outcome'], + required: ['outcome'], }, WebCheckOutcome: { type: 'string', enum: ['valid', 'invalid_credentials', 'rate_limited', 'network_error', 'timeout'], }, + WebSearchPreset: { + type: 'object', + properties: { + id: { + type: 'string', + }, + endpoint: { + $ref: '#/$defs/WebSearchEndpoint', + }, + }, + required: ['id', 'endpoint'], + }, }, }, resources: {}, diff --git a/packages/plugin-sdk/src/generated/methods.ts b/packages/plugin-sdk/src/generated/methods.ts index f38fd78d203..33479d0a98d 100644 --- a/packages/plugin-sdk/src/generated/methods.ts +++ b/packages/plugin-sdk/src/generated/methods.ts @@ -3147,6 +3147,53 @@ export interface ServiceMethods { output: Runtime.SkillLibraryChangeResult; }; }; + workspaceWeb: { + capture: { + mode: 'query'; + input: {}; + output: Runtime.WebCapture; + }; + checkKey: { + mode: 'mutation'; + input: Runtime.WebKey; + output: Runtime.WebUpdate; + }; + deleteKey: { + mode: 'mutation'; + input: Runtime.WebKey; + output: Runtime.WebUpdate; + }; + fetch: { + mode: 'mutation'; + input: Runtime.WebCall_WebFetch; + output: Runtime.WebResult; + }; + probe: { + mode: 'mutation'; + input: Runtime.WebProbe; + output: Runtime.WebResult; + }; + save: { + mode: 'mutation'; + input: Runtime.WebSet; + output: Runtime.WebUpdate; + }; + saveKey: { + mode: 'mutation'; + input: Runtime.WebKey; + output: Runtime.WebUpdate; + }; + search: { + mode: 'mutation'; + input: Runtime.WebCall_WebQuery; + output: Runtime.WebResult; + }; + snapshot: { + mode: 'query'; + input: {}; + output: Runtime.WebSnapshot; + }; + }; } /** * One message the Bot deliberately sent to its user. diff --git a/packages/plugin-sdk/src/generated/runtime.ts b/packages/plugin-sdk/src/generated/runtime.ts index 92576a0c656..a1221369191 100644 --- a/packages/plugin-sdk/src/generated/runtime.ts +++ b/packages/plugin-sdk/src/generated/runtime.ts @@ -77,6 +77,7 @@ export type RuntimeProtocol = | WebSet | WebKey | WebUpdate + | WebSnapshot | WebResult | WebProbe | WebEndpoint @@ -782,7 +783,27 @@ export type DecisionsAnswer = | { type: 'refusal'; }; -export type WebSource = 'model' | 'tavily'; +export type WebSource = 'model' | 'custom'; +export type WebBackend = + | { + kind: 'tavily'; + } + | { + kind: 'brave'; + } + | { + kind: 'exa'; + } + | { + kind: 'serper'; + } + | { + kind: 'custom'; + endpoint: WebSearchEndpoint; + }; +export type WebSearchMethod = 'get' | 'post'; +export type WebParameterLocation = 'query' | 'body'; +export type WebAuthLocation = 'header' | 'query' | 'body'; export type WebUpdate = | { kind: 'updated'; @@ -794,6 +815,10 @@ export type WebUpdate = | { kind: 'invalid_key'; } + | { + kind: 'invalid_settings'; + message: string; + } | { kind: 'check_unavailable'; }; @@ -5719,7 +5744,7 @@ export interface WebCapture { basis: WebBasis; available: boolean; source: WebSource; - credentialConfigured: boolean; + customAvailable: boolean; } export interface WebBasis { revision?: number | null; @@ -5747,14 +5772,49 @@ export interface WebSet { export interface WebSettings { enabled: boolean; source: WebSource; + backend?: WebBackend; +} +export interface WebSearchEndpoint { + url: string; + method: WebSearchMethod; + query: WebParameter; + limit?: WebParameter | null; + urlParameters: { + [k: string]: string | undefined; + }; + body: { + [k: string]: unknown | undefined; + }; + auth?: WebAuth | null; + results: WebResultMapping; +} +export interface WebParameter { + location: WebParameterLocation; + name: string; +} +export interface WebAuth { + location: WebAuthLocation; + name: string; + prefix: string; +} +/** + * JSON pointers, with an empty list pointer selecting the response root. + */ +export interface WebResultMapping { + list: string; + title?: string | null; + url: string; + snippet?: string | null; } export interface WebKey { revision?: number | null; + settingsRevision?: number | null; } export interface WebSnapshot { revision?: number | null; settings: WebSettings; credential: WebCredential; + presets: WebSearchPreset[]; [k: string]: unknown | undefined; } export interface WebCredential { @@ -5764,9 +5824,15 @@ export interface WebCredential { [k: string]: unknown | undefined; } export interface WebCheck { - credential_revision: number; + credential_revision?: number | null; + settings_revision?: number | null; outcome: WebCheckOutcome; } +export interface WebSearchPreset { + id: string; + endpoint: WebSearchEndpoint; + [k: string]: unknown | undefined; +} export interface WebProbe { url: string; } diff --git a/platform/host-runtime/src/http/worker.rs b/platform/host-runtime/src/http/worker.rs index 00827d20bbd..3d926bf92d4 100644 --- a/platform/host-runtime/src/http/worker.rs +++ b/platform/host-runtime/src/http/worker.rs @@ -28,7 +28,7 @@ pub(super) async fn run( let mut response = match request.send().await { Ok(response) => response, Err(error) => { - let error = message(error); + let error = message(error.without_url()); let _ = head.send(Err(error.clone())); return Err(error); } @@ -63,7 +63,7 @@ pub(super) async fn run( Ok(None) => { return Ok(serde_json::json!({"status": status, "receivedBytes": received_bytes})); } - Err(error) => return Err(message(error)), + Err(error) => return Err(message(error.without_url())), } } } diff --git a/plugins/agent/engine/src/prepared_prompt/wire.rs b/plugins/agent/engine/src/prepared_prompt/wire.rs index 30d6d16e5da..5f5fb06657e 100644 --- a/plugins/agent/engine/src/prepared_prompt/wire.rs +++ b/plugins/agent/engine/src/prepared_prompt/wire.rs @@ -153,6 +153,19 @@ pub(super) async fn compile( if cancellation.is_cancelled() { return Err(RunError::Cancelled); } + // The frozen Responses codec has already applied the plaintext-content + // policy to these recipes. Keep that policy with the prepared request. + if matches!( + provider.kind, + maka_model::ProviderKind::OpenResponses(contract) + if contract.reasoning_replay + == maka_agent_facts::model::PlaintextReasoningReplay::PlaintextContent + ) { + prompt.body = prompt + .body + .clone() + .with_normalization(provider.kind.clone()); + } prompt.wire = Some(PreparedWire { format: encoding.format(), codec: encoding.codec().to_owned().into(), diff --git a/plugins/agent/engine/src/reconcile.rs b/plugins/agent/engine/src/reconcile.rs index f78865cca88..89b6e0bd13b 100644 --- a/plugins/agent/engine/src/reconcile.rs +++ b/plugins/agent/engine/src/reconcile.rs @@ -669,6 +669,12 @@ pub(crate) fn model_settlement_action( } } +fn has_local_tool_calls(view: &RunView, attempt: ModelAttemptId) -> bool { + view.tools + .values() + .any(|tool| tool.key.attempt == attempt && !tool.call.provider_executed) +} + fn final_reply(view: &RunView, request: &RequestSpec, now: UnixMillis) -> bool { if view.stopped || view.cancelled_by_risk @@ -693,12 +699,15 @@ fn final_reply(view: &RunView, request: &RequestSpec, now: UnixMillis) -> bool { { return false; } - let Some(attempt) = view.current_attempt.and_then(|id| view.attempts.get(&id)) else { + let Some(id) = view.current_attempt else { + return false; + }; + let Some(attempt) = view.attempts.get(&id) else { return false; }; attempt.step == request.step && attempt.admission.is_some() - && !attempt.has_tools + && !has_local_tool_calls(view, id) && attempt.closed.as_ref().is_some_and(|closed| { closed.outcome == maka_agent_facts::accounting::Outcome::Success && closed.diagnostic.is_none() @@ -1459,15 +1468,18 @@ fn next_action( { return Action::Prepare(Preparation::Notifications { attempt: id }); } + let needs_continuation = protocol.finish_reason + == maka_agent_facts::model::ModelFinishReason::ToolCalls + || (attempt.has_tools && has_local_tool_calls(view, id)); if let Some(cell) = view .cells .values() .find(|cell| matches!(cell.status, CellStatus::Running)) - && !attempt.has_tools + && !needs_continuation { return wait(view, WaitReason::Cell { cell: cell.id }, None, now); } - return if attempt.has_tools { + return if needs_continuation { Action::Prepare(Preparation::ToolContinuation { attempt: id }) } else { Action::Terminate(Terminal::Completed) diff --git a/plugins/agent/engine/src/reconcile/tests.rs b/plugins/agent/engine/src/reconcile/tests.rs index 13735d7eeb1..3654ff43a37 100644 --- a/plugins/agent/engine/src/reconcile/tests.rs +++ b/plugins/agent/engine/src/reconcile/tests.rs @@ -537,6 +537,52 @@ fn spent_budget_does_not_complete_over_child_wait_or_context_compaction_trigger( assert!(!complete_at_budget(&context, &request, UnixMillis(1))); } +#[test] +fn provider_search_and_final_answer_complete_in_one_request() { + use maka_agent_facts::{accounting::Outcome, context::ModelPurpose, model::ModelFinishReason}; + use maka_plugin_core::operation::OperationCleanup; + + let mut view = policy_view(None); + let spec = ContentBlob::json(&view.spec).unwrap(); + apply_policy_fact( + &mut view, + Fact::RunAdmitted { + spec: spec.reference().clone(), + }, + ); + let (mut view, _, attempt) = model_closure( + view, + ModelPurpose::Main, + ModelFinishReason::Stop, + Outcome::Success, + true, + ); + let key = ToolKey { + attempt, + call: "continuation".into(), + }; + let tool = view + .tools + .get_mut(&maka_agent_state::fold::tool_key(&key)) + .unwrap(); + tool.call.provider_executed = true; + tool.accepted = Some(maka_agent_state::fold::ToolAcceptance { + result: view.spec.input.clone(), + outcome: AcceptedResult::Succeeded, + }); + apply_policy_fact( + &mut view, + Fact::ModelCleanupObserved { + attempt, + cleanup: OperationCleanup::Confirmed, + }, + ); + assert!(matches!( + next(&view, &Live::default(), UnixMillis(1), None, false), + Action::Terminate(Terminal::Completed) + )); +} + #[test] fn spent_budget_preserves_final_success_and_waits_for_original_cleanup_ack() { use maka_agent_facts::{accounting::Outcome, context::ModelPurpose, model::ModelFinishReason}; diff --git a/plugins/agent/facts/src/tools/provider.rs b/plugins/agent/facts/src/tools/provider.rs index ec9c1adf160..0368e6e4cf7 100644 --- a/plugins/agent/facts/src/tools/provider.rs +++ b/plugins/agent/facts/src/tools/provider.rs @@ -62,5 +62,18 @@ pub struct ModelToolContext { #[serde(rename_all = "snake_case")] pub enum ProviderToolProtocol { OpenaiResponses, + DeepseekResponses, AnthropicMessages, } + +impl ProviderToolProtocol { + pub fn accepts(self, id: &str) -> bool { + let namespace = match self { + Self::OpenaiResponses => "openai", + Self::DeepseekResponses => "deepseek", + Self::AnthropicMessages => "anthropic", + }; + id.split_once('.') + .is_some_and(|(prefix, _)| prefix == namespace) + } +} diff --git a/plugins/agent/model/src/adapters/responses/decode.rs b/plugins/agent/model/src/adapters/responses/decode.rs index 471a6872bea..3cf43951440 100644 --- a/plugins/agent/model/src/adapters/responses/decode.rs +++ b/plugins/agent/model/src/adapters/responses/decode.rs @@ -44,12 +44,9 @@ impl Decoder { let search_name = tools .iter() .find(|tool| { - tool.provider.as_ref().is_some_and(|provider| { - matches!( - provider.id.as_str(), - "openai.web_search" | "openai.web_search_preview" - ) - }) + tool.provider + .as_ref() + .is_some_and(|provider| super::request::search_kind(&provider.id).is_some()) }) .map(|tool| tool.name.clone()); Self { diff --git a/plugins/agent/model/src/adapters/responses/request.rs b/plugins/agent/model/src/adapters/responses/request.rs index 26836274a41..cad42093d5d 100644 --- a/plugins/agent/model/src/adapters/responses/request.rs +++ b/plugins/agent/model/src/adapters/responses/request.rs @@ -249,7 +249,7 @@ fn project( output, .. } => { - if plaintext.is_none() && options[namespace]["store"] == false { + if plaintext.is_some() || options[namespace]["store"] == false { let replay = replay(provider_options)?; let action = match output { ToolOutput::Json(value) | ToolOutput::ErrorJson(value) => { @@ -293,22 +293,23 @@ fn project( } Ok(input) } +pub(super) fn search_kind(id: &str) -> Option { + match id { + "openai.web_search" | "deepseek.web_search" => Some(SearchKind::Search), + "openai.web_search_preview" => Some(SearchKind::Preview), + "deepseek.deepseek_web_search" => Some(SearchKind::Deepseek), + _ => None, + } +} + fn tool(tool: &ToolDefinition, plaintext: bool) -> Result { if let Some(provider) = &tool.provider { - let kind = match provider.id.as_str() { - "openai.web_search" => SearchKind::Search, - "openai.web_search_preview" => SearchKind::Preview, - id if !id.starts_with("openai.") => { - return Err(Error::Invalid( - "Responses provider tool belongs to another protocol".into(), - )); - } - id => { - return Err(Error::Invalid(format!( - "Unsupported provider-executed tool: {id}" - ))); - } - }; + let kind = search_kind(&provider.id).ok_or_else(|| { + Error::Invalid(format!( + "Unsupported provider-executed tool: {}", + provider.id + )) + })?; Ok(Tool::WebSearch { kind, args: provider.args.clone(), diff --git a/plugins/agent/model/src/adapters/responses/stream.rs b/plugins/agent/model/src/adapters/responses/stream.rs index 91d11783914..74c814b5347 100644 --- a/plugins/agent/model/src/adapters/responses/stream.rs +++ b/plugins/agent/model/src/adapters/responses/stream.rs @@ -164,6 +164,10 @@ async fn run( url.set_path(&format!("{}/responses", url.path().trim_end_matches('/'))); let headers = headers(&request)?; let mut decoder = Decoder::new(plaintext, &request.tools).operation(request.operation); + // DeepSeek's Responses endpoint streams over HTTP. + let lane = lane.filter(|_| { + !(plaintext.is_some() && crate::is_deepseek_endpoint(&request.provider.base_url)) + }); if lane.as_ref().is_some_and(|lane| { lane.retry_transport_phase() == maka_agent_ports::model::RetryTransportPhase::Primary }) && (!request.provider.headers.is_empty() diff --git a/plugins/agent/model/src/adapters/wire/responses.rs b/plugins/agent/model/src/adapters/wire/responses.rs index 3469cdeaa5d..08fd1a87b7d 100644 --- a/plugins/agent/model/src/adapters/wire/responses.rs +++ b/plugins/agent/model/src/adapters/wire/responses.rs @@ -501,8 +501,7 @@ async fn encode_message( )); } AssistantRecipe::ToolResult(result) => { - if plaintext.is_none() - && !store + if (plaintext.is_some() || !store) && let Some(replay) = field( &result.provider_options, &["openai", "responsesReplay"], diff --git a/plugins/agent/model/src/lib.rs b/plugins/agent/model/src/lib.rs index 829cb15f226..563d81b19bb 100644 --- a/plugins/agent/model/src/lib.rs +++ b/plugins/agent/model/src/lib.rs @@ -100,6 +100,9 @@ impl ProviderConfig { capabilities: self.capabilities, provider_tools: match self.kind { ProviderKind::OpenaiResponses => Some(ProviderToolProtocol::OpenaiResponses), + ProviderKind::OpenResponses(_) if is_deepseek_endpoint(&self.base_url) => { + Some(ProviderToolProtocol::DeepseekResponses) + } ProviderKind::Anthropic => Some(ProviderToolProtocol::AnthropicMessages), _ => None, }, @@ -107,6 +110,11 @@ impl ProviderConfig { } } +fn is_deepseek_endpoint(base_url: &str) -> bool { + reqwest::Url::parse(base_url) + .is_ok_and(|url| url.scheme() == "https" && url.host_str() == Some("api.deepseek.com")) +} + /// Complete JSON encodings before transport-level prefix reuse. #[derive(Clone, Copy, Debug, PartialEq, Eq)] pub struct EncodedRequestBytes { @@ -473,17 +481,12 @@ impl ModelExecutor { provider .validate() .map_err(|error| ModelError::Adapter(error.into()))?; - let protocol = request.provider.tool_context().provider_tools; - let compatible = match protocol { - Some(maka_agent_facts::tools::ProviderToolProtocol::OpenaiResponses) => { - provider.id.starts_with("openai.") - } - Some(maka_agent_facts::tools::ProviderToolProtocol::AnthropicMessages) => { - provider.id.starts_with("anthropic.") - } - None => false, - }; - if !compatible { + if !request + .provider + .tool_context() + .provider_tools + .is_some_and(|protocol| protocol.accepts(&provider.id)) + { return Err(ModelError::Adapter( "provider tool does not match the selected adapter".into(), )); diff --git a/plugins/agent/native/src/tools/web.rs b/plugins/agent/native/src/tools/web.rs index 7238a90bb60..e6f14a2f62c 100644 --- a/plugins/agent/native/src/tools/web.rs +++ b/plugins/agent/native/src/tools/web.rs @@ -92,23 +92,26 @@ impl RequestBinding for Binding { let name = service.selection.name.clone(); let projection = if !capture.available { BoundTool::Unavailable - } else if service.selection.method == "search" - && capture.source == maka_web_api::settings::Source::Model - { - input - .model - .as_ref() - .and_then(maka_web::search::native) - .map_or(BoundTool::Unavailable, BoundTool::Provider) - } else if service.selection.method == "search" && !capture.credential_configured - { - BoundTool::Unavailable } else { - BoundTool::Prepared(Arc::new(Service { - shell: None, - web_basis: Some(capture.basis.clone()), - ..service - })) + let search = service.selection.method == "search"; + let prepared = || { + BoundTool::Prepared(Arc::new(Service { + shell: None, + web_basis: Some(capture.basis.clone()), + ..service + })) + }; + if search { + match maka_web::search::select(&capture, input.model.as_ref()) { + Some(maka_web::search::Selection::Provider(tool)) => { + BoundTool::Provider(tool) + } + Some(maka_web::search::Selection::Custom) => prepared(), + None => BoundTool::Unavailable, + } + } else { + prepared() + } }; (name, projection) }) diff --git a/plugins/agent/provider-protocol/src/responses/decode.rs b/plugins/agent/provider-protocol/src/responses/decode.rs index 9552410d8d8..0714cc071f7 100644 --- a/plugins/agent/provider-protocol/src/responses/decode.rs +++ b/plugins/agent/provider-protocol/src/responses/decode.rs @@ -663,23 +663,21 @@ impl Decoder { self.pending_effects.insert(id.into()); } let mut replay = BTreeMap::new(); - if self.reasoning == ReasoningMode::Encrypted { - let finalized = value["type"] == "response.output_item.done"; - let values: Vec<&Value> = if finalized { - vec![&value["item"]] - } else { - value["response"]["output"] - .as_array() - .map(|items| items.iter().collect()) - .unwrap_or_default() - }; - for item in values { - if let Some(id) = item["id"].as_str() - && !self.done.contains(id) - && let Some(template) = super::replay::capture(item) - { - replay.insert(id.to_owned(), template); - } + let items = if value["type"] == "response.output_item.done" { + std::slice::from_ref(&value["item"]) + } else { + value["response"]["output"] + .as_array() + .map(Vec::as_slice) + .unwrap_or_default() + }; + for item in items { + if (self.reasoning == ReasoningMode::Encrypted || item["type"] == "web_search_call") + && let Some(id) = item["id"].as_str() + && !self.done.contains(id) + && let Some(template) = super::replay::capture(item) + { + replay.insert(id.to_owned(), template); } } let event: Event = serde_json::from_value(value) @@ -858,6 +856,85 @@ mod tests { use super::*; use serde_json::json; + #[test] + fn deepseek_search_results_and_citations_survive_plaintext_responses() { + use super::super::request::{Input, Request, SearchKind, Tool}; + + let reasoning = ReasoningMode::PlaintextContent; + for (model, kind, wire_type, action, citation) in [ + ( + "deepseek-v4-pro", + SearchKind::Search, + "web_search", + json!({"type":"search","queries":["official Python site","ws_call_id=fixture"]}), + None, + ), + ( + "deepseek-flash", + SearchKind::Deepseek, + "deepseek_web_search", + json!({"type":"search","sources":[{"url":"https://www.python.org/","title":"Python"}]}), + Some( + json!({"type":"url_citation","url":"https://www.python.org/","title":"Python","start_index":0,"end_index":6}), + ), + ), + ] { + let mut decoder = Decoder::new(reasoning, Some("WebSearch".into())); + let mut item = json!({ + "type":"web_search_call","id":"ws_fixture","status":"completed","action":action + }); + if kind == SearchKind::Deepseek { + item["kind"] = json!("search"); + } + decoder + .push(json!({ + "type":"response.output_item.added", + "item":{"type":"web_search_call","id":"ws_fixture","status":"in_progress"} + })) + .unwrap(); + let events = decoder + .push(json!({"type":"response.output_item.done","item":item})) + .unwrap(); + let [ + OutputEvent::ToolResult { + action, metadata, .. + }, + ] = events.as_slice() + else { + panic!("expected a settled search call, got {events:?}"); + }; + let request = Request { + model, + input: &[Input::ProviderResult { + replay: metadata.replay.clone(), + action: action.clone(), + }], + tools: &[Tool::WebSearch { + kind, + args: json!({}), + }], + tool_choice: Default::default(), + options: &json!({"openResponses":{}}), + max_output_tokens: None, + reasoning, + } + .encode() + .unwrap(); + assert_eq!(request["tools"], json!([{"type":wire_type}])); + assert_eq!(request["input"], json!([item])); + if let Some(annotation) = citation { + let events = decoder + .push(json!({ + "type":"response.output_text.annotation.added", + "item_id":"msg_fixture","annotation_index":0,"annotation":annotation + })) + .unwrap(); + assert!(matches!(events.as_slice(), [OutputEvent::Citation(c)] + if c.url == "https://www.python.org/" && c.title.as_deref() == Some("Python"))); + } + } + } + #[test] fn summary_deltas_retain_item_boundaries_without_rewriting_replay_text() { let mut decoder = Decoder::new(ReasoningMode::Encrypted, None); diff --git a/plugins/agent/provider-protocol/src/responses/request.rs b/plugins/agent/provider-protocol/src/responses/request.rs index 1fe3d39a07c..4e3a33691e5 100644 --- a/plugins/agent/provider-protocol/src/responses/request.rs +++ b/plugins/agent/provider-protocol/src/responses/request.rs @@ -106,6 +106,7 @@ pub enum Tool { pub enum SearchKind { Search, Preview, + Deepseek, } impl Content { @@ -154,7 +155,12 @@ impl Tool { json!({"type":"custom", "name":name, "description":description, "format":format}) } Self::WebSearch { kind, args } => { - let mut value = json!({"type": match kind { SearchKind::Search => "web_search", SearchKind::Preview => "web_search_preview" }}); + let tool_type = match kind { + SearchKind::Search => "web_search", + SearchKind::Preview => "web_search_preview", + SearchKind::Deepseek => "deepseek_web_search", + }; + let mut value = json!({"type": tool_type}); let args = args.as_object().ok_or_else(|| { Error::Invalid("provider tool arguments must be an object".into()) })?; @@ -262,7 +268,7 @@ fn encode_items(input: &[Input], reasoning: ReasoningMode, options: &Value) -> R } Input::ToolOutput { id, custom, output } => items.push(json!({"type": if *custom && reasoning == ReasoningMode::Encrypted { "custom_tool_call_output" } else { "function_call_output" }, "call_id":id, "output":output.encode()})), Input::ProviderResult { replay, action } => { - if reasoning == ReasoningMode::Encrypted && options["store"] == false && let Some(replay) = replay { + if (reasoning.is_plaintext() || options["store"] == false) && let Some(replay) = replay { items.push(replay.provider(action)?); } } diff --git a/plugins/agent/providers/data/catalog-facts.json b/plugins/agent/providers/data/catalog-facts.json index 9686267939a..10bd0593875 100644 --- a/plugins/agent/providers/data/catalog-facts.json +++ b/plugins/agent/providers/data/catalog-facts.json @@ -1 +1 @@ -{"anthropic":{"baseUrl":"https://api.anthropic.com","label":"Anthropic","authKind":"api_key","runtimeAdapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["claude-sonnet-4-6","claude-opus-4-8","claude-haiku-4-5","claude-sonnet-4-5","claude-sonnet-4-5-20250929","claude-opus-4-1-20250805"],"models":{"claude-fable-5":{"metadata":{"displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-06-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-fable-5","displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000},"anthropicAdaptiveThinking":true},"claude-fable-5-1":{"metadata":{"displayName":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-06","structuredOutput":true,"lastUpdated":"2026-09-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-fable-5-1","displayName":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-06"},"anthropicAdaptiveThinking":true},"claude-haiku-4-5":{"metadata":{"displayName":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-02-28","structuredOutput":true,"lastUpdated":"2025-10-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"toggle":true,"offBehavior":"anthropic-thinking-disabled"}},"entry":{"id":"claude-haiku-4-5","displayName":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-02-28"},"anthropicAdaptiveThinking":false},"claude-haiku-4-5-20251001":{"metadata":{"displayName":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-02-28","structuredOutput":true,"lastUpdated":"2025-10-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"toggle":true,"offBehavior":"anthropic-thinking-disabled"}},"entry":{"id":"claude-haiku-4-5-20251001","displayName":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-02-28"},"anthropicAdaptiveThinking":false},"claude-opus-4-5":{"metadata":{"displayName":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2025-11-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-opus-4-5","displayName":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-05"},"anthropicAdaptiveThinking":false},"claude-opus-4-5-20251101":{"metadata":{"displayName":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2025-11-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-opus-4-5-20251101","displayName":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-05"},"anthropicAdaptiveThinking":false},"claude-opus-4-6":{"metadata":{"displayName":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-05-31","structuredOutput":true,"lastUpdated":"2026-03-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-opus-4-6","displayName":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05-31"},"anthropicAdaptiveThinking":true},"claude-opus-4-7":{"metadata":{"displayName":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","structuredOutput":true,"lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-opus-4-7","displayName":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"},"anthropicAdaptiveThinking":true},"claude-opus-4-8":{"metadata":{"displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01","structuredOutput":true,"lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-opus-4-8","displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01"},"anthropicAdaptiveThinking":true},"claude-opus-5":{"metadata":{"displayName":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-05","structuredOutput":true,"lastUpdated":"2026-07-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-opus-5","displayName":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-05"},"anthropicAdaptiveThinking":true},"claude-sonnet-4-5":{"metadata":{"displayName":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-07-31","structuredOutput":true,"lastUpdated":"2025-09-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"toggle":true,"offBehavior":"anthropic-thinking-disabled"}},"entry":{"id":"claude-sonnet-4-5","displayName":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-07-31"},"anthropicAdaptiveThinking":false},"claude-sonnet-4-5-20250929":{"metadata":{"displayName":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-07-31","structuredOutput":true,"lastUpdated":"2025-09-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"toggle":true,"offBehavior":"anthropic-thinking-disabled"}},"entry":{"id":"claude-sonnet-4-5-20250929","displayName":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-07-31"},"anthropicAdaptiveThinking":false},"claude-sonnet-4-6":{"metadata":{"displayName":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-sonnet-4-6","displayName":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-08-31"},"anthropicAdaptiveThinking":true},"claude-sonnet-5":{"metadata":{"displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","structuredOutput":true,"lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-sonnet-5","displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"},"anthropicAdaptiveThinking":true},"claude-opus-4-1-20250805":{"metadata":{"thinkingOptions":{"toggle":true,"offBehavior":"anthropic-thinking-disabled"}},"entry":{"id":"claude-opus-4-1-20250805","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"]},"anthropicAdaptiveThinking":false}}},"kimi-coding-plan":{"baseUrl":"https://api.kimi.com/coding/v1","label":"Kimi Coding Plan","authKind":"api_key","runtimeAdapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"protocolAdapters":{"openai-chat-completions":{"kind":"openai-compatible","name":"provider","normalizeUsage":true,"normalizeBaseUrl":true}},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["k3","kimi-for-coding"],"models":{"k3":{"metadata":{"displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"k3","displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"k3-256k":{"metadata":{"displayName":"Kimi K3-256K","description":"256K-context version of Kimi K3, reducing token consumption for shorter coding sessions","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"k3-256k","displayName":"Kimi K3-256K","description":"256K-context version of Kimi K3, reducing token consumption for shorter coding sessions","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":262144,"defaultContextWindow":262144}},"kimi-for-coding":{"metadata":{"displayName":"kimi-for-coding","description":"Kimi coding model with more efficient thinking and up to 1M context, available through Kimi Code","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":32768,"lastUpdated":"2026-09-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-for-coding","displayName":"kimi-for-coding","description":"Kimi coding model with more efficient thinking and up to 1M context, available through Kimi Code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"kimi-for-coding-highspeed":{"metadata":{"displayName":"Kimi For Coding HighSpeed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-for-coding-highspeed","displayName":"Kimi For Coding HighSpeed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}}}},"minimax-coding-plan":{"baseUrl":"https://api.minimax.io/anthropic","label":"MiniMax Coding Plan","authKind":"api_key","runtimeAdapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["MiniMax-M3","MiniMax-M2","MiniMax-M2.1","MiniMax-M2.5","MiniMax-M2.5-highspeed","MiniMax-M2.7","MiniMax-M2.7-highspeed"],"models":{"MiniMax-M2":{"metadata":{"displayName":"MiniMax-M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2025-10-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2","displayName":"MiniMax-M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.1":{"metadata":{"displayName":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2025-12-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.1","displayName":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.5","displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.5-highspeed":{"metadata":{"displayName":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.5-highspeed","displayName":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.7":{"metadata":{"displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.7","displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.7-highspeed":{"metadata":{"displayName":"MiniMax-M2.7-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.7-highspeed","displayName":"MiniMax-M2.7-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":512000,"lastUpdated":"2026-06-25","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"MiniMax-M3","displayName":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}}}},"tencent-coding-plan":{"baseUrl":"https://api.lkeap.cloud.tencent.com/coding/v3","label":"Tencent Coding Plan (China)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["tc-code-latest","glm-5","minimax-m2.5","kimi-k2.5"],"models":{"glm-5":{"metadata":{"displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":16384,"lastUpdated":"2026-02-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5","displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"hunyuan-2.0-instruct":{"metadata":{"displayName":"Tencent HY 2.0 Instruct","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"lastUpdated":"2026-03-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hunyuan-2.0-instruct","displayName":"Tencent HY 2.0 Instruct","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"hunyuan-2.0-thinking":{"metadata":{"displayName":"Tencent HY 2.0 Think","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"lastUpdated":"2026-03-08","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hunyuan-2.0-thinking","displayName":"Tencent HY 2.0 Think","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"hunyuan-t1":{"metadata":{"displayName":"Hunyuan-T1","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"lastUpdated":"2026-03-08","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hunyuan-t1","displayName":"Hunyuan-T1","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"hunyuan-turbos":{"metadata":{"displayName":"Hunyuan-TurboS","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"lastUpdated":"2026-03-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hunyuan-turbos","displayName":"Hunyuan-TurboS","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"kimi-k2.5":{"metadata":{"displayName":"Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","lastUpdated":"2026-01-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.5","displayName":"Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"minimax-m2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":32768,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax-m2.5","displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"tc-code-latest":{"metadata":{"displayName":"Auto","description":"Automatic model router for matching prompts to suitable backends and budgets","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"lastUpdated":"2026-03-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tc-code-latest","displayName":"Auto","description":"Automatic model router for matching prompts to suitable backends and budgets","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}}}},"volcengine-coding-plan":{"baseUrl":"https://ark.cn-beijing.volces.com/api/coding/v3","label":"Volcengine Ark Coding Plan (China)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["ark-code-latest","doubao-seed-2.0-code","doubao-seed-2.0-pro","doubao-seed-2.0-lite","doubao-seed-code","minimax-m2.7","minimax-m3","glm-5.2","deepseek-v4-flash","deepseek-v4-pro","kimi-k2.6","kimi-k2.7-code"],"models":{"ark-code-latest":{"metadata":{"displayName":"Ark Code Latest","lifecycle":"active","capabilities":{"reasoning":true,"functionCalling":true,"vision":false}},"entry":{"id":"ark-code-latest","displayName":"Ark Code Latest","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"doubao-seed-2.0-code":{"metadata":{"displayName":"Doubao Seed 2.0 Code","lifecycle":"active","capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"doubao-seed-2.0-code","displayName":"Doubao Seed 2.0 Code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"doubao-seed-2.0-pro":{"metadata":{"displayName":"Doubao Seed 2.0 Pro","lifecycle":"active","capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"doubao-seed-2.0-pro","displayName":"Doubao Seed 2.0 Pro","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"doubao-seed-2.0-lite":{"metadata":{"displayName":"Doubao Seed 2.0 Lite","lifecycle":"active","capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"doubao-seed-2.0-lite","displayName":"Doubao Seed 2.0 Lite","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"doubao-seed-code":{"metadata":{"displayName":"Doubao Seed Code","lifecycle":"active","capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"doubao-seed-code","displayName":"Doubao Seed Code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"minimax-m2.7":{"metadata":{"displayName":"MiniMax-M2.7","lifecycle":"active","contextWindow":200000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":false}},"entry":{"id":"minimax-m2.7","displayName":"MiniMax-M2.7","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}},"minimax-m3":{"metadata":{"displayName":"MiniMax-M3","lifecycle":"active","contextWindow":512000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"minimax-m3","displayName":"MiniMax-M3","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":512000,"defaultContextWindow":512000}},"glm-5.2":{"metadata":{"displayName":"GLM-5.2","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":false}},"entry":{"id":"glm-5.2","displayName":"GLM-5.2","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}},"deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek-V4-Flash","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":384000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":false}},"entry":{"id":"deepseek-v4-flash","displayName":"DeepSeek-V4-Flash","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}},"deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek-V4-Pro","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":384000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":false}},"entry":{"id":"deepseek-v4-pro","displayName":"DeepSeek-V4-Pro","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}},"kimi-k2.6":{"metadata":{"displayName":"Kimi-K2.6","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"kimi-k2.6","displayName":"Kimi-K2.6","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"kimi-k2.7-code":{"metadata":{"displayName":"Kimi-K2.7-Code","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"kimi-k2.7-code","displayName":"Kimi-K2.7-Code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}}}},"volcengine-agent-plan":{"baseUrl":"https://ark.cn-beijing.volces.com/api/plan/v3","label":"Volcengine Ark Agent Plan (China)","authKind":"api_key","runtimeAdapter":{"kind":"openai","apiProtocol":"openai-responses","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":false,"modelDiscovery":{"kind":"fallback","reason":"Agent Plan model discovery is a control-plane API that requires AK/SK signing; the plan API key reaches only the inference data plane"},"fallbackModels":["ark-code-latest","glm-5.3","glm-5.3-flash","doubao-seed-2.0-mini","doubao-seed-2.0-lite","deepseek-v4-flash","doubao-seed-2.1-turbo","doubao-seed-evolving","doubao-seed-2.0-code","doubao-seed-2.0-pro","minimax-m2.7","minimax-m3","glm-5.2","glm-latest","kimi-k2.6","kimi-k2.7-code","deepseek-v4-pro","kimi-k3"],"models":{"ark-code-latest":{"metadata":{"displayName":"Ark Code Latest","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"ark-code-latest","displayName":"Ark Code Latest","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"glm-5.3":{"metadata":{"displayName":"GLM-5.3","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true}},"entry":{"id":"glm-5.3","displayName":"GLM-5.3","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}},"doubao-seed-2.0-mini":{"metadata":{"displayName":"Doubao Seed 2.0 Mini","lifecycle":"active","contextWindow":256000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"doubao-seed-2.0-mini","displayName":"Doubao Seed 2.0 Mini","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"doubao-seed-2.0-lite":{"metadata":{"displayName":"Doubao Seed 2.0 Lite","lifecycle":"active","contextWindow":256000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"doubao-seed-2.0-lite","displayName":"Doubao Seed 2.0 Lite","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek-V4-Flash","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":384000,"capabilities":{"reasoning":true,"functionCalling":true}},"entry":{"id":"deepseek-v4-flash","displayName":"DeepSeek-V4-Flash","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}},"doubao-seed-2.1-turbo":{"metadata":{"displayName":"Doubao Seed 2.1 Turbo","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"doubao-seed-2.1-turbo","displayName":"Doubao Seed 2.1 Turbo","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"doubao-seed-evolving":{"metadata":{"displayName":"Doubao Seed Evolving","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":256000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"doubao-seed-evolving","displayName":"Doubao Seed Evolving","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}},"doubao-seed-2.0-code":{"metadata":{"displayName":"Doubao Seed 2.0 Code","lifecycle":"deprecated","contextWindow":256000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true}},"entry":{"id":"doubao-seed-2.0-code","displayName":"Doubao Seed 2.0 Code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"doubao-seed-2.0-pro":{"metadata":{"displayName":"Doubao Seed 2.0 Pro","lifecycle":"deprecated","contextWindow":256000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true}},"entry":{"id":"doubao-seed-2.0-pro","displayName":"Doubao Seed 2.0 Pro","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"minimax-m2.7":{"metadata":{"displayName":"MiniMax-M2.7","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true}},"entry":{"id":"minimax-m2.7","displayName":"MiniMax-M2.7","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}},"minimax-m3":{"metadata":{"displayName":"MiniMax-M3","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"minimax-m3","displayName":"MiniMax-M3","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}},"glm-5.2":{"metadata":{"displayName":"GLM-5.2","lifecycle":"deprecated","contextWindow":1024000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true}},"entry":{"id":"glm-5.2","displayName":"GLM-5.2","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}},"glm-latest":{"metadata":{"displayName":"GLM Latest","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true}},"entry":{"id":"glm-latest","displayName":"GLM Latest","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}},"glm-5.3-flash":{"metadata":{"displayName":"GLM-5.3-Flash","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"glm-5.3-flash","displayName":"GLM-5.3-Flash","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}},"kimi-k2.6":{"metadata":{"displayName":"Kimi-K2.6","lifecycle":"deprecated","contextWindow":256000,"maxOutputTokens":32000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"kimi-k2.6","displayName":"Kimi-K2.6","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"kimi-k2.7-code":{"metadata":{"displayName":"Kimi-K2.7-Code","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"kimi-k2.7-code","displayName":"Kimi-K2.7-Code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek-V4-Pro","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":384000,"capabilities":{"reasoning":true,"functionCalling":true}},"entry":{"id":"deepseek-v4-pro","displayName":"DeepSeek-V4-Pro","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}},"kimi-k3":{"metadata":{"displayName":"Kimi-K3","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"kimi-k3","displayName":"Kimi-K3","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}}}},"tencent-token-plan":{"baseUrl":"https://api.lkeap.cloud.tencent.com/plan/v3","label":"Tencent Token Plan","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["tc-code-latest","deepseek-v4-flash-202605","deepseek-v4-pro-202606","minimax-m2.5","minimax-m2.7","glm-5","glm-5.1","kimi-k2.5","hy3","hy3-preview"],"models":{"hy3":{"metadata":{"displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":256000,"inputLimit":192000,"maxOutputTokens":128000,"lastUpdated":"2026-07-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hy3","displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high"],"contextWindow":256000,"inputLimit":192000,"defaultContextWindow":256000,"defaultInputLimit":192000}},"hy4-preview":{"metadata":{"displayName":"Hy4 preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":64000,"lastUpdated":"2026-08-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hy4-preview","displayName":"Hy4 preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high"],"contextWindow":1024000,"defaultContextWindow":1024000}},"hy3-preview":{"metadata":{"thinkingOptions":{"efforts":["low","medium","high"]}},"entry":{"id":"hy3-preview","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"]}},"tc-code-latest":{"metadata":{},"entry":{"id":"tc-code-latest","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"deepseek-v4-flash-202605":{"metadata":{},"entry":{"id":"deepseek-v4-flash-202605","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"deepseek-v4-pro-202606":{"metadata":{},"entry":{"id":"deepseek-v4-pro-202606","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"minimax-m2.5":{"metadata":{},"entry":{"id":"minimax-m2.5","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"minimax-m2.7":{"metadata":{},"entry":{"id":"minimax-m2.7","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"glm-5":{"metadata":{},"entry":{"id":"glm-5","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"glm-5.1":{"metadata":{},"entry":{"id":"glm-5.1","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"kimi-k2.5":{"metadata":{},"entry":{"id":"kimi-k2.5","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}}}},"openai":{"baseUrl":"https://api.openai.com/v1","label":"OpenAI","authKind":"api_key","runtimeAdapter":{"kind":"openai","applyPatchProtocol":"openai-structured","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["gpt-5.5","gpt-5.5-pro","gpt-5.4","gpt-5.4-mini","gpt-5"],"models":{"chatgpt-image-latest":{"metadata":{"displayName":"chatgpt-image-latest","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-12-16","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"chatgpt-image-latest","displayName":"chatgpt-image-latest","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"gpt-3.5-turbo":{"metadata":{"displayName":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"deprecated","contextWindow":16385,"maxOutputTokens":4096,"knowledgeCutoff":"2021-09-01","structuredOutput":false,"lastUpdated":"2023-11-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"gpt-3.5-turbo","displayName":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16385,"defaultContextWindow":16385,"knowledgeCutoff":"2021-09-01"}},"gpt-4":{"metadata":{"displayName":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"deprecated","contextWindow":8192,"maxOutputTokens":8192,"knowledgeCutoff":"2023-11","structuredOutput":false,"lastUpdated":"2024-04-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"gpt-4","displayName":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2023-11"}},"gpt-4-turbo":{"metadata":{"displayName":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-12","structuredOutput":false,"lastUpdated":"2024-04-09","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-4-turbo","displayName":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-12"}},"gpt-4.1":{"metadata":{"displayName":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","lifecycle":"active","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-4.1","displayName":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"gpt-4.1-mini":{"metadata":{"displayName":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","lifecycle":"active","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-4.1-mini","displayName":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"gpt-4.1-nano":{"metadata":{"displayName":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","lifecycle":"deprecated","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-4.1-nano","displayName":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"gpt-4o":{"metadata":{"displayName":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-08-06","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-4o","displayName":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"gpt-4o-2024-05-13":{"metadata":{"displayName":"GPT-4o (2024-05-13)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-05-13","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-4o-2024-05-13","displayName":"GPT-4o (2024-05-13)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"gpt-4o-2024-08-06":{"metadata":{"displayName":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-08-06","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-4o-2024-08-06","displayName":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"gpt-4o-2024-11-20":{"metadata":{"displayName":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-11-20","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-4o-2024-11-20","displayName":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"gpt-4o-mini":{"metadata":{"displayName":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-07-18","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-4o-mini","displayName":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"gpt-5":{"metadata":{"displayName":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5","displayName":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"gpt-5-mini":{"metadata":{"displayName":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-05-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5-mini","displayName":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-05-30"}},"gpt-5-nano":{"metadata":{"displayName":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-05-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5-nano","displayName":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-05-30"}},"gpt-5-pro":{"metadata":{"displayName":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":272000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-10-06","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5-pro","displayName":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"gpt-5.1":{"metadata":{"displayName":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.1","displayName":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"gpt-5.2":{"metadata":{"displayName":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.2","displayName":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.2-chat-latest":{"metadata":{"displayName":"GPT-5.2 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.2-chat-latest","displayName":"GPT-5.2 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium"],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.2-pro":{"metadata":{"displayName":"GPT-5.2 Pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":false,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.2-pro","displayName":"GPT-5.2 Pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.3-chat-latest":{"metadata":{"displayName":"GPT-5.3 Chat (latest)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-03","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.3-chat-latest","displayName":"GPT-5.3 Chat (latest)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.3-codex":{"metadata":{"displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-02-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.3-codex","displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.3-codex-spark":{"metadata":{"displayName":"GPT-5.3 Codex Spark","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":128000,"inputLimit":100000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-02-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.3-codex-spark","displayName":"GPT-5.3 Codex Spark","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":128000,"inputLimit":100000,"defaultContextWindow":128000,"defaultInputLimit":100000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4":{"metadata":{"displayName":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.4","displayName":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4-mini":{"metadata":{"displayName":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.4-mini","displayName":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4-nano":{"metadata":{"displayName":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.4-nano","displayName":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4-pro":{"metadata":{"displayName":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":false,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.4-pro","displayName":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.5":{"metadata":{"displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.5","displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-12-01"}},"gpt-5.5-pro":{"metadata":{"displayName":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.5-pro","displayName":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-12-01"}},"gpt-5.6":{"metadata":{"displayName":"GPT-5.6","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.6","displayName":"GPT-5.6","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"gpt-5.6-luna":{"metadata":{"displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.6-luna","displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"gpt-5.6-sol":{"metadata":{"displayName":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.6-sol","displayName":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"gpt-5.6-terra":{"metadata":{"displayName":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.6-terra","displayName":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"gpt-6-astra":{"metadata":{"displayName":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-04-30","structuredOutput":true,"lastUpdated":"2026-09-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-6-astra","displayName":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-04-30"}},"gpt-image-1":{"metadata":{"displayName":"gpt-image-1","description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","lifecycle":"deprecated","lastUpdated":"2025-04-24","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["image"]}},"entry":{"id":"gpt-image-1","displayName":"gpt-image-1","description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"gpt-image-1-mini":{"metadata":{"displayName":"gpt-image-1-mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-09-26","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"gpt-image-1-mini","displayName":"gpt-image-1-mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"gpt-image-1.5":{"metadata":{"displayName":"gpt-image-1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-11-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"gpt-image-1.5","displayName":"gpt-image-1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"gpt-image-2":{"metadata":{"displayName":"gpt-image-2","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["image"]}},"entry":{"id":"gpt-image-2","displayName":"gpt-image-2","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"gpt-realtime-2.1":{"metadata":{"displayName":"GPT-Realtime-2.1","description":"Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior","lifecycle":"active","contextWindow":128000,"inputLimit":96000,"maxOutputTokens":32000,"knowledgeCutoff":"2024-09-30","structuredOutput":false,"lastUpdated":"2026-07-06","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","audio","image"],"output":["text","audio"]}},"entry":{"id":"gpt-realtime-2.1","displayName":"GPT-Realtime-2.1","description":"Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":128000,"inputLimit":96000,"defaultContextWindow":128000,"defaultInputLimit":96000,"knowledgeCutoff":"2024-09-30"}},"o1":{"metadata":{"displayName":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-12-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"o1","displayName":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2023-09"}},"o1-pro":{"metadata":{"displayName":"o1-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2025-03-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"o1-pro","displayName":"o1-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2023-09"}},"o3":{"metadata":{"displayName":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"o3","displayName":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"o3-mini":{"metadata":{"displayName":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-01-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"o3-mini","displayName":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"o3-pro":{"metadata":{"displayName":"o3-pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-06-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"o3-pro","displayName":"o3-pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"o4-mini":{"metadata":{"displayName":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"o4-mini","displayName":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"text-embedding-3-large":{"metadata":{"displayName":"text-embedding-3-large","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8191,"maxOutputTokens":3072,"knowledgeCutoff":"2024-01","lastUpdated":"2024-01-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"text-embedding-3-large","displayName":"text-embedding-3-large","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8191,"defaultContextWindow":8191,"knowledgeCutoff":"2024-01"}},"text-embedding-3-small":{"metadata":{"displayName":"text-embedding-3-small","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8191,"maxOutputTokens":1536,"knowledgeCutoff":"2024-01","lastUpdated":"2024-01-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"text-embedding-3-small","displayName":"text-embedding-3-small","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8191,"defaultContextWindow":8191,"knowledgeCutoff":"2024-01"}},"text-embedding-ada-002":{"metadata":{"displayName":"text-embedding-ada-002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"knowledgeCutoff":"2022-12","lastUpdated":"2022-12-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"text-embedding-ada-002","displayName":"text-embedding-ada-002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2022-12"}},"gpt-6-sol":{"metadata":{"displayName":"GPT-6 Sol","thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]}},"entry":{"id":"gpt-6-sol","displayName":"GPT-6 Sol","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high","xhigh","max"]}},"gpt-6-luna":{"metadata":{"displayName":"GPT-6 Luna","thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]}},"entry":{"id":"gpt-6-luna","displayName":"GPT-6 Luna","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high","xhigh","max"]}}}},"google":{"baseUrl":"https://generativelanguage.googleapis.com/v1beta","label":"Google Gemini","authKind":"api_key","runtimeAdapter":{"kind":"google"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["gemini-3.5-flash","gemini-3.1-pro-preview","gemini-2.5-pro","gemini-2.5-flash"],"models":{"deep-research-max-preview-04-2026":{"metadata":{"displayName":"Deep Research Max Preview (Apr-21-2026)","description":"Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text","image"]}},"entry":{"id":"deep-research-max-preview-04-2026","displayName":"Deep Research Max Preview (Apr-21-2026)","description":"Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"deep-research-preview-04-2026":{"metadata":{"displayName":"Deep Research Preview (Apr-21-2026)","description":"Agentic model for autonomous multi-step research, synthesis, and cited reports","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text","image"]}},"entry":{"id":"deep-research-preview-04-2026","displayName":"Deep Research Preview (Apr-21-2026)","description":"Agentic model for autonomous multi-step research, synthesis, and cited reports","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"gemini-2.5-computer-use-preview-10-2025":{"metadata":{"displayName":"Gemini 2.5 Computer Use Preview 10-2025","description":"Specialized Gemini 2.5 model for browser-control agents that automate UI tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","lastUpdated":"2025-10-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gemini-2.5-computer-use-preview-10-2025","displayName":"Gemini 2.5 Computer Use Preview 10-2025","description":"Specialized Gemini 2.5 model for browser-control agents that automate UI tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"gemini-2.5-flash":{"metadata":{"displayName":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-06-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true,"offBehavior":"google-thinking-budget-zero"},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]}},"entry":{"id":"gemini-2.5-flash","displayName":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-2.5-flash-image":{"metadata":{"displayName":"Nano Banana","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","lifecycle":"active","contextWindow":32768,"maxOutputTokens":32768,"knowledgeCutoff":"2024-06","lastUpdated":"2025-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"gemini-2.5-flash-image","displayName":"Nano Banana","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-06"}},"gemini-2.5-flash-lite":{"metadata":{"displayName":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-06-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]}},"entry":{"id":"gemini-2.5-flash-lite","displayName":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-2.5-flash-preview-tts":{"metadata":{"displayName":"Gemini 2.5 Flash Preview TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":16384,"knowledgeCutoff":"2025-01","lastUpdated":"2025-05-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"gemini-2.5-flash-preview-tts","displayName":"Gemini 2.5 Flash Preview TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2025-01"}},"gemini-2.5-pro":{"metadata":{"displayName":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-06-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]}},"entry":{"id":"gemini-2.5-pro","displayName":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-2.5-pro-preview-tts":{"metadata":{"displayName":"Gemini 2.5 Pro Preview TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":16384,"knowledgeCutoff":"2025-01","lastUpdated":"2025-05-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"gemini-2.5-pro-preview-tts","displayName":"Gemini 2.5 Pro Preview TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2025-01"}},"gemini-3-flash-preview":{"metadata":{"displayName":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-12-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-3-flash-preview","displayName":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-3-pro-image":{"metadata":{"displayName":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["low","high"]},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"gemini-3-pro-image","displayName":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"gemini-3-pro-image-preview":{"metadata":{"displayName":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","lastUpdated":"2025-11-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"gemini-3-pro-image-preview","displayName":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"gemini-3.1-flash-image":{"metadata":{"displayName":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":65536,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["minimal","high"]},"modalities":{"input":["text","image","video","pdf"],"output":["text","image"]}},"entry":{"id":"gemini-3.1-flash-image","displayName":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","high"],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-01"}},"gemini-3.1-flash-image-preview":{"metadata":{"displayName":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":65536,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","lastUpdated":"2026-02-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["minimal","high"]},"modalities":{"input":["text","image","pdf"],"output":["text","image"]}},"entry":{"id":"gemini-3.1-flash-image-preview","displayName":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","high"],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-01"}},"gemini-3.1-flash-lite":{"metadata":{"displayName":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-3.1-flash-lite","displayName":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-3.1-flash-lite-image":{"metadata":{"displayName":"Nano Banana 2 Lite","description":"Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing","lifecycle":"active","contextWindow":65536,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":false,"lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","high"]},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"gemini-3.1-flash-lite-image","displayName":"Nano Banana 2 Lite","description":"Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","high"],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-01"}},"gemini-3.1-flash-lite-preview":{"metadata":{"displayName":"Gemini 3.1 Flash Lite Preview","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-03-03","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-3.1-flash-lite-preview","displayName":"Gemini 3.1 Flash Lite Preview","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-3.1-flash-live-preview":{"metadata":{"displayName":"Gemini 3.1 Flash Live Preview","description":"High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":false,"lastUpdated":"2026-03-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio"],"output":["text","audio"]}},"entry":{"id":"gemini-3.1-flash-live-preview","displayName":"Gemini 3.1 Flash Live Preview","description":"High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"gemini-3.1-flash-tts-preview":{"metadata":{"displayName":"Gemini 3.1 Flash TTS Preview","description":"Low-latency speech generation with steerable prompts and expressive audio tags","lifecycle":"active","contextWindow":8192,"maxOutputTokens":16384,"knowledgeCutoff":"2025-01","lastUpdated":"2026-04-15","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"gemini-3.1-flash-tts-preview","displayName":"Gemini 3.1 Flash TTS Preview","description":"Low-latency speech generation with steerable prompts and expressive audio tags","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2025-01"}},"gemini-3.1-pro-preview":{"metadata":{"displayName":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-02-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-3.1-pro-preview","displayName":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-3.1-pro-preview-customtools":{"metadata":{"displayName":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-02-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-3.1-pro-preview-customtools","displayName":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-3.5-flash":{"metadata":{"displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-3.5-flash","displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-3.5-flash-lite":{"metadata":{"displayName":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-07-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-3.5-flash-lite","displayName":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2026-03"}},"gemini-3.5-live-translate-preview":{"metadata":{"displayName":"Gemini 3.5 Live Translate Preview","description":"Low-latency audio-to-audio model for real-time speech translation across 70+ languages","lifecycle":"active","contextWindow":16384,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","lastUpdated":"2026-06-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["audio","text"]}},"entry":{"id":"gemini-3.5-live-translate-preview","displayName":"Gemini 3.5 Live Translate Preview","description":"Low-latency audio-to-audio model for real-time speech translation across 70+ languages","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16384,"defaultContextWindow":16384,"knowledgeCutoff":"2025-01"}},"gemini-3.6-flash":{"metadata":{"displayName":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-07-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-3.6-flash","displayName":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2026-03"}},"gemini-3.7-flash":{"metadata":{"displayName":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-08-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-3.7-flash","displayName":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2026-03"}},"gemini-3.8-flash":{"metadata":{"displayName":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-3.8-flash","displayName":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576}},"gemini-embedding-001":{"metadata":{"displayName":"Gemini Embedding 001","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":2048,"maxOutputTokens":1,"knowledgeCutoff":"2025-05","lastUpdated":"2025-05-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"gemini-embedding-001","displayName":"Gemini Embedding 001","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":2048,"defaultContextWindow":2048,"knowledgeCutoff":"2025-05"}},"gemini-embedding-2":{"metadata":{"displayName":"Gemini Embedding 2","description":"Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1,"knowledgeCutoff":"2025-11","lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]}},"entry":{"id":"gemini-embedding-2","displayName":"Gemini Embedding 2","description":"Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2025-11"}},"gemini-flash-latest":{"metadata":{"displayName":"Gemini Flash Latest","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-08-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-flash-latest","displayName":"Gemini Flash Latest","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2026-03"}},"gemini-flash-lite-latest":{"metadata":{"displayName":"Gemini Flash-Lite Latest","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-07-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-flash-lite-latest","displayName":"Gemini Flash-Lite Latest","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2026-03"}},"gemini-omni-flash-preview":{"metadata":{"displayName":"Gemini Omni Flash Preview","description":"Video generation and editing model for fast, conversational text- and image-to-video workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"modalities":{"input":["text","image","video"],"output":["video"]}},"entry":{"id":"gemini-omni-flash-preview","displayName":"Gemini Omni Flash Preview","description":"Video generation and editing model for fast, conversational text- and image-to-video workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"gemma-4-26b-a4b-it":{"metadata":{"displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gemma-4-26b-a4b-it","displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"gemma-4-31b-it":{"metadata":{"displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gemma-4-31b-it","displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"lyria-3-clip-preview":{"metadata":{"displayName":"Lyria 3 Clip Preview","description":"Music generation model for short 30-second clips, loops, and previews from text or image prompts","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"structuredOutput":false,"lastUpdated":"2026-03-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","audio"]}},"entry":{"id":"lyria-3-clip-preview","displayName":"Lyria 3 Clip Preview","description":"Music generation model for short 30-second clips, loops, and previews from text or image prompts","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}},"lyria-3-pro-preview":{"metadata":{"displayName":"Lyria 3 Pro Preview","description":"Music generation model for full-length songs from text or images with vocals and structure","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"structuredOutput":false,"lastUpdated":"2026-03-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","audio"]}},"entry":{"id":"lyria-3-pro-preview","displayName":"Lyria 3 Pro Preview","description":"Music generation model for full-length songs from text or images with vocals and structure","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}},"veo-3.1-fast-generate-preview":{"metadata":{"displayName":"Veo 3.1 fast","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","contextWindow":480,"maxOutputTokens":8192,"lastUpdated":"2026-01-01","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","video"],"output":["video"]}},"entry":{"id":"veo-3.1-fast-generate-preview","displayName":"Veo 3.1 fast","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":480,"defaultContextWindow":480}},"veo-3.1-generate-preview":{"metadata":{"displayName":"Veo 3.1","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"beta","contextWindow":480,"maxOutputTokens":8192,"lastUpdated":"2026-01","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["video"]}},"entry":{"id":"veo-3.1-generate-preview","displayName":"Veo 3.1","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":480,"defaultContextWindow":480}},"veo-3.1-lite-generate-preview":{"metadata":{"displayName":"Veo 3.1 lite","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","contextWindow":480,"maxOutputTokens":8192,"lastUpdated":"2026-03-31","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["video"]}},"entry":{"id":"veo-3.1-lite-generate-preview","displayName":"Veo 3.1 lite","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":480,"defaultContextWindow":480}}}},"deepseek":{"baseUrl":"https://api.deepseek.com","label":"DeepSeek","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider","applyPatchProtocol":"codex-v4a-freeform","responses":{"adapter":"open-responses","reasoningReplay":"plaintext-content"}},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["deepseek-v4-flash","deepseek-v4-flash-vision-exp","deepseek-v4-pro","deepseek-reasoner","deepseek-chat"],"models":{"deepseek-flash":{"metadata":{"displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-flash","displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-08-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true,"webSearch":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash","displayName":"DeepSeek V4 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-flash-vision-exp":{"metadata":{"displayName":"DeepSeek-V4-Flash-Vision-Exp","description":"Experimental DeepSeek V4 Flash model for image understanding and multimodal agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-08-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true,"webSearch":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash-vision-exp","displayName":"DeepSeek-V4-Flash-Vision-Exp","description":"Experimental DeepSeek V4 Flash model for image understanding and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"webSearch":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-pro","displayName":"DeepSeek V4 Pro","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"deepseek-reasoner":{"metadata":{},"entry":{"id":"deepseek-reasoner","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"deepseek-chat":{"metadata":{},"entry":{"id":"deepseek-chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}}}},"moonshot":{"baseUrl":"https://api.moonshot.cn/v1","label":"Moonshot","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["kimi-k2.6","kimi-k2.7-code","kimi-k2.7-code-highspeed","kimi-k3"],"models":{"kimi-k2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.6","displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k2.7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.7-code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k2.7-code-highspeed":{"metadata":{"displayName":"Kimi K2.7 Code HighSpeed","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.7-code-highspeed","displayName":"Kimi K2.7 Code HighSpeed","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k3":{"metadata":{"displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k3","displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}}}},"moonshot-global":{"baseUrl":"https://api.moonshot.ai/v1","label":"Moonshot Global","authKind":"api_key","runtimeAdapter":{"kind":"openai","apiProtocol":"openai-responses","responses":{"adapter":"open-responses","reasoningReplay":"plaintext-summary"}},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["kimi-k3","kimi-k2.6","kimi-k2.7-code","kimi-k2.7-code-highspeed"],"models":{"kimi-k2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.6","displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k2.7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.7-code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k2.7-code-highspeed":{"metadata":{"displayName":"Kimi K2.7 Code HighSpeed","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.7-code-highspeed","displayName":"Kimi K2.7 Code HighSpeed","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k3":{"metadata":{"displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k3","displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}}}},"zai-coding-plan":{"baseUrl":"https://api.z.ai/api/coding/paas/v4","label":"Z.AI Coding Plan","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["glm-5.2","glm-5.1","glm-5-turbo","glm-4.7","glm-4.5-air"],"models":{"glm-4.7":{"metadata":{"displayName":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2025-12-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.7","displayName":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"glm-5-turbo":{"metadata":{"displayName":"GLM-5-Turbo","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":200000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-03-16","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5-turbo","displayName":"GLM-5-Turbo","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}},"glm-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5.2-highspeed":{"metadata":{"displayName":"GLM-5.2 Highspeed","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.2-highspeed","displayName":"GLM-5.2 Highspeed","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5.3":{"metadata":{"displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.3","displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5.3-flash":{"metadata":{"displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"glm-5.3-flash","displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5.3-highspeed":{"metadata":{"displayName":"GLM-5.3 Highspeed","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.3-highspeed","displayName":"GLM-5.3 Highspeed","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5.1":{"metadata":{"thinkingOptions":{"toggle":true}},"entry":{"id":"glm-5.1","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"glm-5v-turbo":{"metadata":{"thinkingOptions":{"toggle":true}},"entry":{"id":"glm-5v-turbo","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"glm-4.5-air":{"metadata":{"thinkingOptions":{"toggle":true}},"entry":{"id":"glm-4.5-air","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}}}},"MiniMax":{"baseUrl":"https://api.minimax.io/anthropic/v1","label":"MiniMax","authKind":"api_key","runtimeAdapter":{"kind":"anthropic","auth":"bearer","normalizeBaseUrl":false},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["MiniMax-M3"],"models":{"MiniMax-M2":{"metadata":{"displayName":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2025-10-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2","displayName":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.1":{"metadata":{"displayName":"MiniMax-M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2025-12-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.1","displayName":"MiniMax-M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.5","displayName":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.5-highspeed":{"metadata":{"displayName":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.5-highspeed","displayName":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.7":{"metadata":{"displayName":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.7","displayName":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.7-highspeed":{"metadata":{"displayName":"MiniMax-M2.7-highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.7-highspeed","displayName":"MiniMax-M2.7-highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":512000,"lastUpdated":"2026-06-25","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"MiniMax-M3","displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}}}},"MiniMax-cn":{"baseUrl":"https://api.minimaxi.com/anthropic/v1","label":"MiniMax 中国站","authKind":"api_key","runtimeAdapter":{"kind":"anthropic","auth":"bearer","normalizeBaseUrl":false},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["MiniMax-M3"],"models":{"MiniMax-M2":{"metadata":{"displayName":"MiniMax-M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2025-10-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2","displayName":"MiniMax-M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.1":{"metadata":{"displayName":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2025-12-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.1","displayName":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.5","displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.5-highspeed":{"metadata":{"displayName":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.5-highspeed","displayName":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.7":{"metadata":{"displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.7","displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.7-highspeed":{"metadata":{"displayName":"MiniMax-M2.7-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.7-highspeed","displayName":"MiniMax-M2.7-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":512000,"lastUpdated":"2026-06-25","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"MiniMax-M3","displayName":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}}}},"siliconflow":{"baseUrl":"https://api.siliconflow.com/v1","label":"SiliconFlow","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol","query":{"sub_type":"chat"}},"fallbackModels":["moonshotai/Kimi-K2.6","baidu/ERNIE-4.5-300B-A47B","ByteDance-Seed/Seed-OSS-36B-Instruct","deepseek-ai/DeepSeek-R1","deepseek-ai/DeepSeek-V3","deepseek-ai/DeepSeek-V3.1","deepseek-ai/DeepSeek-V3.1-Terminus","deepseek-ai/DeepSeek-V3.2","deepseek-ai/DeepSeek-V3.2-Exp","deepseek-ai/DeepSeek-V4-Flash","deepseek-ai/DeepSeek-V4-Pro","google/gemma-4-26B-A4B-it","google/gemma-4-31B-it","inclusionAI/Ling-flash-2.0","MiniMaxAI/MiniMax-M2.5","moonshotai/Kimi-K2.5","openai/gpt-oss-120b","openai/gpt-oss-20b","Qwen/Qwen2.5-72B-Instruct","Qwen/Qwen2.5-7B-Instruct","Qwen/Qwen3-14B","Qwen/Qwen3-235B-A22B-Thinking-2507","Qwen/Qwen3-30B-A3B-Instruct-2507","Qwen/Qwen3-32B","Qwen/Qwen3-8B","Qwen/Qwen3-Coder-30B-A3B-Instruct","Qwen/Qwen3-Coder-480B-A35B-Instruct","Qwen/Qwen3-VL-235B-A22B-Instruct","Qwen/Qwen3-VL-235B-A22B-Thinking","Qwen/Qwen3-VL-30B-A3B-Instruct","Qwen/Qwen3-VL-30B-A3B-Thinking","Qwen/Qwen3-VL-32B-Instruct","Qwen/Qwen3-VL-32B-Thinking","Qwen/Qwen3-VL-8B-Instruct","Qwen/Qwen3.5-122B-A10B","Qwen/Qwen3.5-27B","Qwen/Qwen3.5-35B-A3B","Qwen/Qwen3.5-397B-A17B","Qwen/Qwen3.5-9B","Qwen/Qwen3.6-27B","Qwen/Qwen3.6-35B-A3B","stepfun-ai/Step-3.5-Flash","tencent/Hunyuan-A13B-Instruct","tencent/Hy3-preview","zai-org/GLM-4.5-Air","zai-org/GLM-5","zai-org/GLM-5.1","zai-org/GLM-5.2","zai-org/GLM-5V-Turbo"],"models":{"baidu/ERNIE-4.5-300B-A47B":{"metadata":{"displayName":"baidu/ERNIE-4.5-300B-A47B","description":"Tool-capable chat model for instruction following and agentic application workflows","lifecycle":"active","contextWindow":131000,"maxOutputTokens":131000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"baidu/ERNIE-4.5-300B-A47B","displayName":"baidu/ERNIE-4.5-300B-A47B","description":"Tool-capable chat model for instruction following and agentic application workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000}},"ByteDance-Seed/Seed-OSS-36B-Instruct":{"metadata":{"displayName":"ByteDance-Seed/Seed-OSS-36B-Instruct","description":"Tool-capable chat model for instruction following and agentic application workflows","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"ByteDance-Seed/Seed-OSS-36B-Instruct","displayName":"ByteDance-Seed/Seed-OSS-36B-Instruct","description":"Tool-capable chat model for instruction following and agentic application workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"deepseek-ai/DeepSeek-R1":{"metadata":{"displayName":"deepseek-ai/DeepSeek-R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","lifecycle":"active","contextWindow":164000,"maxOutputTokens":164000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-R1","displayName":"deepseek-ai/DeepSeek-R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":164000,"defaultContextWindow":164000}},"deepseek-ai/DeepSeek-V3":{"metadata":{"displayName":"deepseek-ai/DeepSeek-V3","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":164000,"maxOutputTokens":164000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3","displayName":"deepseek-ai/DeepSeek-V3","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":164000,"defaultContextWindow":164000}},"deepseek-ai/DeepSeek-V3.1":{"metadata":{"displayName":"deepseek-ai/DeepSeek-V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":164000,"maxOutputTokens":164000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3.1","displayName":"deepseek-ai/DeepSeek-V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":164000,"defaultContextWindow":164000}},"deepseek-ai/DeepSeek-V3.1-Terminus":{"metadata":{"displayName":"deepseek-ai/DeepSeek-V3.1-Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":164000,"maxOutputTokens":164000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3.1-Terminus","displayName":"deepseek-ai/DeepSeek-V3.1-Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":164000,"defaultContextWindow":164000}},"deepseek-ai/DeepSeek-V3.2":{"metadata":{"displayName":"deepseek-ai/DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":164000,"maxOutputTokens":164000,"structuredOutput":true,"lastUpdated":"2025-12-03","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3.2","displayName":"deepseek-ai/DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":164000,"defaultContextWindow":164000}},"deepseek-ai/DeepSeek-V3.2-Exp":{"metadata":{"displayName":"deepseek-ai/DeepSeek-V3.2-Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":164000,"maxOutputTokens":164000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3.2-Exp","displayName":"deepseek-ai/DeepSeek-V3.2-Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":164000,"defaultContextWindow":164000}},"deepseek-ai/DeepSeek-V4-Flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Flash","displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-ai/DeepSeek-V4-Pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Pro","displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"google/gemma-4-26B-A4B-it":{"metadata":{"displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"google/gemma-4-26B-A4B-it","displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"google/gemma-4-31B-it":{"metadata":{"displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"google/gemma-4-31B-it","displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"inclusionAI/Ling-flash-2.0":{"metadata":{"displayName":"inclusionAI/Ling-flash-2.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":131000,"maxOutputTokens":131000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionAI/Ling-flash-2.0","displayName":"inclusionAI/Ling-flash-2.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000}},"MiniMaxAI/MiniMax-M2.5":{"metadata":{"displayName":"MiniMaxAI/MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":197000,"maxOutputTokens":131000,"structuredOutput":false,"lastUpdated":"2026-06-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M2.5","displayName":"MiniMaxAI/MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":197000,"defaultContextWindow":197000}},"moonshotai/Kimi-K2.5":{"metadata":{"displayName":"moonshotai/Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2.5","displayName":"moonshotai/Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"moonshotai/Kimi-K2.6":{"metadata":{"displayName":"moonshotai/Kimi-K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2026-06-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2.6","displayName":"moonshotai/Kimi-K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"openai/gpt-oss-120b":{"metadata":{"displayName":"openai/gpt-oss-120b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131000,"maxOutputTokens":8000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-120b","displayName":"openai/gpt-oss-120b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000}},"openai/gpt-oss-20b":{"metadata":{"displayName":"openai/gpt-oss-20b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131000,"maxOutputTokens":8000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-20b","displayName":"openai/gpt-oss-20b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000}},"Qwen/Qwen2.5-72B-Instruct":{"metadata":{"displayName":"Qwen/Qwen2.5-72B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":33000,"maxOutputTokens":4000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen2.5-72B-Instruct","displayName":"Qwen/Qwen2.5-72B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":33000,"defaultContextWindow":33000}},"Qwen/Qwen2.5-7B-Instruct":{"metadata":{"displayName":"Qwen/Qwen2.5-7B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":33000,"maxOutputTokens":4000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen2.5-7B-Instruct","displayName":"Qwen/Qwen2.5-7B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":33000,"defaultContextWindow":33000}},"Qwen/Qwen3-14B":{"metadata":{"displayName":"Qwen/Qwen3-14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131000,"maxOutputTokens":131000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-14B","displayName":"Qwen/Qwen3-14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000}},"Qwen/Qwen3-235B-A22B-Thinking-2507":{"metadata":{"displayName":"Qwen/Qwen3-235B-A22B-Thinking-2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","displayName":"Qwen/Qwen3-235B-A22B-Thinking-2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"Qwen/Qwen3-30B-A3B-Instruct-2507":{"metadata":{"displayName":"Qwen/Qwen3-30B-A3B-Instruct-2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-30B-A3B-Instruct-2507","displayName":"Qwen/Qwen3-30B-A3B-Instruct-2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"Qwen/Qwen3-32B":{"metadata":{"displayName":"Qwen/Qwen3-32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131000,"maxOutputTokens":131000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-32B","displayName":"Qwen/Qwen3-32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000}},"Qwen/Qwen3-8B":{"metadata":{"displayName":"Qwen/Qwen3-8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131000,"maxOutputTokens":131000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-8B","displayName":"Qwen/Qwen3-8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000}},"Qwen/Qwen3-Coder-30B-A3B-Instruct":{"metadata":{"displayName":"Qwen/Qwen3-Coder-30B-A3B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","displayName":"Qwen/Qwen3-Coder-30B-A3B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"Qwen/Qwen3-Coder-480B-A35B-Instruct":{"metadata":{"displayName":"Qwen/Qwen3-Coder-480B-A35B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","displayName":"Qwen/Qwen3-Coder-480B-A35B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"Qwen/Qwen3-VL-235B-A22B-Instruct":{"metadata":{"displayName":"Qwen/Qwen3-VL-235B-A22B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-VL-235B-A22B-Instruct","displayName":"Qwen/Qwen3-VL-235B-A22B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"Qwen/Qwen3-VL-235B-A22B-Thinking":{"metadata":{"displayName":"Qwen/Qwen3-VL-235B-A22B-Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":true,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-VL-235B-A22B-Thinking","displayName":"Qwen/Qwen3-VL-235B-A22B-Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"Qwen/Qwen3-VL-30B-A3B-Instruct":{"metadata":{"displayName":"Qwen/Qwen3-VL-30B-A3B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-VL-30B-A3B-Instruct","displayName":"Qwen/Qwen3-VL-30B-A3B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"Qwen/Qwen3-VL-30B-A3B-Thinking":{"metadata":{"displayName":"Qwen/Qwen3-VL-30B-A3B-Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":true,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-VL-30B-A3B-Thinking","displayName":"Qwen/Qwen3-VL-30B-A3B-Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"Qwen/Qwen3-VL-32B-Instruct":{"metadata":{"displayName":"Qwen/Qwen3-VL-32B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-VL-32B-Instruct","displayName":"Qwen/Qwen3-VL-32B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"Qwen/Qwen3-VL-32B-Thinking":{"metadata":{"displayName":"Qwen/Qwen3-VL-32B-Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":true,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-VL-32B-Thinking","displayName":"Qwen/Qwen3-VL-32B-Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"Qwen/Qwen3-VL-8B-Instruct":{"metadata":{"displayName":"Qwen/Qwen3-VL-8B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-VL-8B-Instruct","displayName":"Qwen/Qwen3-VL-8B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"Qwen/Qwen3.5-122B-A10B":{"metadata":{"displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-122B-A10B","displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.5-27B":{"metadata":{"displayName":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-27B","displayName":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.5-35B-A3B":{"metadata":{"displayName":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-35B-A3B","displayName":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.5-397B-A17B":{"metadata":{"displayName":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-02-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-397B-A17B","displayName":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.5-9B":{"metadata":{"displayName":"Qwen/Qwen3.5-9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-9B","displayName":"Qwen/Qwen3.5-9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.6-27B":{"metadata":{"displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.6-27B","displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.6-35B-A3B":{"metadata":{"displayName":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-04-17","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.6-35B-A3B","displayName":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"stepfun-ai/Step-3.5-Flash":{"metadata":{"displayName":"stepfun-ai/Step-3.5-Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2026-02-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"stepfun-ai/Step-3.5-Flash","displayName":"stepfun-ai/Step-3.5-Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"tencent/Hunyuan-A13B-Instruct":{"metadata":{"displayName":"tencent/Hunyuan-A13B-Instruct","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":131000,"maxOutputTokens":131000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/Hunyuan-A13B-Instruct","displayName":"tencent/Hunyuan-A13B-Instruct","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000}},"tencent/Hy3-preview":{"metadata":{"displayName":"Hy3 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"lastUpdated":"2026-04-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/Hy3-preview","displayName":"Hy3 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"zai-org/GLM-4.5-Air":{"metadata":{"displayName":"zai-org/GLM-4.5-Air","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":131000,"maxOutputTokens":131000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-4.5-Air","displayName":"zai-org/GLM-4.5-Air","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000}},"zai-org/GLM-5":{"metadata":{"displayName":"zai-org/GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":205000,"maxOutputTokens":205000,"structuredOutput":true,"lastUpdated":"2026-06-15","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5","displayName":"zai-org/GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":205000,"defaultContextWindow":205000}},"zai-org/GLM-5.1":{"metadata":{"displayName":"zai-org/GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":205000,"maxOutputTokens":205000,"structuredOutput":true,"lastUpdated":"2026-04-08","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.1","displayName":"zai-org/GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":205000,"defaultContextWindow":205000}},"zai-org/GLM-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1049000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1049000,"defaultContextWindow":1049000}},"zai-org/GLM-5V-Turbo":{"metadata":{"displayName":"zai-org/GLM-5V-Turbo","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":131072,"lastUpdated":"2026-04-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true,"chat":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5V-Turbo","displayName":"zai-org/GLM-5V-Turbo","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}}}},"vercel":{"baseUrl":"https://ai-gateway.vercel.sh/v1","label":"Vercel AI Gateway","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol","auth":"none","filter":"language-models"},"fallbackModels":["anthropic/claude-opus-4.8","alibaba/qwen-3-14b","alibaba/qwen-3-235b","alibaba/qwen-3-30b","alibaba/qwen-3-32b","alibaba/qwen-3.6-max-preview","alibaba/qwen3-235b-a22b-thinking","alibaba/qwen3-coder","alibaba/qwen3-coder-30b-a3b","alibaba/qwen3-coder-next","alibaba/qwen3-coder-plus","alibaba/qwen3-max","alibaba/qwen3-max-preview","alibaba/qwen3-max-thinking","alibaba/qwen3-next-80b-a3b-instruct","alibaba/qwen3-next-80b-a3b-thinking","alibaba/qwen3-vl-instruct","alibaba/qwen3-vl-thinking","alibaba/qwen3.5-flash","alibaba/qwen3.5-plus","alibaba/qwen3.6-27b","alibaba/qwen3.6-plus","alibaba/qwen3.7-flash","alibaba/qwen3.7-max","alibaba/qwen3.7-plus","alibaba/qwen3.8-2.4t-a95b","alibaba/qwen3.8-27b","alibaba/qwen3.8-flash","alibaba/qwen3.8-max","alibaba/qwen3.8-max-0902","amazon/nova-lite","amazon/nova-micro","amazon/nova-pro","anthropic/claude-3-haiku","anthropic/claude-fable-5","anthropic/claude-fable-5.1","anthropic/claude-haiku-4.5","anthropic/claude-opus-4","anthropic/claude-opus-4.5","anthropic/claude-opus-4.6","anthropic/claude-opus-4.7","anthropic/claude-opus-4.8-fast","anthropic/claude-opus-5","anthropic/claude-opus-5-fast","anthropic/claude-sonnet-4","anthropic/claude-sonnet-4.5","anthropic/claude-sonnet-4.6","anthropic/claude-sonnet-5","arcee-ai/trinity-large-thinking","bytedance/seed-1.6","bytedance/seed-1.8","bytedance/seed-2.1-turbo","cohere/command-a","deepseek/deepseek-v3.1","deepseek/deepseek-v3.1-terminus","deepseek/deepseek-v3.2-thinking","deepseek/deepseek-v4-flash","deepseek/deepseek-v4-flash-0731","deepseek/deepseek-v4-flash-vision-exp","deepseek/deepseek-v4-pro","deepseek/deepseek-v4-pro-0813","deepseek/deepseek-v4.1-flash","google/gemini-2.5-flash","google/gemini-2.5-flash-lite","google/gemini-2.5-pro","google/gemini-3-flash","google/gemini-3.1-flash-lite","google/gemini-3.1-pro-preview","google/gemini-3.5-flash","google/gemini-3.5-flash-lite","google/gemini-3.6-flash","google/gemini-3.7-flash","google/gemini-3.8-flash","google/gemma-4-26b-a4b-it","google/gemma-4-31b-it","inception/mercury-2","inception/mercury-2.5","inception/mercury-coder-small","inclusionai/ling-3.0-flash","inclusionai/ling-3.0-flash-fin","inclusionai/ling-3.0-flash-fin-free","inclusionai/ling-3.0-flash-sante","inclusionai/ling-3.0-flash-sante-free","inclusionai/ling-3.0-flash-vl","inclusionai/ling-3.0-flash-vl-free","kwaipilot/kat-coder-air-v2.5","kwaipilot/kat-coder-pro-v2","kwaipilot/kat-coder-pro-v2.5","meta/llama-3.1-70b","meta/llama-3.1-8b","meta/llama-3.3-70b","meta/llama-4-maverick","meta/llama-4-scout","meta/muse-glimmer-30b","meta/muse-spark-1.1","meta/muse-spark-1.2","meta/muse-spark-1.2-contributor","meta/muse-spark-1.3","meta/muse-spark-1.3-contributor","minimax/minimax-m2","minimax/minimax-m2.1","minimax/minimax-m2.1-lightning","minimax/minimax-m2.5","minimax/minimax-m2.5-highspeed","minimax/minimax-m2.7","minimax/minimax-m2.7-highspeed","minimax/minimax-m3","mistral/codestral","mistral/devstral-2","mistral/devstral-small-2","mistral/ministral-3b","mistral/ministral-8b","mistral/mistral-medium","mistral/mistral-medium-3.5","mistral/mistral-nemo","mistral/mistral-small","mistral/pixtral-12b","moonshotai/kimi-k2","moonshotai/kimi-k2-thinking","moonshotai/kimi-k2.5","moonshotai/kimi-k2.6","moonshotai/kimi-k2.7-code","moonshotai/kimi-k2.7-code-highspeed","moonshotai/kimi-k3","moonshotai/kimi-k3-fast","nvidia/nemotron-3-ultra-550b-a55b","nvidia/nemotron-3.5-lightning","nvidia/nemotron-nano-12b-v2-vl","nvidia/nemotron-nano-9b-v2","openai/gpt-4.1","openai/gpt-4.1-fast","openai/gpt-4.1-mini","openai/gpt-4.1-mini-fast","openai/gpt-4.1-nano-fast","openai/gpt-4o","openai/gpt-4o-fast","openai/gpt-4o-mini","openai/gpt-4o-mini-fast","openai/gpt-5","openai/gpt-5-codex","openai/gpt-5-fast","openai/gpt-5-mini","openai/gpt-5-mini-fast","openai/gpt-5-nano","openai/gpt-5-pro","openai/gpt-5.1-codex","openai/gpt-5.1-codex-max","openai/gpt-5.1-codex-mini","openai/gpt-5.1-thinking","openai/gpt-5.1-thinking-fast","openai/gpt-5.2","openai/gpt-5.2-codex","openai/gpt-5.2-fast","openai/gpt-5.2-pro","openai/gpt-5.3-codex","openai/gpt-5.3-codex-fast","openai/gpt-5.4","openai/gpt-5.4-fast","openai/gpt-5.4-mini","openai/gpt-5.4-mini-fast","openai/gpt-5.4-nano","openai/gpt-5.4-pro","openai/gpt-5.5","openai/gpt-5.5-fast","openai/gpt-5.5-pro","openai/gpt-5.6-luna","openai/gpt-5.6-luna-fast","openai/gpt-5.6-sol","openai/gpt-5.6-sol-fast","openai/gpt-5.6-terra","openai/gpt-5.6-terra-fast","openai/gpt-6-astra","openai/gpt-6-astra-fast","openai/gpt-oss-120b","openai/gpt-oss-20b","openai/gpt-oss-safeguard-120b","openai/gpt-oss-safeguard-20b","openai/o3","openai/o3-fast","openai/o3-pro","openai/o4-mini-fast","perplexity/sonar","perplexity/sonar-pro","poolside/laguna-s-2.1","poolside/laguna-s-2.1-free","sakana/fugu-max","sakana/fugu-ultra","sakana/fugu-ultra-v2","sakana/namazu","spacexai/grok-4.1-fast-non-reasoning","spacexai/grok-4.1-fast-reasoning","spacexai/grok-4.20-multi-agent","spacexai/grok-4.20-multi-agent-beta","spacexai/grok-4.20-non-reasoning","spacexai/grok-4.20-non-reasoning-beta","spacexai/grok-4.20-reasoning","spacexai/grok-4.20-reasoning-beta","spacexai/grok-4.3","spacexai/grok-4.5","spacexai/grok-4.6","spacexai/grok-build-0.1","stepfun/step-3.5-flash","stepfun/step-3.7-flash","tencent/hy3","tencent/hy4-preview","thinkingmachines/inkling","thinkingmachines/inkling-small","xiaomi/mimo-v2.5","xiaomi/mimo-v2.5-pro","zai/glm-4.5","zai/glm-4.5-air","zai/glm-4.5v","zai/glm-4.6","zai/glm-4.7","zai/glm-4.7-flash","zai/glm-4.7-flashx","zai/glm-5","zai/glm-5-turbo","zai/glm-5.1","zai/glm-5.2","zai/glm-5.2-fast","zai/glm-5.3","zai/glm-5.3-fast","zai/glm-5.3-flash","zai/glm-5v-turbo"],"models":{"alibaba/qwen-3-14b":{"metadata":{"displayName":"Qwen3-14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":40960,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen-3-14b","displayName":"Qwen3-14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":40960,"defaultContextWindow":40960,"knowledgeCutoff":"2025-04"}},"alibaba/qwen-3-235b":{"metadata":{"displayName":"Qwen3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen-3-235b","displayName":"Qwen3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"alibaba/qwen-3-30b":{"metadata":{"displayName":"Qwen3-30B-A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":40960,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen-3-30b","displayName":"Qwen3-30B-A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":40960,"defaultContextWindow":40960,"knowledgeCutoff":"2025-04"}},"alibaba/qwen-3-32b":{"metadata":{"displayName":"Qwen 3.32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen-3-32b","displayName":"Qwen 3.32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-04"}},"alibaba/qwen-3.6-max-preview":{"metadata":{"displayName":"Qwen 3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","lifecycle":"active","contextWindow":240000,"maxOutputTokens":64000,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen-3.6-max-preview","displayName":"Qwen 3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":240000,"defaultContextWindow":240000}},"alibaba/qwen3-235b-a22b-thinking":{"metadata":{"displayName":"Qwen3 235B A22B Thinking 2507","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-235b-a22b-thinking","displayName":"Qwen3 235B A22B Thinking 2507","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3-coder":{"metadata":{"displayName":"Qwen3 Coder 480B A35B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-coder","displayName":"Qwen3 Coder 480B A35B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3-coder-30b-a3b":{"metadata":{"displayName":"Qwen 3 Coder 30B A3B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":8192,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-coder-30b-a3b","displayName":"Qwen 3 Coder 30B A3B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3-coder-next":{"metadata":{"displayName":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-09","structuredOutput":true,"lastUpdated":"2026-02-03","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-coder-next","displayName":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-09"}},"alibaba/qwen3-coder-plus":{"metadata":{"displayName":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-coder-plus","displayName":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3-embedding-0.6b":{"metadata":{"displayName":"Qwen3 Embedding 0.6B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":32768,"maxOutputTokens":32768,"lastUpdated":"2025-11-14","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-embedding-0.6b","displayName":"Qwen3 Embedding 0.6B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"alibaba/qwen3-embedding-4b":{"metadata":{"displayName":"Qwen3 Embedding 4B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":32768,"maxOutputTokens":32768,"lastUpdated":"2025-06-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-embedding-4b","displayName":"Qwen3 Embedding 4B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"alibaba/qwen3-embedding-8b":{"metadata":{"displayName":"Qwen3 Embedding 8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":32768,"maxOutputTokens":32768,"lastUpdated":"2025-06-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-embedding-8b","displayName":"Qwen3 Embedding 8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"alibaba/qwen3-max":{"metadata":{"displayName":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-max","displayName":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3-max-preview":{"metadata":{"displayName":"Qwen3 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-max-preview","displayName":"Qwen3 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3-max-thinking":{"metadata":{"displayName":"Qwen 3 Max Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":256000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","lastUpdated":"2025-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-max-thinking","displayName":"Qwen 3 Max Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-01"}},"alibaba/qwen3-next-80b-a3b-instruct":{"metadata":{"displayName":"Qwen3 Next 80B A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-next-80b-a3b-instruct","displayName":"Qwen3 Next 80B A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3-next-80b-a3b-thinking":{"metadata":{"displayName":"Qwen3 Next 80B A3B Thinking","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-next-80b-a3b-thinking","displayName":"Qwen3 Next 80B A3B Thinking","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3-vl-235b-a22b-instruct":{"metadata":{"displayName":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":129024,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-09-23","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-vl-235b-a22b-instruct","displayName":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-03-31"}},"alibaba/qwen3-vl-instruct":{"metadata":{"displayName":"Qwen3 VL Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":129024,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-24","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-vl-instruct","displayName":"Qwen3 VL Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3-vl-thinking":{"metadata":{"displayName":"Qwen3 VL Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-09","lastUpdated":"2025-09-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-vl-thinking","displayName":"Qwen3 VL Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-09"}},"alibaba/qwen3.5-flash":{"metadata":{"displayName":"Qwen 3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.5-flash","displayName":"Qwen 3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"alibaba/qwen3.5-plus":{"metadata":{"displayName":"Qwen 3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.5-plus","displayName":"Qwen 3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3.6-27b":{"metadata":{"displayName":"Qwen 3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.6-27b","displayName":"Qwen 3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"alibaba/qwen3.6-plus":{"metadata":{"displayName":"Qwen 3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-04","lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.6-plus","displayName":"Qwen 3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3.7-flash":{"metadata":{"displayName":"Qwen 3.7 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":991000,"maxOutputTokens":64000,"structuredOutput":true,"lastUpdated":"2026-07-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.7-flash","displayName":"Qwen 3.7 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":991000,"defaultContextWindow":991000}},"alibaba/qwen3.7-max":{"metadata":{"displayName":"Qwen 3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","lifecycle":"active","contextWindow":991000,"maxOutputTokens":64000,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.7-max","displayName":"Qwen 3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":991000,"defaultContextWindow":991000}},"alibaba/qwen3.7-plus":{"metadata":{"displayName":"Qwen 3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-04","lastUpdated":"2026-06-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.7-plus","displayName":"Qwen 3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3.8-2.4t-a95b":{"metadata":{"displayName":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.8-2.4t-a95b","displayName":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":262144,"defaultContextWindow":262144}},"alibaba/qwen3.8-27b":{"metadata":{"displayName":"Qwen3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.8-27b","displayName":"Qwen3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"alibaba/qwen3.8-flash":{"metadata":{"displayName":"Qwen 3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":991000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.8-flash","displayName":"Qwen 3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":991000,"defaultContextWindow":991000}},"alibaba/qwen3.8-max":{"metadata":{"displayName":"Qwen 3.8 Max","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"lastUpdated":"2026-07-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.8-max","displayName":"Qwen 3.8 Max","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"alibaba/qwen3.8-max-0902":{"metadata":{"displayName":"Qwen3.8 Max 0902","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":991000,"maxOutputTokens":128000,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.8-max-0902","displayName":"Qwen3.8 Max 0902","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":991000,"defaultContextWindow":991000}},"alibaba/wan-v2.5-t2v-preview":{"metadata":{"displayName":"Wan v2.5 Text-to-Video Preview","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2025-09-24","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"alibaba/wan-v2.5-t2v-preview","displayName":"Wan v2.5 Text-to-Video Preview","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"alibaba/wan-v2.6-i2v":{"metadata":{"displayName":"Wan v2.6 Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-12-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"alibaba/wan-v2.6-i2v","displayName":"Wan v2.6 Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"alibaba/wan-v2.6-i2v-flash":{"metadata":{"displayName":"Wan v2.6 Image-to-Video Flash","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-12-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"alibaba/wan-v2.6-i2v-flash","displayName":"Wan v2.6 Image-to-Video Flash","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"alibaba/wan-v2.6-r2v":{"metadata":{"displayName":"Wan v2.6 Reference-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2025-12-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"alibaba/wan-v2.6-r2v","displayName":"Wan v2.6 Reference-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"alibaba/wan-v2.6-r2v-flash":{"metadata":{"displayName":"Wan v2.6 Reference-to-Video Flash","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2025-12-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"alibaba/wan-v2.6-r2v-flash","displayName":"Wan v2.6 Reference-to-Video Flash","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"alibaba/wan-v2.6-t2v":{"metadata":{"displayName":"Wan v2.6 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2025-12-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"alibaba/wan-v2.6-t2v","displayName":"Wan v2.6 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"alibaba/wan-v2.7-r2v":{"metadata":{"displayName":"Wan v2.7 Reference-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"alibaba/wan-v2.7-r2v","displayName":"Wan v2.7 Reference-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"alibaba/wan-v2.7-t2v":{"metadata":{"displayName":"Wan v2.7 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"alibaba/wan-v2.7-t2v","displayName":"Wan v2.7 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"alibaba/wan-v3.0-video":{"metadata":{"displayName":"Wan v3.0 Video","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-08-23","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["video"]}},"entry":{"id":"alibaba/wan-v3.0-video","displayName":"Wan v3.0 Video","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"alibaba/wan-v3.0-video-prime":{"metadata":{"displayName":"Wan v3.0 Video Prime","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-08-28","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["video"]}},"entry":{"id":"alibaba/wan-v3.0-video-prime","displayName":"Wan v3.0 Video Prime","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"amazon/nova-2-lite":{"metadata":{"displayName":"Nova 2 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":1000000,"knowledgeCutoff":"2024-10","lastUpdated":"2024-12-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"amazon/nova-2-lite","displayName":"Nova 2 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-10"}},"amazon/nova-lite":{"metadata":{"displayName":"Nova Lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":300000,"maxOutputTokens":10000,"knowledgeCutoff":"2024-10","lastUpdated":"2024-12-03","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"amazon/nova-lite","displayName":"Nova Lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":300000,"defaultContextWindow":300000,"knowledgeCutoff":"2024-10"}},"amazon/nova-micro":{"metadata":{"displayName":"Nova Micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":128000,"maxOutputTokens":10000,"knowledgeCutoff":"2024-10","lastUpdated":"2024-12-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"amazon/nova-micro","displayName":"Nova Micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-10"}},"amazon/nova-pro":{"metadata":{"displayName":"Nova Pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":300000,"maxOutputTokens":10000,"knowledgeCutoff":"2024-10","lastUpdated":"2024-12-03","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"amazon/nova-pro","displayName":"Nova Pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":300000,"defaultContextWindow":300000,"knowledgeCutoff":"2024-10"}},"amazon/titan-embed-text-v2":{"metadata":{"displayName":"Titan Text Embeddings V2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2024-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"amazon/titan-embed-text-v2","displayName":"Titan Text Embeddings V2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"anthropic/claude-3-haiku":{"metadata":{"displayName":"Claude Haiku 3","description":"Legacy model retained for compatibility with older integrations","lifecycle":"active","contextWindow":200000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-08-31","lastUpdated":"2024-03-13","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"anthropic/claude-3-haiku","displayName":"Claude Haiku 3","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2023-08-31"}},"anthropic/claude-fable-5":{"metadata":{"displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-06-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-fable-5","displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"anthropic/claude-fable-5.1":{"metadata":{"displayName":"Claude Fable 5.1","description":"Claude model for creative writing, analysis, and controlled agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-06","lastUpdated":"2026-09-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-fable-5.1","displayName":"Claude Fable 5.1","description":"Claude model for creative writing, analysis, and controlled agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-06"}},"anthropic/claude-haiku-4.5":{"metadata":{"displayName":"Claude Haiku 4.5","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-02-28","lastUpdated":"2025-10-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-haiku-4.5","displayName":"Claude Haiku 4.5","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-02-28"}},"anthropic/claude-opus-4":{"metadata":{"displayName":"Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":8192,"knowledgeCutoff":"2025-03-31","lastUpdated":"2025-05-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4","displayName":"Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-03-31"}},"anthropic/claude-opus-4.5":{"metadata":{"displayName":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-05","lastUpdated":"2025-11-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4.5","displayName":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-05"}},"anthropic/claude-opus-4.6":{"metadata":{"displayName":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-05-31","lastUpdated":"2026-03-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4.6","displayName":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05-31"}},"anthropic/claude-opus-4.7":{"metadata":{"displayName":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4.7","displayName":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"anthropic/claude-opus-4.8":{"metadata":{"displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01","lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4.8","displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01"}},"anthropic/claude-opus-4.8-fast":{"metadata":{"displayName":"Claude Opus 4.8 (Fast)","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01","lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4.8-fast","displayName":"Claude Opus 4.8 (Fast)","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01"}},"anthropic/claude-opus-5":{"metadata":{"displayName":"Claude Opus 5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-05","lastUpdated":"2026-07-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-5","displayName":"Claude Opus 5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-05"}},"anthropic/claude-opus-5-fast":{"metadata":{"displayName":"Claude Opus 5 (Fast)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-05","lastUpdated":"2026-07-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-5-fast","displayName":"Claude Opus 5 (Fast)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-05"}},"anthropic/claude-sonnet-4":{"metadata":{"displayName":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":8192,"knowledgeCutoff":"2025-03-31","lastUpdated":"2025-05-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-sonnet-4","displayName":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-03-31"}},"anthropic/claude-sonnet-4.5":{"metadata":{"displayName":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-07-31","structuredOutput":true,"lastUpdated":"2025-09-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-sonnet-4.5","displayName":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-07-31"}},"anthropic/claude-sonnet-4.6":{"metadata":{"displayName":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-03-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-sonnet-4.6","displayName":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-08-31"}},"anthropic/claude-sonnet-5":{"metadata":{"displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-sonnet-5","displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"arcee-ai/trinity-large-thinking":{"metadata":{"displayName":"Trinity Large Thinking","description":"Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use","lifecycle":"active","contextWindow":262100,"maxOutputTokens":80000,"lastUpdated":"2026-04-03","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"arcee-ai/trinity-large-thinking","displayName":"Trinity Large Thinking","description":"Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262100,"defaultContextWindow":262100}},"bfl/flux-2-flex":{"metadata":{"displayName":"FLUX.2 [flex]","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-06-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bfl/flux-2-flex","displayName":"FLUX.2 [flex]","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"bfl/flux-2-klein-4b":{"metadata":{"displayName":"FLUX.2 [klein] 4B","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-06-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bfl/flux-2-klein-4b","displayName":"FLUX.2 [klein] 4B","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"bfl/flux-2-klein-9b":{"metadata":{"displayName":"FLUX.2 [klein] 9B","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-06-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bfl/flux-2-klein-9b","displayName":"FLUX.2 [klein] 9B","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"bfl/flux-2-max":{"metadata":{"displayName":"FLUX.2 [max]","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":67300,"maxOutputTokens":67300,"lastUpdated":"2026-06-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bfl/flux-2-max","displayName":"FLUX.2 [max]","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":67300,"defaultContextWindow":67300}},"bfl/flux-2-pro":{"metadata":{"displayName":"FLUX.2 [pro]","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":67300,"maxOutputTokens":67300,"lastUpdated":"2026-06-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bfl/flux-2-pro","displayName":"FLUX.2 [pro]","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":67300,"defaultContextWindow":67300}},"bfl/flux-3-video":{"metadata":{"displayName":"Flux 3","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-08-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"bfl/flux-3-video","displayName":"Flux 3","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"bfl/flux-kontext-max":{"metadata":{"displayName":"FLUX.1 Kontext Max","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":512,"lastUpdated":"2025-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bfl/flux-kontext-max","displayName":"FLUX.1 Kontext Max","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":512,"defaultContextWindow":512}},"bfl/flux-kontext-pro":{"metadata":{"displayName":"FLUX.1 Kontext Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":512,"lastUpdated":"2025-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bfl/flux-kontext-pro","displayName":"FLUX.1 Kontext Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":512,"defaultContextWindow":512}},"bfl/flux-pro-1.0-fill":{"metadata":{"displayName":"FLUX.1 Fill [pro]","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":512,"lastUpdated":"2024-10","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bfl/flux-pro-1.0-fill","displayName":"FLUX.1 Fill [pro]","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":512,"defaultContextWindow":512}},"bfl/flux-pro-1.1":{"metadata":{"displayName":"FLUX1.1 [pro]","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":512,"lastUpdated":"2024-10","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bfl/flux-pro-1.1","displayName":"FLUX1.1 [pro]","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":512,"defaultContextWindow":512}},"bfl/flux-pro-1.1-ultra":{"metadata":{"displayName":"FLUX1.1 [pro] Ultra","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":512,"lastUpdated":"2024-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bfl/flux-pro-1.1-ultra","displayName":"FLUX1.1 [pro] Ultra","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":512,"defaultContextWindow":512}},"bytedance/seed-1.6":{"metadata":{"displayName":"Seed 1.6","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"knowledgeCutoff":"2024-10","lastUpdated":"2025-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"bytedance/seed-1.6","displayName":"Seed 1.6","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-10"}},"bytedance/seed-1.8":{"metadata":{"displayName":"Seed 1.8","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2024-10","lastUpdated":"2025-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"bytedance/seed-1.8","displayName":"Seed 1.8","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-10"}},"bytedance/seed-2.1-turbo":{"metadata":{"displayName":"Seed 2.1 Turbo","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"lastUpdated":"2026-06-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","minimal","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"bytedance/seed-2.1-turbo","displayName":"Seed 2.1 Turbo","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","minimal","low","medium","high","xhigh","max"],"contextWindow":262144,"defaultContextWindow":262144}},"bytedance/seedance-2.0":{"metadata":{"displayName":"Seedance 2.0","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["video"]}},"entry":{"id":"bytedance/seedance-2.0","displayName":"Seedance 2.0","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"bytedance/seedance-2.0-fast":{"metadata":{"displayName":"Seedance 2.0 Fast","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["video"]}},"entry":{"id":"bytedance/seedance-2.0-fast","displayName":"Seedance 2.0 Fast","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"bytedance/seedance-2.0-mini":{"metadata":{"displayName":"Seedance 2.0 Mini","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-06-22","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["video"]}},"entry":{"id":"bytedance/seedance-2.0-mini","displayName":"Seedance 2.0 Mini","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"bytedance/seedance-2.5":{"metadata":{"displayName":"Seedance 2.5","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-08-07","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"bytedance/seedance-2.5","displayName":"Seedance 2.5","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"bytedance/seedance-v1.0-pro":{"metadata":{"displayName":"Seedance v1.0 Pro","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2025-06-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"bytedance/seedance-v1.0-pro","displayName":"Seedance v1.0 Pro","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"bytedance/seedance-v1.0-pro-fast":{"metadata":{"displayName":"Seedance v1.0 Pro Fast","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2025-10-31","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"bytedance/seedance-v1.0-pro-fast","displayName":"Seedance v1.0 Pro Fast","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"bytedance/seedance-v1.5-pro":{"metadata":{"displayName":"Seedance v1.5 Pro","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2025-12-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"bytedance/seedance-v1.5-pro","displayName":"Seedance v1.5 Pro","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"bytedance/seedream-4.0":{"metadata":{"displayName":"Seedream 4.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-08-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bytedance/seedream-4.0","displayName":"Seedream 4.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"bytedance/seedream-4.5":{"metadata":{"displayName":"Seedream 4.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-11-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bytedance/seedream-4.5","displayName":"Seedream 4.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"bytedance/seedream-5.0-lite":{"metadata":{"displayName":"Seedream 5.0 Lite","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-01-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bytedance/seedream-5.0-lite","displayName":"Seedream 5.0 Lite","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"bytedance/seedream-5.0-pro":{"metadata":{"displayName":"Seedream 5.0 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-07-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bytedance/seedream-5.0-pro","displayName":"Seedream 5.0 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"cohere/command-a":{"metadata":{"displayName":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","lifecycle":"active","contextWindow":256000,"maxOutputTokens":8000,"knowledgeCutoff":"2024-10","lastUpdated":"2025-03-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"cohere/command-a","displayName":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-10"}},"cohere/embed-v4.0":{"metadata":{"displayName":"Embed v4.0","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":128000,"maxOutputTokens":1536,"lastUpdated":"2025-04-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"cohere/embed-v4.0","displayName":"Embed v4.0","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"cohere/rerank-v3.5":{"metadata":{"displayName":"Cohere Rerank 3.5","description":"Reranking model for improving retrieval quality in search and recommendation systems","lifecycle":"active","contextWindow":4096,"maxOutputTokens":4096,"lastUpdated":"2024-12-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"cohere/rerank-v3.5","displayName":"Cohere Rerank 3.5","description":"Reranking model for improving retrieval quality in search and recommendation systems","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":4096,"defaultContextWindow":4096}},"cohere/rerank-v4-fast":{"metadata":{"displayName":"Cohere Rerank 4 Fast","description":"Reranking model for improving retrieval quality in search and recommendation systems","lifecycle":"active","contextWindow":32000,"maxOutputTokens":32000,"lastUpdated":"2025-12-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"cohere/rerank-v4-fast","displayName":"Cohere Rerank 4 Fast","description":"Reranking model for improving retrieval quality in search and recommendation systems","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"cohere/rerank-v4-pro":{"metadata":{"displayName":"Cohere Rerank 4 Pro","description":"Reranking model for improving retrieval quality in search and recommendation systems","lifecycle":"active","contextWindow":32000,"maxOutputTokens":32000,"lastUpdated":"2025-12-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"cohere/rerank-v4-pro","displayName":"Cohere Rerank 4 Pro","description":"Reranking model for improving retrieval quality in search and recommendation systems","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"deepseek/deepseek-r1":{"metadata":{"displayName":"DeepSeek-R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","lifecycle":"active","contextWindow":128000,"maxOutputTokens":32768,"knowledgeCutoff":"2024-07","lastUpdated":"2025-05-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-r1","displayName":"DeepSeek-R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-07"}},"deepseek/deepseek-v3.1":{"metadata":{"displayName":"DeepSeek-V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":128000,"lastUpdated":"2025-08-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v3.1","displayName":"DeepSeek-V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840}},"deepseek/deepseek-v3.1-terminus":{"metadata":{"displayName":"DeepSeek V3.1 Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"knowledgeCutoff":"2025-07","lastUpdated":"2025-09-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v3.1-terminus","displayName":"DeepSeek V3.1 Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-07"}},"deepseek/deepseek-v3.2":{"metadata":{"displayName":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8000,"knowledgeCutoff":"2024-07","structuredOutput":true,"lastUpdated":"2025-12-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v3.2","displayName":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-07"}},"deepseek/deepseek-v3.2-thinking":{"metadata":{"displayName":"DeepSeek V3.2 Thinking","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8000,"knowledgeCutoff":"2024-07","lastUpdated":"2025-12-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v3.2-thinking","displayName":"DeepSeek V3.2 Thinking","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-07"}},"deepseek/deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-flash","displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek/deepseek-v4-flash-0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-flash-0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek/deepseek-v4-flash-vision-exp":{"metadata":{"displayName":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"structuredOutput":true,"lastUpdated":"2026-08-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-flash-vision-exp","displayName":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"deepseek/deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-pro","displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek/deepseek-v4-pro-0813":{"metadata":{"displayName":"DeepSeek V4 Pro 0813","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-pro-0813","displayName":"DeepSeek V4 Pro 0813","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"deepseek/deepseek-v4.1-flash":{"metadata":{"displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4.1-flash","displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"fish-audio/s1":{"metadata":{"displayName":"S1","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2025-10-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"fish-audio/s1","displayName":"S1","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"fish-audio/s1-free":{"metadata":{"displayName":"S1 (Free)","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2025-10-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"fish-audio/s1-free","displayName":"S1 (Free)","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"fish-audio/s2-pro":{"metadata":{"displayName":"S2 Pro","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-03-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"fish-audio/s2-pro","displayName":"S2 Pro","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"fish-audio/s2-pro-free":{"metadata":{"displayName":"S2 Pro (Free)","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-03-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"fish-audio/s2-pro-free","displayName":"S2 Pro (Free)","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"fish-audio/s2.1-pro":{"metadata":{"displayName":"S2.1 Pro","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-07-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"fish-audio/s2.1-pro","displayName":"S2.1 Pro","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"fish-audio/s2.1-pro-free":{"metadata":{"displayName":"S2.1 Pro (Free)","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-07-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"fish-audio/s2.1-pro-free","displayName":"S2.1 Pro (Free)","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"fish-audio/transcribe-1":{"metadata":{"displayName":"Transcribe-1","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2026-03-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"fish-audio/transcribe-1","displayName":"Transcribe-1","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"fish-audio/transcribe-1-free":{"metadata":{"displayName":"Transcribe-1 (Free)","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2026-03-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"fish-audio/transcribe-1-free","displayName":"Transcribe-1 (Free)","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"google/gemini-2.5-flash":{"metadata":{"displayName":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-06-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-2.5-flash","displayName":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-2.5-flash-image":{"metadata":{"displayName":"Nano Banana (Gemini 2.5 Flash Image)","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","lifecycle":"active","contextWindow":32768,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","lastUpdated":"2025-08-26","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"google/gemini-2.5-flash-image","displayName":"Nano Banana (Gemini 2.5 Flash Image)","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2025-01"}},"google/gemini-2.5-flash-lite":{"metadata":{"displayName":"Gemini 2.5 Flash Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-06-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-2.5-flash-lite","displayName":"Gemini 2.5 Flash Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-2.5-pro":{"metadata":{"displayName":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-06-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-2.5-pro","displayName":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-3-flash":{"metadata":{"displayName":"Gemini 3 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65000,"knowledgeCutoff":"2025-03","lastUpdated":"2025-12-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3-flash","displayName":"Gemini 3 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-03"}},"google/gemini-3-pro-image":{"metadata":{"displayName":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","lifecycle":"active","contextWindow":65536,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"google/gemini-3-pro-image","displayName":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-flash-image":{"metadata":{"displayName":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["minimal","high"]},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"google/gemini-3.1-flash-image","displayName":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","high"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-flash-image-preview":{"metadata":{"displayName":"Gemini 3.1 Flash Image Preview (Nano Banana 2)","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","lastUpdated":"2026-02-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["minimal","high"]},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"google/gemini-3.1-flash-image-preview","displayName":"Gemini 3.1 Flash Image Preview (Nano Banana 2)","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","high"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-flash-lite":{"metadata":{"displayName":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65000,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.1-flash-lite","displayName":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-flash-lite-image":{"metadata":{"displayName":"Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":65536,"maxOutputTokens":4096,"knowledgeCutoff":"2025-01","structuredOutput":false,"lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"google/gemini-3.1-flash-lite-image","displayName":"Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-pro-preview":{"metadata":{"displayName":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-02-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.1-pro-preview","displayName":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-01"}},"google/gemini-3.5-flash":{"metadata":{"displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.5-flash","displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-01"}},"google/gemini-3.5-flash-lite":{"metadata":{"displayName":"Gemini 3.5 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65000,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-07-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.5-flash-lite","displayName":"Gemini 3.5 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-03"}},"google/gemini-3.5-transcribe":{"metadata":{"displayName":"Gemini 3.5 Transcribe","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2026-08-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"google/gemini-3.5-transcribe","displayName":"Gemini 3.5 Transcribe","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"google/gemini-3.5-transcribe-live":{"metadata":{"displayName":"Gemini 3.5 Transcribe Live","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2026-08-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"google/gemini-3.5-transcribe-live","displayName":"Gemini 3.5 Transcribe Live","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"google/gemini-3.6-flash":{"metadata":{"displayName":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-07-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.6-flash","displayName":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-03"}},"google/gemini-3.7-flash":{"metadata":{"displayName":"Gemini 3.7 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-08-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.7-flash","displayName":"Gemini 3.7 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-03"}},"google/gemini-3.8-flash":{"metadata":{"displayName":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.8-flash","displayName":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"google/gemini-embedding-001":{"metadata":{"displayName":"Gemini Embedding 001","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"knowledgeCutoff":"2025-05","lastUpdated":"2025-05-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"google/gemini-embedding-001","displayName":"Gemini Embedding 001","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2025-05"}},"google/gemini-embedding-2":{"metadata":{"displayName":"Gemini Embedding 2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","knowledgeCutoff":"2025-11","lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"google/gemini-embedding-2","displayName":"Gemini Embedding 2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"knowledgeCutoff":"2025-11"}},"google/gemini-omni-flash-preview":{"metadata":{"displayName":"Gemini Omni Flash Preview","description":"Omni-modal model for text, vision, audio, and multimodal agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":57920,"lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-omni-flash-preview","displayName":"Gemini Omni Flash Preview","description":"Omni-modal model for text, vision, audio, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"google/gemma-4-26b-a4b-it":{"metadata":{"displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemma-4-26b-a4b-it","displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"google/gemma-4-31b-it":{"metadata":{"displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemma-4-31b-it","displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"google/text-embedding-005":{"metadata":{"displayName":"Text Embedding 005","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2024-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"google/text-embedding-005","displayName":"Text Embedding 005","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"google/text-multilingual-embedding-002":{"metadata":{"displayName":"Text Multilingual Embedding 002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2024-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"google/text-multilingual-embedding-002","displayName":"Text Multilingual Embedding 002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"google/veo-3.0-fast-generate-001":{"metadata":{"displayName":"Veo 3.0 Fast Generate","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-06-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"google/veo-3.0-fast-generate-001","displayName":"Veo 3.0 Fast Generate","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"google/veo-3.0-generate-001":{"metadata":{"displayName":"Veo 3.0","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-06-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"google/veo-3.0-generate-001","displayName":"Veo 3.0","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"google/veo-3.1-fast-generate-001":{"metadata":{"displayName":"Veo 3.1 Fast Generate","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-06-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"google/veo-3.1-fast-generate-001","displayName":"Veo 3.1 Fast Generate","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"google/veo-3.1-generate-001":{"metadata":{"displayName":"Veo 3.1","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-06-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"google/veo-3.1-generate-001","displayName":"Veo 3.1","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"google/veo-3.1-lite-generate-001":{"metadata":{"displayName":"Veo 3.1 Lite Generate","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-04-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"google/veo-3.1-lite-generate-001","displayName":"Veo 3.1 Lite Generate","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"inception/mercury-2":{"metadata":{"displayName":"Mercury 2","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"lastUpdated":"2026-03-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inception/mercury-2","displayName":"Mercury 2","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":128000,"defaultContextWindow":128000}},"inception/mercury-2.5":{"metadata":{"displayName":"Mercury 2.5","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":260000,"maxOutputTokens":65536,"lastUpdated":"2026-09-08","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inception/mercury-2.5","displayName":"Mercury 2.5","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high"],"contextWindow":260000,"defaultContextWindow":260000}},"inception/mercury-coder-small":{"metadata":{"displayName":"Mercury Coder Small Beta","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":32000,"maxOutputTokens":16384,"lastUpdated":"2025-02-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inception/mercury-coder-small","displayName":"Mercury Coder Small Beta","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"inclusionai/ling-3.0-flash":{"metadata":{"displayName":"Ling 3.0 Flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"lastUpdated":"2026-08-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash","displayName":"Ling 3.0 Flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"inclusionai/ling-3.0-flash-fin":{"metadata":{"displayName":"Ling 3.0 Flash Fin","description":"Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"lastUpdated":"2026-08-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash-fin","displayName":"Ling 3.0 Flash Fin","description":"Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"inclusionai/ling-3.0-flash-fin-free":{"metadata":{"displayName":"Ling 3.0 Flash Fin (Free)","description":"Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"lastUpdated":"2026-08-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash-fin-free","displayName":"Ling 3.0 Flash Fin (Free)","description":"Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"inclusionai/ling-3.0-flash-sante":{"metadata":{"displayName":"Ling 3.0 Flash Sante","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"lastUpdated":"2026-09-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash-sante","displayName":"Ling 3.0 Flash Sante","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"inclusionai/ling-3.0-flash-sante-free":{"metadata":{"displayName":"Ling 3.0 Flash Sante (Free)","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"lastUpdated":"2026-09-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash-sante-free","displayName":"Ling 3.0 Flash Sante (Free)","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"inclusionai/ling-3.0-flash-vl":{"metadata":{"displayName":"Ling 3.0 Flash VL","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"lastUpdated":"2026-09-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash-vl","displayName":"Ling 3.0 Flash VL","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"inclusionai/ling-3.0-flash-vl-free":{"metadata":{"displayName":"Ling 3.0 Flash VL (Free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"lastUpdated":"2026-09-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash-vl-free","displayName":"Ling 3.0 Flash VL (Free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"interfaze/interfaze-beta":{"metadata":{"displayName":"Interfaze Beta","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":32000,"lastUpdated":"2026-04-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"interfaze/interfaze-beta","displayName":"Interfaze Beta","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000}},"klingai/kling-v2.5-turbo-i2v":{"metadata":{"displayName":"Kling v2.5 Turbo Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-09-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"klingai/kling-v2.5-turbo-i2v","displayName":"Kling v2.5 Turbo Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"klingai/kling-v2.5-turbo-t2v":{"metadata":{"displayName":"Kling v2.5 Turbo Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2025-09-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"klingai/kling-v2.5-turbo-t2v","displayName":"Kling v2.5 Turbo Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"klingai/kling-v2.6-i2v":{"metadata":{"displayName":"Kling v2.6 Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-12-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"klingai/kling-v2.6-i2v","displayName":"Kling v2.6 Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"klingai/kling-v2.6-motion-control":{"metadata":{"displayName":"Kling v2.6 Motion Control","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2025-12-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"klingai/kling-v2.6-motion-control","displayName":"Kling v2.6 Motion Control","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"klingai/kling-v2.6-t2v":{"metadata":{"displayName":"Kling v2.6 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2025-12-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"klingai/kling-v2.6-t2v","displayName":"Kling v2.6 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"klingai/kling-v3.0-i2v":{"metadata":{"displayName":"Kling v3.0 Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-02-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"klingai/kling-v3.0-i2v","displayName":"Kling v3.0 Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"klingai/kling-v3.0-motion-control":{"metadata":{"displayName":"Kling v3.0 Motion Control","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-03-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"klingai/kling-v3.0-motion-control","displayName":"Kling v3.0 Motion Control","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"klingai/kling-v3.0-t2v":{"metadata":{"displayName":"Kling v3.0 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-02-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"klingai/kling-v3.0-t2v","displayName":"Kling v3.0 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"kwaipilot/kat-coder-air-v2.5":{"metadata":{"displayName":"Kat Coder Air V2.5","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":80000,"lastUpdated":"2026-07-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"kwaipilot/kat-coder-air-v2.5","displayName":"Kat Coder Air V2.5","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"kwaipilot/kat-coder-pro-v1":{"metadata":{"displayName":"KAT-Coder-Pro V1","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"knowledgeCutoff":"2024-10","lastUpdated":"2025-10-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"kwaipilot/kat-coder-pro-v1","displayName":"KAT-Coder-Pro V1","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-10"}},"kwaipilot/kat-coder-pro-v2":{"metadata":{"displayName":"Kat Coder Pro V2","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"lastUpdated":"2026-03-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"kwaipilot/kat-coder-pro-v2","displayName":"Kat Coder Pro V2","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"kwaipilot/kat-coder-pro-v2.5":{"metadata":{"displayName":"Kat Coder Pro V2.5","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":80000,"lastUpdated":"2026-07-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"kwaipilot/kat-coder-pro-v2.5","displayName":"Kat Coder Pro V2.5","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"meta/llama-3.1-70b":{"metadata":{"displayName":"Llama 3.1 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"knowledgeCutoff":"2023-12","lastUpdated":"2024-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta/llama-3.1-70b","displayName":"Llama 3.1 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-12"}},"meta/llama-3.1-8b":{"metadata":{"displayName":"Llama 3.1 8B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"knowledgeCutoff":"2023-12","lastUpdated":"2024-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta/llama-3.1-8b","displayName":"Llama 3.1 8B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-12"}},"meta/llama-3.3-70b":{"metadata":{"displayName":"Llama-3.3-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-12","lastUpdated":"2024-12-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta/llama-3.3-70b","displayName":"Llama-3.3-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-12"}},"meta/llama-4-maverick":{"metadata":{"displayName":"Llama-4-Maverick-17B-128E-Instruct-FP8","description":"Open multimodal Llama model for strong reasoning and fast responses","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2024-08","lastUpdated":"2025-04-05","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta/llama-4-maverick","displayName":"Llama-4-Maverick-17B-128E-Instruct-FP8","description":"Open multimodal Llama model for strong reasoning and fast responses","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-08"}},"meta/llama-4-scout":{"metadata":{"displayName":"Llama-4-Scout-17B-16E-Instruct-FP8","description":"Open multimodal Llama model for long-context analysis and efficient agents","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2024-08","lastUpdated":"2025-04-05","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta/llama-4-scout","displayName":"Llama-4-Scout-17B-16E-Instruct-FP8","description":"Open multimodal Llama model for long-context analysis and efficient agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-08"}},"meta/muse-glimmer-30b":{"metadata":{"displayName":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2026-01-04","structuredOutput":true,"lastUpdated":"2026-08-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta/muse-glimmer-30b","displayName":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2026-01-04"}},"meta/muse-image-1.0":{"metadata":{"displayName":"Muse Image 1.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["image"]}},"entry":{"id":"meta/muse-image-1.0","displayName":"Muse Image 1.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"meta/muse-spark-1.1":{"metadata":{"displayName":"Muse Spark 1.1","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"meta/muse-spark-1.1","displayName":"Muse Spark 1.1","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"meta/muse-spark-1.2":{"metadata":{"displayName":"Muse Spark 1.2","description":"Open Llama multimodal model for image understanding and text reasoning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"structuredOutput":true,"lastUpdated":"2026-08-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"meta/muse-spark-1.2","displayName":"Muse Spark 1.2","description":"Open Llama multimodal model for image understanding and text reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}},"meta/muse-spark-1.2-contributor":{"metadata":{"displayName":"Muse Spark 1.2 Contributor","description":"Open Llama multimodal model for image understanding and text reasoning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"lastUpdated":"2026-08-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"meta/muse-spark-1.2-contributor","displayName":"Muse Spark 1.2 Contributor","description":"Open Llama multimodal model for image understanding and text reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"meta/muse-spark-1.3":{"metadata":{"displayName":"Muse Spark 1.3","description":"Open Llama multimodal model for image understanding and text reasoning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"meta/muse-spark-1.3","displayName":"Muse Spark 1.3","description":"Open Llama multimodal model for image understanding and text reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"meta/muse-spark-1.3-contributor":{"metadata":{"displayName":"Muse Spark 1.3 Contributor","description":"Open Llama multimodal model for image understanding and text reasoning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"meta/muse-spark-1.3-contributor","displayName":"Muse Spark 1.3 Contributor","description":"Open Llama multimodal model for image understanding and text reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"minimax/minimax-h3":{"metadata":{"displayName":"MiniMax H3","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-07-30","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["video"]}},"entry":{"id":"minimax/minimax-h3","displayName":"MiniMax H3","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"minimax/minimax-h3-max":{"metadata":{"displayName":"MiniMax H3 Max","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-08-27","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["video"]}},"entry":{"id":"minimax/minimax-h3-max","displayName":"MiniMax H3 Max","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"minimax/minimax-m2":{"metadata":{"displayName":"MiniMax M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","lifecycle":"active","contextWindow":205000,"maxOutputTokens":205000,"knowledgeCutoff":"2024-10","lastUpdated":"2025-10-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2","displayName":"MiniMax M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":205000,"defaultContextWindow":205000,"knowledgeCutoff":"2024-10"}},"minimax/minimax-m2.1":{"metadata":{"displayName":"MiniMax M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2025-12-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2.1","displayName":"MiniMax M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"minimax/minimax-m2.1-lightning":{"metadata":{"displayName":"MiniMax M2.1 Lightning","description":"High-speed MiniMax model for low-latency coding and agent workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2024-10","lastUpdated":"2025-10-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2.1-lightning","displayName":"MiniMax M2.1 Lightning","description":"High-speed MiniMax model for low-latency coding and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2024-10"}},"minimax/minimax-m2.5":{"metadata":{"displayName":"MiniMax M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131000,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2.5","displayName":"MiniMax M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"minimax/minimax-m2.5-highspeed":{"metadata":{"displayName":"MiniMax M2.5 High Speed","description":"High-speed MiniMax model for low-latency coding and agent workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131000,"lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2.5-highspeed","displayName":"MiniMax M2.5 High Speed","description":"High-speed MiniMax model for low-latency coding and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"minimax/minimax-m2.7":{"metadata":{"displayName":"Minimax M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131000,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2.7","displayName":"Minimax M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"minimax/minimax-m2.7-highspeed":{"metadata":{"displayName":"MiniMax M2.7 High Speed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131100,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2.7-highspeed","displayName":"MiniMax M2.7 High Speed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"minimax/minimax-m3":{"metadata":{"displayName":"MiniMax M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","lifecycle":"active","contextWindow":512000,"maxOutputTokens":512000,"lastUpdated":"2026-06-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"minimax/minimax-m3","displayName":"MiniMax M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":512000,"defaultContextWindow":512000}},"mistral/codestral":{"metadata":{"displayName":"Codestral (latest)","description":"Mistral code model for completions, refactors, and developer IDE workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":4096,"knowledgeCutoff":"2024-10","lastUpdated":"2025-01-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistral/codestral","displayName":"Codestral (latest)","description":"Mistral code model for completions, refactors, and developer IDE workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-10"}},"mistral/codestral-embed":{"metadata":{"displayName":"Codestral Embed","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2025-05-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistral/codestral-embed","displayName":"Codestral Embed","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"mistral/devstral-2":{"metadata":{"displayName":"Devstral 2","description":"Mistral coding agent model for repository tasks and software engineering workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2024-10","lastUpdated":"2025-12-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistral/devstral-2","displayName":"Devstral 2","description":"Mistral coding agent model for repository tasks and software engineering workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-10"}},"mistral/devstral-small-2":{"metadata":{"displayName":"Devstral Small 2","description":"Mistral coding agent model for repository tasks and software engineering workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2024-10","lastUpdated":"2025-05-07","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral/devstral-small-2","displayName":"Devstral Small 2","description":"Mistral coding agent model for repository tasks and software engineering workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-10"}},"mistral/ministral-14b":{"metadata":{"displayName":"Ministral 14B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2024-10","lastUpdated":"2025-12-01","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"mistral/ministral-14b","displayName":"Ministral 14B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-10"}},"mistral/ministral-3b":{"metadata":{"displayName":"Ministral 3B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-10","lastUpdated":"2024-10-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistral/ministral-3b","displayName":"Ministral 3B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-10"}},"mistral/ministral-8b":{"metadata":{"displayName":"Ministral 8B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-10","lastUpdated":"2024-10-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistral/ministral-8b","displayName":"Ministral 8B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-10"}},"mistral/mistral-embed":{"metadata":{"displayName":"Mistral Embed","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2023-12-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistral/mistral-embed","displayName":"Mistral Embed","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"mistral/mistral-large-3":{"metadata":{"displayName":"Mistral Large 3","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2024-10","lastUpdated":"2025-12-02","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral/mistral-large-3","displayName":"Mistral Large 3","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-10"}},"mistral/mistral-medium":{"metadata":{"displayName":"Mistral Medium 3.1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2024-10","lastUpdated":"2025-05-07","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral/mistral-medium","displayName":"Mistral Medium 3.1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-10"}},"mistral/mistral-medium-3.5":{"metadata":{"displayName":"Mistral Medium Latest","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"lastUpdated":"2026-05-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral/mistral-medium-3.5","displayName":"Mistral Medium Latest","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","high"],"contextWindow":256000,"defaultContextWindow":256000}},"mistral/mistral-nemo":{"metadata":{"displayName":"Mistral Nemo","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-04","lastUpdated":"2024-07-01","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral/mistral-nemo","displayName":"Mistral Nemo","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-04"}},"mistral/mistral-small":{"metadata":{"displayName":"Mistral Small (latest)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","lifecycle":"active","contextWindow":32000,"maxOutputTokens":4000,"knowledgeCutoff":"2025-06","lastUpdated":"2026-03-16","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral/mistral-small","displayName":"Mistral Small (latest)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000,"knowledgeCutoff":"2025-06"}},"mistral/pixtral-12b":{"metadata":{"displayName":"Pixtral 12B","description":"Mistral vision-language model for image understanding and multimodal chat","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09","lastUpdated":"2024-09-01","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral/pixtral-12b","displayName":"Pixtral 12B","description":"Mistral vision-language model for image understanding and multimodal chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-09"}},"moonshotai/kimi-k2":{"metadata":{"displayName":"Kimi K2 Instruct","description":"Kimi model for long-context chat, coding, and agentic reasoning","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"lastUpdated":"2025-09-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2","displayName":"Kimi K2 Instruct","description":"Kimi model for long-context chat, coding, and agentic reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"moonshotai/kimi-k2-thinking":{"metadata":{"displayName":"Kimi K2 Thinking","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","lifecycle":"active","contextWindow":216144,"maxOutputTokens":216144,"knowledgeCutoff":"2024-08","lastUpdated":"2025-11-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2-thinking","displayName":"Kimi K2 Thinking","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":216144,"defaultContextWindow":216144,"knowledgeCutoff":"2024-08"}},"moonshotai/kimi-k2.5":{"metadata":{"displayName":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","lifecycle":"active","contextWindow":262114,"maxOutputTokens":262114,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.5","displayName":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262114,"defaultContextWindow":262114,"knowledgeCutoff":"2025-01"}},"moonshotai/kimi-k2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.6","displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000,"knowledgeCutoff":"2025-01"}},"moonshotai/kimi-k2.7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.7-code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-01"}},"moonshotai/kimi-k2.7-code-highspeed":{"metadata":{"displayName":"Kimi K2.7 Code High Speed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.7-code-highspeed","displayName":"Kimi K2.7 Code High Speed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/kimi-k3":{"metadata":{"displayName":"Kimi K3","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k3","displayName":"Kimi K3","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"moonshotai/kimi-k3-fast":{"metadata":{"displayName":"Kimi K3 Fast","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k3-fast","displayName":"Kimi K3 Fast","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"morph/morph-v3-fast":{"metadata":{"displayName":"Morph v3 Fast","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":16000,"maxOutputTokens":16000,"lastUpdated":"2024-08-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"morph/morph-v3-fast","displayName":"Morph v3 Fast","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16000,"defaultContextWindow":16000}},"morph/morph-v3-large":{"metadata":{"displayName":"Morph v3 Large","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":32000,"maxOutputTokens":32000,"lastUpdated":"2024-08-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"morph/morph-v3-large","displayName":"Morph v3 Large","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"nvidia/nemotron-3-nano-30b-a3b":{"metadata":{"displayName":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"lastUpdated":"2025-12-15","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-nano-30b-a3b","displayName":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"nvidia/nemotron-3-super-120b-a12b":{"metadata":{"displayName":"NVIDIA Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"lastUpdated":"2026-03-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-super-120b-a12b","displayName":"NVIDIA Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"nvidia/nemotron-3-ultra-550b-a55b":{"metadata":{"displayName":"Nemotron 3 Ultra","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65000,"lastUpdated":"2026-06-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-ultra-550b-a55b","displayName":"Nemotron 3 Ultra","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"nvidia/nemotron-3.5-lightning":{"metadata":{"displayName":"Nemotron 3.5 Lightning 30B","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3.5-lightning","displayName":"Nemotron 3.5 Lightning 30B","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"nvidia/nemotron-nano-12b-v2-vl":{"metadata":{"displayName":"Nvidia Nemotron Nano 12B V2 VL","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"lastUpdated":"2025-10-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-nano-12b-v2-vl","displayName":"Nvidia Nemotron Nano 12B V2 VL","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"nvidia/nemotron-nano-9b-v2":{"metadata":{"displayName":"Nvidia Nemotron Nano 9B V2","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"lastUpdated":"2025-08-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-nano-9b-v2","displayName":"Nvidia Nemotron Nano 9B V2","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"openai/gpt-3.5-turbo":{"metadata":{"displayName":"GPT-3.5 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":16385,"inputLimit":12289,"maxOutputTokens":4096,"knowledgeCutoff":"2021-09","structuredOutput":false,"lastUpdated":"2023-11-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-3.5-turbo","displayName":"GPT-3.5 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16385,"inputLimit":12289,"defaultContextWindow":16385,"defaultInputLimit":12289,"knowledgeCutoff":"2021-09"}},"openai/gpt-4-turbo":{"metadata":{"displayName":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-12","structuredOutput":false,"lastUpdated":"2024-04-09","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openai/gpt-4-turbo","displayName":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-12"}},"openai/gpt-4.1":{"metadata":{"displayName":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","lifecycle":"active","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4.1","displayName":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"openai/gpt-4.1-fast":{"metadata":{"displayName":"GPT-4.1 (Fast)","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","lifecycle":"active","contextWindow":1047576,"inputLimit":1014808,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4.1-fast","displayName":"GPT-4.1 (Fast)","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"inputLimit":1014808,"defaultContextWindow":1047576,"defaultInputLimit":1014808,"knowledgeCutoff":"2024-04"}},"openai/gpt-4.1-mini":{"metadata":{"displayName":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","lifecycle":"active","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4.1-mini","displayName":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"openai/gpt-4.1-mini-fast":{"metadata":{"displayName":"GPT-4.1 mini (Fast)","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","lifecycle":"active","contextWindow":1047576,"inputLimit":1014808,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4.1-mini-fast","displayName":"GPT-4.1 mini (Fast)","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"inputLimit":1014808,"defaultContextWindow":1047576,"defaultInputLimit":1014808,"knowledgeCutoff":"2024-04"}},"openai/gpt-4.1-nano":{"metadata":{"displayName":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","lifecycle":"deprecated","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openai/gpt-4.1-nano","displayName":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"openai/gpt-4.1-nano-fast":{"metadata":{"displayName":"GPT-4.1 nano (Fast)","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","lifecycle":"active","contextWindow":1047576,"inputLimit":1014808,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4.1-nano-fast","displayName":"GPT-4.1 nano (Fast)","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"inputLimit":1014808,"defaultContextWindow":1047576,"defaultInputLimit":1014808,"knowledgeCutoff":"2024-04"}},"openai/gpt-4o":{"metadata":{"displayName":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-08-06","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4o","displayName":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"openai/gpt-4o-fast":{"metadata":{"displayName":"GPT-4o (Fast)","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","lifecycle":"active","contextWindow":128000,"inputLimit":111616,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-08-06","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4o-fast","displayName":"GPT-4o (Fast)","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"inputLimit":111616,"defaultContextWindow":128000,"defaultInputLimit":111616,"knowledgeCutoff":"2023-09"}},"openai/gpt-4o-mini":{"metadata":{"displayName":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-07-18","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4o-mini","displayName":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"openai/gpt-4o-mini-fast":{"metadata":{"displayName":"GPT-4o mini (Fast)","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","lifecycle":"active","contextWindow":128000,"inputLimit":111616,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-07-18","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4o-mini-fast","displayName":"GPT-4o mini (Fast)","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"inputLimit":111616,"defaultContextWindow":128000,"defaultInputLimit":111616,"knowledgeCutoff":"2023-09"}},"openai/gpt-4o-mini-transcribe":{"metadata":{"displayName":"GPT-4o mini Transcribe","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2024-03-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"openai/gpt-4o-mini-transcribe","displayName":"GPT-4o mini Transcribe","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-4o-transcribe":{"metadata":{"displayName":"GPT-4o Transcribe","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2024-03-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"openai/gpt-4o-transcribe","displayName":"GPT-4o Transcribe","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-5":{"metadata":{"displayName":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openai/gpt-5","displayName":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5-codex":{"metadata":{"displayName":"GPT-5-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-09-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5-codex","displayName":"GPT-5-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5-fast":{"metadata":{"displayName":"GPT-5 (Fast)","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5-fast","displayName":"GPT-5 (Fast)","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5-mini":{"metadata":{"displayName":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-05-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openai/gpt-5-mini","displayName":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-05-30"}},"openai/gpt-5-mini-fast":{"metadata":{"displayName":"GPT-5 mini (Fast)","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-05-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5-mini-fast","displayName":"GPT-5 mini (Fast)","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-05-30"}},"openai/gpt-5-nano":{"metadata":{"displayName":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-05-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openai/gpt-5-nano","displayName":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-05-30"}},"openai/gpt-5-pro":{"metadata":{"displayName":"GPT-5 pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","lifecycle":"active","contextWindow":400000,"inputLimit":128000,"maxOutputTokens":272000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-10-06","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5-pro","displayName":"GPT-5 pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high"],"contextWindow":400000,"inputLimit":128000,"defaultContextWindow":400000,"defaultInputLimit":128000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5.1-codex":{"metadata":{"displayName":"GPT-5.1-Codex","description":"Codex GPT for repository edits, code review, and practical software agents","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.1-codex","displayName":"GPT-5.1-Codex","description":"Codex GPT for repository edits, code review, and practical software agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5.1-codex-max":{"metadata":{"displayName":"GPT 5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.1-codex-max","displayName":"GPT 5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5.1-codex-mini":{"metadata":{"displayName":"GPT-5.1 Codex mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.1-codex-mini","displayName":"GPT-5.1 Codex mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5.1-thinking":{"metadata":{"displayName":"GPT 5.1 Thinking","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-10","lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text","image"]}},"entry":{"id":"openai/gpt-5.1-thinking","displayName":"GPT 5.1 Thinking","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-10"}},"openai/gpt-5.1-thinking-fast":{"metadata":{"displayName":"GPT 5.1 Thinking (Fast)","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"lastUpdated":"2025-11-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.1-thinking-fast","displayName":"GPT 5.1 Thinking (Fast)","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000}},"openai/gpt-5.2":{"metadata":{"displayName":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-10","structuredOutput":true,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.2","displayName":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-10"}},"openai/gpt-5.2-codex":{"metadata":{"displayName":"GPT-5.2-Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.2-codex","displayName":"GPT-5.2-Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.2-fast":{"metadata":{"displayName":"GPT 5.2 (Fast)","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.2-fast","displayName":"GPT 5.2 (Fast)","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.2-pro":{"metadata":{"displayName":"GPT 5.2 ","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":false,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.2-pro","displayName":"GPT 5.2 ","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.3-codex":{"metadata":{"displayName":"GPT 5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-02-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.3-codex","displayName":"GPT 5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.3-codex-fast":{"metadata":{"displayName":"GPT 5.3 Codex (Fast)","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-02-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.3-codex-fast","displayName":"GPT 5.3 Codex (Fast)","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4":{"metadata":{"displayName":"GPT 5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.4","displayName":"GPT 5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4-fast":{"metadata":{"displayName":"GPT 5.4 (Fast)","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.4-fast","displayName":"GPT 5.4 (Fast)","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4-mini":{"metadata":{"displayName":"GPT 5.4 Mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.4-mini","displayName":"GPT 5.4 Mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4-mini-fast":{"metadata":{"displayName":"GPT 5.4 Mini (Fast)","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.4-mini-fast","displayName":"GPT 5.4 Mini (Fast)","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4-nano":{"metadata":{"displayName":"GPT 5.4 Nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.4-nano","displayName":"GPT 5.4 Nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4-pro":{"metadata":{"displayName":"GPT 5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":false,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.4-pro","displayName":"GPT 5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.5":{"metadata":{"displayName":"GPT 5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","lifecycle":"active","contextWindow":1000000,"inputLimit":872000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.5","displayName":"GPT 5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1000000,"inputLimit":872000,"defaultContextWindow":1000000,"defaultInputLimit":872000,"knowledgeCutoff":"2025-12-01"}},"openai/gpt-5.5-fast":{"metadata":{"displayName":"GPT 5.5 (Fast)","description":"Default frontier GPT for coding, computer use, research, and knowledge work","lifecycle":"active","contextWindow":1000000,"inputLimit":872000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.5-fast","displayName":"GPT 5.5 (Fast)","description":"Default frontier GPT for coding, computer use, research, and knowledge work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1000000,"inputLimit":872000,"defaultContextWindow":1000000,"defaultInputLimit":872000,"knowledgeCutoff":"2025-12-01"}},"openai/gpt-5.5-pro":{"metadata":{"displayName":"GPT 5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","lifecycle":"active","contextWindow":1000000,"inputLimit":872000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.5-pro","displayName":"GPT 5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1000000,"inputLimit":872000,"defaultContextWindow":1000000,"defaultInputLimit":872000,"knowledgeCutoff":"2025-12-01"}},"openai/gpt-5.6-luna":{"metadata":{"displayName":"GPT 5.6 Luna","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-luna","displayName":"GPT 5.6 Luna","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-luna-fast":{"metadata":{"displayName":"GPT 5.6 Luna (Fast)","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-luna-fast","displayName":"GPT 5.6 Luna (Fast)","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-sol":{"metadata":{"displayName":"GPT 5.6 Sol","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-sol","displayName":"GPT 5.6 Sol","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-sol-fast":{"metadata":{"displayName":"GPT 5.6 Sol (Fast)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-sol-fast","displayName":"GPT 5.6 Sol (Fast)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-terra":{"metadata":{"displayName":"GPT 5.6 Terra","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-terra","displayName":"GPT 5.6 Terra","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-terra-fast":{"metadata":{"displayName":"GPT 5.6 Terra (Fast)","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-terra-fast","displayName":"GPT 5.6 Terra (Fast)","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-6-astra":{"metadata":{"displayName":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-04-30","structuredOutput":true,"lastUpdated":"2026-09-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-6-astra","displayName":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-04-30"}},"openai/gpt-6-astra-fast":{"metadata":{"displayName":"GPT-6 Astra (Fast)","description":"Fast variant of GPT-6 Astra for low-latency assistance and high-volume workloads.","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-09-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-6-astra-fast","displayName":"GPT-6 Astra (Fast)","description":"Fast variant of GPT-6 Astra for low-latency assistance and high-volume workloads.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000}},"openai/gpt-image-1":{"metadata":{"displayName":"GPT Image 1","description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","lifecycle":"active","lastUpdated":"2025-04-24","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"openai/gpt-image-1","displayName":"GPT Image 1","description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-image-1-mini":{"metadata":{"displayName":"GPT Image 1 Mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-10-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"openai/gpt-image-1-mini","displayName":"GPT Image 1 Mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-image-1.5":{"metadata":{"displayName":"GPT Image 1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"openai/gpt-image-1.5","displayName":"GPT Image 1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-image-2":{"metadata":{"displayName":"GPT Image 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-04-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"openai/gpt-image-2","displayName":"GPT Image 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-image-2.5-flare":{"metadata":{"displayName":"GPT Image 2.5 Flare","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-09-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"openai/gpt-image-2.5-flare","displayName":"GPT Image 2.5 Flare","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-image-2.5-sunburst":{"metadata":{"displayName":"GPT Image 2.5 Sunburst","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-09-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"openai/gpt-image-2.5-sunburst","displayName":"GPT Image 2.5 Sunburst","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-oss-120b":{"metadata":{"displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2024-10","structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-120b","displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-10"}},"openai/gpt-oss-20b":{"metadata":{"displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"inputLimit":122880,"maxOutputTokens":8192,"knowledgeCutoff":"2024-10","structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-20b","displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"inputLimit":122880,"defaultContextWindow":131072,"defaultInputLimit":122880,"knowledgeCutoff":"2024-10"}},"openai/gpt-oss-safeguard-120b":{"metadata":{"displayName":"GPT OSS Safeguard 120B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"active","contextWindow":128000,"inputLimit":112000,"maxOutputTokens":16000,"structuredOutput":true,"lastUpdated":"2025-10-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-safeguard-120b","displayName":"GPT OSS Safeguard 120B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":128000,"inputLimit":112000,"defaultContextWindow":128000,"defaultInputLimit":112000}},"openai/gpt-oss-safeguard-20b":{"metadata":{"displayName":"gpt-oss-safeguard-20b","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"active","contextWindow":128000,"inputLimit":112000,"maxOutputTokens":16000,"structuredOutput":true,"lastUpdated":"2025-10-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-safeguard-20b","displayName":"gpt-oss-safeguard-20b","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":128000,"inputLimit":112000,"defaultContextWindow":128000,"defaultInputLimit":112000}},"openai/gpt-realtime-1.5":{"metadata":{"displayName":"GPT-Realtime-1.5","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-02-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","audio"],"output":["text","audio"]}},"entry":{"id":"openai/gpt-realtime-1.5","displayName":"GPT-Realtime-1.5","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-realtime-2":{"metadata":{"displayName":"gpt-realtime-2","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-05-07","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","audio"],"output":["text","audio"]}},"entry":{"id":"openai/gpt-realtime-2","displayName":"gpt-realtime-2","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-realtime-2.1":{"metadata":{"displayName":"gpt-realtime-2.1","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":128000,"inputLimit":96000,"maxOutputTokens":32000,"knowledgeCutoff":"2024-09-30","structuredOutput":false,"lastUpdated":"2026-07-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","audio"],"output":["text","audio"]}},"entry":{"id":"openai/gpt-realtime-2.1","displayName":"gpt-realtime-2.1","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":128000,"inputLimit":96000,"defaultContextWindow":128000,"defaultInputLimit":96000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-realtime-mini":{"metadata":{"displayName":"GPT-Realtime mini","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2025-10-10","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","audio"],"output":["text","audio"]}},"entry":{"id":"openai/gpt-realtime-mini","displayName":"GPT-Realtime mini","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-realtime-whisper":{"metadata":{"displayName":"gpt-realtime-whisper","description":"Streaming speech-to-text model for low-latency transcript deltas from live audio","lifecycle":"active","lastUpdated":"2026-05-07","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"openai/gpt-realtime-whisper","displayName":"gpt-realtime-whisper","description":"Streaming speech-to-text model for low-latency transcript deltas from live audio","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/o1":{"metadata":{"displayName":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-12-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/o1","displayName":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2023-09"}},"openai/o3":{"metadata":{"displayName":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/o3","displayName":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"openai/o3-fast":{"metadata":{"displayName":"o3 (Fast)","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","lifecycle":"active","contextWindow":200000,"inputLimit":100000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/o3-fast","displayName":"o3 (Fast)","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"inputLimit":100000,"defaultContextWindow":200000,"defaultInputLimit":100000,"knowledgeCutoff":"2024-05"}},"openai/o3-mini":{"metadata":{"displayName":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-01-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/o3-mini","displayName":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"openai/o3-pro":{"metadata":{"displayName":"o3 Pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","lifecycle":"active","contextWindow":200000,"inputLimit":100000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-10","structuredOutput":true,"lastUpdated":"2025-06-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/o3-pro","displayName":"o3 Pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"inputLimit":100000,"defaultContextWindow":200000,"defaultInputLimit":100000,"knowledgeCutoff":"2024-10"}},"openai/o4-mini":{"metadata":{"displayName":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openai/o4-mini","displayName":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"openai/o4-mini-fast":{"metadata":{"displayName":"o4-mini (Fast)","description":"Fast o-series model for compact reasoning, coding, and tool use","lifecycle":"active","contextWindow":200000,"inputLimit":100000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/o4-mini-fast","displayName":"o4-mini (Fast)","description":"Fast o-series model for compact reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"inputLimit":100000,"defaultContextWindow":200000,"defaultInputLimit":100000,"knowledgeCutoff":"2024-05"}},"openai/text-embedding-3-large":{"metadata":{"displayName":"text-embedding-3-large","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8192,"inputLimit":6656,"maxOutputTokens":1536,"lastUpdated":"2024-01-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/text-embedding-3-large","displayName":"text-embedding-3-large","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"inputLimit":6656,"defaultContextWindow":8192,"defaultInputLimit":6656}},"openai/text-embedding-3-small":{"metadata":{"displayName":"text-embedding-3-small","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8192,"inputLimit":6656,"maxOutputTokens":1536,"lastUpdated":"2024-01-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/text-embedding-3-small","displayName":"text-embedding-3-small","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"inputLimit":6656,"defaultContextWindow":8192,"defaultInputLimit":6656}},"openai/text-embedding-ada-002":{"metadata":{"displayName":"text-embedding-ada-002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8192,"inputLimit":6656,"maxOutputTokens":1536,"lastUpdated":"2022-12-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/text-embedding-ada-002","displayName":"text-embedding-ada-002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"inputLimit":6656,"defaultContextWindow":8192,"defaultInputLimit":6656}},"openai/tts-1":{"metadata":{"displayName":"TTS-1","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2023-11-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"openai/tts-1","displayName":"TTS-1","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/tts-1-hd":{"metadata":{"displayName":"TTS-1 HD","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2023-11-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"openai/tts-1-hd","displayName":"TTS-1 HD","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/whisper-1":{"metadata":{"displayName":"Whisper","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2022-09-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"openai/whisper-1","displayName":"Whisper","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"perplexity/pplx-embed-v1-0.6b":{"metadata":{"displayName":"Embed v1 0.6b","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":32000,"lastUpdated":"2026-02-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"perplexity/pplx-embed-v1-0.6b","displayName":"Embed v1 0.6b","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"perplexity/pplx-embed-v1-4b":{"metadata":{"displayName":"Embed v1 4b","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":32000,"lastUpdated":"2026-02-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"perplexity/pplx-embed-v1-4b","displayName":"Embed v1 4b","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"perplexity/sonar":{"metadata":{"displayName":"Sonar","description":"Sonar search model for current answers, retrieval, and citation-backed chat","lifecycle":"active","contextWindow":127000,"maxOutputTokens":8000,"knowledgeCutoff":"2025-02","lastUpdated":"2025-02-19","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"perplexity/sonar","displayName":"Sonar","description":"Sonar search model for current answers, retrieval, and citation-backed chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":127000,"defaultContextWindow":127000,"knowledgeCutoff":"2025-02"}},"perplexity/sonar-pro":{"metadata":{"displayName":"Sonar Pro","description":"Advanced Sonar search model for deeper research and cited synthesis","lifecycle":"active","contextWindow":200000,"maxOutputTokens":8000,"knowledgeCutoff":"2025-09","lastUpdated":"2025-02-19","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"perplexity/sonar-pro","displayName":"Sonar Pro","description":"Advanced Sonar search model for deeper research and cited synthesis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-09"}},"perplexity/sonar-reasoning-pro":{"metadata":{"displayName":"Sonar Reasoning Pro","description":"Web-grounded reasoning model for multi-step research and cited answers","lifecycle":"active","contextWindow":127000,"maxOutputTokens":8000,"knowledgeCutoff":"2025-09","lastUpdated":"2025-02-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"perplexity/sonar-reasoning-pro","displayName":"Sonar Reasoning Pro","description":"Web-grounded reasoning model for multi-step research and cited answers","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":127000,"defaultContextWindow":127000,"knowledgeCutoff":"2025-09"}},"poolside/laguna-s-2.1":{"metadata":{"displayName":"Laguna S 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":false,"lastUpdated":"2026-07-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"poolside/laguna-s-2.1","displayName":"Laguna S 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"poolside/laguna-s-2.1-free":{"metadata":{"displayName":"Laguna S 2.1 Free","description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-07-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"poolside/laguna-s-2.1-free","displayName":"Laguna S 2.1 Free","description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"prodia/flux-fast-schnell":{"metadata":{"displayName":"Flux Schnell","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":512,"lastUpdated":"2026-06-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"prodia/flux-fast-schnell","displayName":"Flux Schnell","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":512,"defaultContextWindow":512}},"quiverai/arrow-1.1":{"metadata":{"displayName":"Arrow 1.1","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"lastUpdated":"2026-04-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"quiverai/arrow-1.1","displayName":"Arrow 1.1","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"recraft/recraft-v2":{"metadata":{"displayName":"Recraft V2","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":512,"lastUpdated":"2024-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"recraft/recraft-v2","displayName":"Recraft V2","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":512,"defaultContextWindow":512}},"recraft/recraft-v3":{"metadata":{"displayName":"Recraft V3","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":512,"lastUpdated":"2024-10","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"recraft/recraft-v3","displayName":"Recraft V3","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":512,"defaultContextWindow":512}},"recraft/recraft-v4":{"metadata":{"displayName":"Recraft V4","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-02-17","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"recraft/recraft-v4","displayName":"Recraft V4","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"recraft/recraft-v4-pro":{"metadata":{"displayName":"Recraft V4 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-02-17","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"recraft/recraft-v4-pro","displayName":"Recraft V4 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"recraft/recraft-v4.1":{"metadata":{"displayName":"Recraft V4.1","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-05-14","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"recraft/recraft-v4.1","displayName":"Recraft V4.1","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"recraft/recraft-v4.1-pro":{"metadata":{"displayName":"Recraft V4.1 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-05-14","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"recraft/recraft-v4.1-pro","displayName":"Recraft V4.1 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"recraft/recraft-v4.1-utility":{"metadata":{"displayName":"Recraft V4.1 Utility","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-05-14","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"recraft/recraft-v4.1-utility","displayName":"Recraft V4.1 Utility","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"recraft/recraft-v4.1-utility-pro":{"metadata":{"displayName":"Recraft V4.1 Utility Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-05-14","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"recraft/recraft-v4.1-utility-pro","displayName":"Recraft V4.1 Utility Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"sakana/fugu-max":{"metadata":{"displayName":"Fugu Max","description":"Multi-agent model for routing expert agents across complex analytical tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":1000000,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"sakana/fugu-max","displayName":"Fugu Max","description":"Multi-agent model for routing expert agents across complex analytical tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"sakana/fugu-ultra":{"metadata":{"displayName":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":1000000,"structuredOutput":true,"lastUpdated":"2026-06-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"sakana/fugu-ultra","displayName":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"sakana/fugu-ultra-v2":{"metadata":{"displayName":"Fugu Ultra v2","description":"Quality-first multi-agent model for hard research, analysis, and competitions","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":1000000,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"sakana/fugu-ultra-v2","displayName":"Fugu Ultra v2","description":"Quality-first multi-agent model for hard research, analysis, and competitions","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"sakana/namazu":{"metadata":{"displayName":"Sakana Namazu","description":"Multi-agent model for routing expert agents across complex analytical tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"lastUpdated":"2026-08-03","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"sakana/namazu","displayName":"Sakana Namazu","description":"Multi-agent model for routing expert agents across complex analytical tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"spacexai/grok-4.1-fast-non-reasoning":{"metadata":{"displayName":"Grok 4.1 Fast Non-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":1000000,"lastUpdated":"2025-11-19","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"spacexai/grok-4.1-fast-non-reasoning","displayName":"Grok 4.1 Fast Non-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"spacexai/grok-4.1-fast-reasoning":{"metadata":{"displayName":"Grok 4.1 Fast Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":1000000,"structuredOutput":true,"lastUpdated":"2025-11-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"spacexai/grok-4.1-fast-reasoning","displayName":"Grok 4.1 Fast Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"spacexai/grok-4.20-multi-agent":{"metadata":{"displayName":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":2000000,"lastUpdated":"2026-03-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"spacexai/grok-4.20-multi-agent","displayName":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000}},"spacexai/grok-4.20-multi-agent-beta":{"metadata":{"displayName":"Grok 4.20 Multi Agent Beta","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":2000000,"lastUpdated":"2026-03-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"spacexai/grok-4.20-multi-agent-beta","displayName":"Grok 4.20 Multi Agent Beta","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000}},"spacexai/grok-4.20-non-reasoning":{"metadata":{"displayName":"Grok 4.20 Non-Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":2000000,"lastUpdated":"2026-03-10","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"spacexai/grok-4.20-non-reasoning","displayName":"Grok 4.20 Non-Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000}},"spacexai/grok-4.20-non-reasoning-beta":{"metadata":{"displayName":"Grok 4.20 Beta Non-Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":2000000,"lastUpdated":"2026-03-11","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"spacexai/grok-4.20-non-reasoning-beta","displayName":"Grok 4.20 Beta Non-Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000}},"spacexai/grok-4.20-reasoning":{"metadata":{"displayName":"Grok 4.20 Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":2000000,"lastUpdated":"2026-03-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"spacexai/grok-4.20-reasoning","displayName":"Grok 4.20 Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000}},"spacexai/grok-4.20-reasoning-beta":{"metadata":{"displayName":"Grok 4.20 Beta Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":2000000,"lastUpdated":"2026-03-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"spacexai/grok-4.20-reasoning-beta","displayName":"Grok 4.20 Beta Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000}},"spacexai/grok-4.3":{"metadata":{"displayName":"Grok 4.3","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":1000000,"structuredOutput":true,"lastUpdated":"2026-04-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"spacexai/grok-4.3","displayName":"Grok 4.3","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000}},"spacexai/grok-4.5":{"metadata":{"displayName":"Grok 4.5","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":500000,"maxOutputTokens":500000,"structuredOutput":true,"lastUpdated":"2026-07-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"spacexai/grok-4.5","displayName":"Grok 4.5","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":500000,"defaultContextWindow":500000}},"spacexai/grok-4.6":{"metadata":{"displayName":"Grok 4.6","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":500000,"maxOutputTokens":500000,"knowledgeCutoff":"2026-02-01","structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"spacexai/grok-4.6","displayName":"Grok 4.6","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":500000,"defaultContextWindow":500000,"knowledgeCutoff":"2026-02-01"}},"spacexai/grok-build-0.1":{"metadata":{"displayName":"Grok Build 0.1","description":"Grok coding model for agentic engineering, edits, and codebase workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"structuredOutput":true,"lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"spacexai/grok-build-0.1","displayName":"Grok Build 0.1","description":"Grok coding model for agentic engineering, edits, and codebase workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"spacexai/grok-imagine-image":{"metadata":{"displayName":"Grok Imagine Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-01-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"spacexai/grok-imagine-image","displayName":"Grok Imagine Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"spacexai/grok-imagine-image-2.0":{"metadata":{"displayName":"Grok Imagine Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-08-07","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"spacexai/grok-imagine-image-2.0","displayName":"Grok Imagine Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"spacexai/grok-imagine-video":{"metadata":{"displayName":"Grok Imagine","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-01-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"spacexai/grok-imagine-video","displayName":"Grok Imagine","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"spacexai/grok-imagine-video-1.5":{"metadata":{"displayName":"Grok Imagine Video 1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-05-30","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"spacexai/grok-imagine-video-1.5","displayName":"Grok Imagine Video 1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"spacexai/grok-stt":{"metadata":{"displayName":"Grok STT","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2026-03-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"spacexai/grok-stt","displayName":"Grok STT","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"spacexai/grok-tts":{"metadata":{"displayName":"Grok TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-03-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"spacexai/grok-tts","displayName":"Grok TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"spacexai/grok-voice-think-fast-1.0":{"metadata":{"displayName":"Grok Voice Think Fast 1.0","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-04-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","audio"],"output":["text","audio"]}},"entry":{"id":"spacexai/grok-voice-think-fast-1.0","displayName":"Grok Voice Think Fast 1.0","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"spacexai/grok-voice-think-fast-2.0":{"metadata":{"displayName":"Grok Voice Think Fast 2.0","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-07-29","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","audio"],"output":["text","audio"]}},"entry":{"id":"spacexai/grok-voice-think-fast-2.0","displayName":"Grok Voice Think Fast 2.0","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"stepfun/step-3.5-flash":{"metadata":{"displayName":"StepFun 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","lifecycle":"active","contextWindow":262114,"maxOutputTokens":262114,"knowledgeCutoff":"2025-01","lastUpdated":"2026-02-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"stepfun/step-3.5-flash","displayName":"StepFun 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":262114,"defaultContextWindow":262114,"knowledgeCutoff":"2025-01"}},"stepfun/step-3.7-flash":{"metadata":{"displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2026-03-01","lastUpdated":"2026-05-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"stepfun/step-3.7-flash","displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2026-03-01"}},"tencent/hy-mt2-lite":{"metadata":{"displayName":"Tencent Hy-MT2-Lite","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":8000,"maxOutputTokens":4000,"lastUpdated":"2026-06-12","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy-mt2-lite","displayName":"Tencent Hy-MT2-Lite","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8000,"defaultContextWindow":8000}},"tencent/hy-mt2-plus":{"metadata":{"displayName":"Tencent Hy-MT2-Plus","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":8000,"maxOutputTokens":4000,"lastUpdated":"2026-06-12","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy-mt2-plus","displayName":"Tencent Hy-MT2-Plus","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8000,"defaultContextWindow":8000}},"tencent/hy-mt2-pro":{"metadata":{"displayName":"Tencent Hy-MT2-Pro","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":8000,"maxOutputTokens":4000,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy-mt2-pro","displayName":"Tencent Hy-MT2-Pro","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8000,"defaultContextWindow":8000}},"tencent/hy3":{"metadata":{"displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"lastUpdated":"2026-07-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy3","displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","high"],"contextWindow":262144,"defaultContextWindow":262144}},"tencent/hy4-preview":{"metadata":{"displayName":"Tencent Hy4 Preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":64000,"lastUpdated":"2026-08-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy4-preview","displayName":"Tencent Hy4 Preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high"],"contextWindow":1024000,"defaultContextWindow":1024000}},"thinkingmachines/inkling":{"metadata":{"displayName":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"lastUpdated":"2026-07-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","minimal","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"thinkingmachines/inkling","displayName":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","minimal","low","medium","high","xhigh","max"],"contextWindow":256000,"defaultContextWindow":256000}},"thinkingmachines/inkling-small":{"metadata":{"displayName":"Inkling Small","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":1000000,"lastUpdated":"2026-07-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","minimal","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"thinkingmachines/inkling-small","displayName":"Inkling Small","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","minimal","low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"voyage/rerank-2.5":{"metadata":{"displayName":"Voyage Rerank 2.5","description":"Reranking model for improving retrieval quality in search and recommendation systems","lifecycle":"active","contextWindow":32000,"maxOutputTokens":32000,"lastUpdated":"2025-08-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/rerank-2.5","displayName":"Voyage Rerank 2.5","description":"Reranking model for improving retrieval quality in search and recommendation systems","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"voyage/rerank-2.5-lite":{"metadata":{"displayName":"Voyage Rerank 2.5 Lite","description":"Reranking model for improving retrieval quality in search and recommendation systems","lifecycle":"active","contextWindow":32000,"maxOutputTokens":32000,"lastUpdated":"2025-08-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/rerank-2.5-lite","displayName":"Voyage Rerank 2.5 Lite","description":"Reranking model for improving retrieval quality in search and recommendation systems","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"voyage/voyage-3-large":{"metadata":{"displayName":"voyage-3-large","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/voyage-3-large","displayName":"voyage-3-large","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"voyage/voyage-3.5":{"metadata":{"displayName":"voyage-3.5","description":"General-purpose chat model for instruction following, writing, and analysis","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2025-05-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/voyage-3.5","displayName":"voyage-3.5","description":"General-purpose chat model for instruction following, writing, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"voyage/voyage-3.5-lite":{"metadata":{"displayName":"voyage-3.5-lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2025-05-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/voyage-3.5-lite","displayName":"voyage-3.5-lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"voyage/voyage-4":{"metadata":{"displayName":"voyage-4","description":"General-purpose chat model for instruction following, writing, and analysis","lifecycle":"active","contextWindow":32000,"lastUpdated":"2026-03-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/voyage-4","displayName":"voyage-4","description":"General-purpose chat model for instruction following, writing, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"voyage/voyage-4-large":{"metadata":{"displayName":"voyage-4-large","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":32000,"lastUpdated":"2026-03-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/voyage-4-large","displayName":"voyage-4-large","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"voyage/voyage-4-lite":{"metadata":{"displayName":"voyage-4-lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":32000,"lastUpdated":"2026-03-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/voyage-4-lite","displayName":"voyage-4-lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"voyage/voyage-code-2":{"metadata":{"displayName":"voyage-code-2","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2024-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/voyage-code-2","displayName":"voyage-code-2","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"voyage/voyage-code-3":{"metadata":{"displayName":"voyage-code-3","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/voyage-code-3","displayName":"voyage-code-3","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"voyage/voyage-finance-2":{"metadata":{"displayName":"voyage-finance-2","description":"General-purpose chat model for instruction following, writing, and analysis","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2024-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/voyage-finance-2","displayName":"voyage-finance-2","description":"General-purpose chat model for instruction following, writing, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"voyage/voyage-law-2":{"metadata":{"displayName":"voyage-law-2","description":"General-purpose chat model for instruction following, writing, and analysis","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2024-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/voyage-law-2","displayName":"voyage-law-2","description":"General-purpose chat model for instruction following, writing, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"xiaomi/mimo-v2.5":{"metadata":{"displayName":"MiMo M2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":131100,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"xiaomi/mimo-v2.5","displayName":"MiMo M2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2024-12"}},"xiaomi/mimo-v2.5-pro":{"metadata":{"displayName":"MiMo V2.5 Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":131000,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"xiaomi/mimo-v2.5-pro","displayName":"MiMo V2.5 Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2024-12"}},"zai/glm-4.5":{"metadata":{"displayName":"GLM 4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","lifecycle":"active","contextWindow":128000,"maxOutputTokens":96000,"knowledgeCutoff":"2025-07","lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-4.5","displayName":"GLM 4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-07"}},"zai/glm-4.5-air":{"metadata":{"displayName":"GLM 4.5 Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","lifecycle":"active","contextWindow":128000,"maxOutputTokens":96000,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-4.5-air","displayName":"GLM 4.5 Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-04"}},"zai/glm-4.5v":{"metadata":{"displayName":"GLM 4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":66000,"maxOutputTokens":16000,"knowledgeCutoff":"2025-08","lastUpdated":"2025-08-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"zai/glm-4.5v","displayName":"GLM 4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":66000,"defaultContextWindow":66000,"knowledgeCutoff":"2025-08"}},"zai/glm-4.6":{"metadata":{"displayName":"GLM 4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","lifecycle":"active","contextWindow":200000,"maxOutputTokens":96000,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-4.6","displayName":"GLM 4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-04"}},"zai/glm-4.7":{"metadata":{"displayName":"GLM 4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","lifecycle":"active","contextWindow":200000,"maxOutputTokens":120000,"knowledgeCutoff":"2025-04","lastUpdated":"2025-12-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-4.7","displayName":"GLM 4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-04"}},"zai/glm-4.7-flash":{"metadata":{"displayName":"GLM 4.7 Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","lifecycle":"active","contextWindow":200000,"maxOutputTokens":131000,"knowledgeCutoff":"2025-04","lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-4.7-flash","displayName":"GLM 4.7 Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-04"}},"zai/glm-4.7-flashx":{"metadata":{"displayName":"GLM 4.7 FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":200000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-4.7-flashx","displayName":"GLM 4.7 FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01"}},"zai/glm-5":{"metadata":{"displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","lifecycle":"active","contextWindow":202800,"maxOutputTokens":131100,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-5","displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202800,"defaultContextWindow":202800}},"zai/glm-5-turbo":{"metadata":{"displayName":"GLM 5 Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","lifecycle":"active","contextWindow":202800,"maxOutputTokens":131100,"structuredOutput":true,"lastUpdated":"2026-03-16","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-5-turbo","displayName":"GLM 5 Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202800,"defaultContextWindow":202800}},"zai/glm-5.1":{"metadata":{"displayName":"GLM 5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","lifecycle":"active","contextWindow":202800,"maxOutputTokens":64000,"structuredOutput":true,"lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-5.1","displayName":"GLM 5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202800,"defaultContextWindow":202800}},"zai/glm-5.2":{"metadata":{"displayName":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-5.2","displayName":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"zai/glm-5.2-fast":{"metadata":{"displayName":"GLM 5.2 Fast","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-5.2-fast","displayName":"GLM 5.2 Fast","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"zai/glm-5.3":{"metadata":{"displayName":"GLM 5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":1000000,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-5.3","displayName":"GLM 5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"zai/glm-5.3-fast":{"metadata":{"displayName":"GLM 5.3 Fast","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-5.3-fast","displayName":"GLM 5.3 Fast","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"zai/glm-5.3-flash":{"metadata":{"displayName":"GLM 5.3 Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131000,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"zai/glm-5.3-flash","displayName":"GLM 5.3 Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"zai/glm-5v-turbo":{"metadata":{"displayName":"GLM 5V Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","lifecycle":"active","contextWindow":200000,"maxOutputTokens":128000,"lastUpdated":"2026-04-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"zai/glm-5v-turbo","displayName":"GLM 5V Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}}}},"xai":{"baseUrl":"https://api.x.ai/v1","label":"xAI","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["grok-4.5","grok-4.20-0309-non-reasoning","grok-4.20-0309-reasoning","grok-4.3","grok-4.6","grok-build-0.1"],"models":{"grok-4.20-0309-non-reasoning":{"metadata":{"displayName":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":30000,"structuredOutput":true,"lastUpdated":"2026-03-09","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.20-0309-non-reasoning","displayName":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"grok-4.20-0309-reasoning":{"metadata":{"displayName":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":30000,"structuredOutput":true,"lastUpdated":"2026-03-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.20-0309-reasoning","displayName":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"grok-4.20-multi-agent-0309":{"metadata":{"displayName":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":30000,"structuredOutput":true,"lastUpdated":"2026-03-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.20-multi-agent-0309","displayName":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"grok-4.3":{"metadata":{"displayName":"Grok 4.3","description":"xAI's Grok for chat, coding, agentic tools, and lower hallucination risk","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":30000,"structuredOutput":true,"lastUpdated":"2026-04-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.3","displayName":"Grok 4.3","description":"xAI's Grok for chat, coding, agentic tools, and lower hallucination risk","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000}},"grok-4.5":{"metadata":{"displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","lifecycle":"active","contextWindow":500000,"maxOutputTokens":500000,"structuredOutput":true,"lastUpdated":"2026-07-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.5","displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":500000,"defaultContextWindow":500000}},"grok-4.6":{"metadata":{"displayName":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","lifecycle":"active","contextWindow":500000,"maxOutputTokens":500000,"knowledgeCutoff":"2026-02-01","structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.6","displayName":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":500000,"defaultContextWindow":500000,"knowledgeCutoff":"2026-02-01"}},"grok-build-0.1":{"metadata":{"displayName":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"structuredOutput":true,"lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-build-0.1","displayName":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"grok-imagine-image":{"metadata":{"displayName":"Grok Imagine Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":16000,"lastUpdated":"2026-01-28","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","pdf"],"output":["image","pdf"]}},"entry":{"id":"grok-imagine-image","displayName":"Grok Imagine Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":16000,"defaultContextWindow":16000}},"grok-imagine-image-2.0":{"metadata":{"displayName":"Grok Imagine Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":64000,"lastUpdated":"2026-08-07","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","pdf"],"output":["image","pdf"]}},"entry":{"id":"grok-imagine-image-2.0","displayName":"Grok Imagine Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":64000,"defaultContextWindow":64000}},"grok-imagine-image-quality":{"metadata":{"displayName":"Grok Imagine Image Quality","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":16000,"lastUpdated":"2026-04-03","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","pdf"],"output":["image","pdf"]}},"entry":{"id":"grok-imagine-image-quality","displayName":"Grok Imagine Image Quality","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":16000,"defaultContextWindow":16000}},"grok-imagine-video":{"metadata":{"displayName":"Grok Imagine Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":1024,"lastUpdated":"2026-01-28","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","video","pdf"],"output":["video"]}},"entry":{"id":"grok-imagine-video","displayName":"Grok Imagine Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1024,"defaultContextWindow":1024}},"grok-imagine-video-1.5":{"metadata":{"displayName":"Grok Imagine Video 1.5","description":"Video model for image-to-video generation, editing, and extension workflows","lifecycle":"active","contextWindow":1024,"lastUpdated":"2026-05-30","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","audio","pdf"],"output":["video"]}},"entry":{"id":"grok-imagine-video-1.5","displayName":"Grok Imagine Video 1.5","description":"Video model for image-to-video generation, editing, and extension workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1024,"defaultContextWindow":1024}}}},"xai-oauth":{"baseUrl":"https://api.x.ai/v1","label":"xAI OAuth (SuperGrok / X Premium)","authKind":"oauth_token","runtimeAdapter":{"kind":"openai-compatible","name":"provider","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol","auth":"oauth-bearer"},"fallbackModels":["grok-4.5","grok-4.20-0309-non-reasoning","grok-4.20-0309-reasoning","grok-4.3","grok-4.6","grok-build-0.1"],"models":{"grok-4.20-0309-non-reasoning":{"metadata":{"displayName":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":30000,"structuredOutput":true,"lastUpdated":"2026-03-09","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.20-0309-non-reasoning","displayName":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"grok-4.20-0309-reasoning":{"metadata":{"displayName":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":30000,"structuredOutput":true,"lastUpdated":"2026-03-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.20-0309-reasoning","displayName":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"grok-4.20-multi-agent-0309":{"metadata":{"displayName":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":30000,"structuredOutput":true,"lastUpdated":"2026-03-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.20-multi-agent-0309","displayName":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"grok-4.3":{"metadata":{"displayName":"Grok 4.3","description":"xAI's Grok for chat, coding, agentic tools, and lower hallucination risk","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":30000,"structuredOutput":true,"lastUpdated":"2026-04-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.3","displayName":"Grok 4.3","description":"xAI's Grok for chat, coding, agentic tools, and lower hallucination risk","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000}},"grok-4.5":{"metadata":{"displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","lifecycle":"active","contextWindow":500000,"maxOutputTokens":500000,"structuredOutput":true,"lastUpdated":"2026-07-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.5","displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":500000,"defaultContextWindow":500000}},"grok-4.6":{"metadata":{"displayName":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","lifecycle":"active","contextWindow":500000,"maxOutputTokens":500000,"knowledgeCutoff":"2026-02-01","structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.6","displayName":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":500000,"defaultContextWindow":500000,"knowledgeCutoff":"2026-02-01"}},"grok-build-0.1":{"metadata":{"displayName":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"structuredOutput":true,"lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-build-0.1","displayName":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"grok-imagine-image":{"metadata":{"displayName":"Grok Imagine Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":16000,"lastUpdated":"2026-01-28","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","pdf"],"output":["image","pdf"]}},"entry":{"id":"grok-imagine-image","displayName":"Grok Imagine Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":16000,"defaultContextWindow":16000}},"grok-imagine-image-2.0":{"metadata":{"displayName":"Grok Imagine Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":64000,"lastUpdated":"2026-08-07","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","pdf"],"output":["image","pdf"]}},"entry":{"id":"grok-imagine-image-2.0","displayName":"Grok Imagine Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":64000,"defaultContextWindow":64000}},"grok-imagine-image-quality":{"metadata":{"displayName":"Grok Imagine Image Quality","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":16000,"lastUpdated":"2026-04-03","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","pdf"],"output":["image","pdf"]}},"entry":{"id":"grok-imagine-image-quality","displayName":"Grok Imagine Image Quality","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":16000,"defaultContextWindow":16000}},"grok-imagine-video":{"metadata":{"displayName":"Grok Imagine Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":1024,"lastUpdated":"2026-01-28","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","video","pdf"],"output":["video"]}},"entry":{"id":"grok-imagine-video","displayName":"Grok Imagine Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1024,"defaultContextWindow":1024}},"grok-imagine-video-1.5":{"metadata":{"displayName":"Grok Imagine Video 1.5","description":"Video model for image-to-video generation, editing, and extension workflows","lifecycle":"active","contextWindow":1024,"lastUpdated":"2026-05-30","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","audio","pdf"],"output":["video"]}},"entry":{"id":"grok-imagine-video-1.5","displayName":"Grok Imagine Video 1.5","description":"Video model for image-to-video generation, editing, and extension workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1024,"defaultContextWindow":1024}}}},"zai":{"baseUrl":"https://api.z.ai/api/paas/v4","label":"Z.AI","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["glm-5.2","glm-4.5","glm-4.5-air","glm-4.5-flash","glm-4.5v","glm-4.6","glm-4.6v","glm-4.7","glm-4.7-flash","glm-4.7-flashx","glm-5","glm-5-turbo","glm-5.1","glm-5.3","glm-5.3-flash","glm-5v-turbo"],"models":{"glm-4.5":{"metadata":{"displayName":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","lifecycle":"active","contextWindow":131072,"maxOutputTokens":98304,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.5","displayName":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"glm-4.5-air":{"metadata":{"displayName":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":98304,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.5-air","displayName":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"glm-4.5-flash":{"metadata":{"displayName":"GLM-4.5-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":98304,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.5-flash","displayName":"GLM-4.5-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"glm-4.5v":{"metadata":{"displayName":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":64000,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","lastUpdated":"2025-08-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"glm-4.5v","displayName":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":64000,"defaultContextWindow":64000,"knowledgeCutoff":"2025-04"}},"glm-4.6":{"metadata":{"displayName":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.6","displayName":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"glm-4.6v":{"metadata":{"displayName":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":128000,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-12-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"glm-4.6v","displayName":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-04"}},"glm-4.7":{"metadata":{"displayName":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2025-12-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.7","displayName":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"glm-4.7-flash":{"metadata":{"displayName":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","lifecycle":"active","contextWindow":200000,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.7-flash","displayName":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-04"}},"glm-4.7-flashx":{"metadata":{"displayName":"GLM-4.7-FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":200000,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.7-flashx","displayName":"GLM-4.7-FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-04"}},"glm-5":{"metadata":{"displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5","displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"glm-5-turbo":{"metadata":{"displayName":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","lifecycle":"active","contextWindow":200000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-03-16","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5-turbo","displayName":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}},"glm-5.1":{"metadata":{"displayName":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","lifecycle":"active","contextWindow":200000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.1","displayName":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}},"glm-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5.3":{"metadata":{"displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.3","displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5.3-flash":{"metadata":{"displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"glm-5.3-flash","displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5v-turbo":{"metadata":{"displayName":"GLM-5V-Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","lifecycle":"active","contextWindow":200000,"maxOutputTokens":131072,"lastUpdated":"2026-04-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"glm-5v-turbo","displayName":"GLM-5V-Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}}}},"xiaomi":{"baseUrl":"https://api.xiaomimimo.com/v1","label":"Xiaomi","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["mimo-v2.5","mimo-v2.5-pro","mimo-v2.5-pro-ultraspeed"],"models":{"mimo-v2-flash":{"metadata":{"displayName":"MiMo-V2-Flash","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2024-12-01","lastUpdated":"2026-06-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2-flash","displayName":"MiMo-V2-Flash","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-12-01"}},"mimo-v2-omni":{"metadata":{"displayName":"MiMo-V2-Omni","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-06-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]}},"entry":{"id":"mimo-v2-omni","displayName":"MiMo-V2-Omni","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-12"}},"mimo-v2-pro":{"metadata":{"displayName":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","lifecycle":"deprecated","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-06-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2-pro","displayName":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2.5":{"metadata":{"displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-06-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]}},"entry":{"id":"mimo-v2.5","displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2.5-pro":{"metadata":{"displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-06-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2.5-pro","displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2.5-pro-ultraspeed":{"metadata":{"displayName":"MiMo-V2.5-Pro-UltraSpeed","description":"MiMo pro model for strong multimodal reasoning and agent execution","lifecycle":"beta","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-06-09","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2.5-pro-ultraspeed","displayName":"MiMo-V2.5-Pro-UltraSpeed","description":"MiMo pro model for strong multimodal reasoning and agent execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}}}},"xiaomi-token-plan-cn":{"baseUrl":"https://token-plan-cn.xiaomimimo.com/v1","label":"Xiaomi Token Plan (China)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["mimo-v2.5-pro","mimo-v2.5"],"models":{"mimo-v2-pro":{"metadata":{"displayName":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","lifecycle":"deprecated","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2-pro","displayName":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2-tts":{"metadata":{"displayName":"MiMo-V2-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2-tts","displayName":"MiMo-V2-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"mimo-v2.5":{"metadata":{"displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]}},"entry":{"id":"mimo-v2.5","displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2.5-pro":{"metadata":{"displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2.5-pro","displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2.5-tts":{"metadata":{"displayName":"MiMo-V2.5-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2.5-tts","displayName":"MiMo-V2.5-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"mimo-v2.5-tts-voiceclone":{"metadata":{"displayName":"MiMo-V2.5-TTS-VoiceClone","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2.5-tts-voiceclone","displayName":"MiMo-V2.5-TTS-VoiceClone","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"mimo-v2.5-tts-voicedesign":{"metadata":{"displayName":"MiMo-V2.5-TTS-VoiceDesign","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2.5-tts-voicedesign","displayName":"MiMo-V2.5-TTS-VoiceDesign","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}}}},"xiaomi-token-plan-sgp":{"baseUrl":"https://token-plan-sgp.xiaomimimo.com/v1","label":"Xiaomi Token Plan (Singapore)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["mimo-v2.5-pro","mimo-v2.5"],"models":{"mimo-v2-pro":{"metadata":{"displayName":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","lifecycle":"deprecated","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2-pro","displayName":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2-tts":{"metadata":{"displayName":"MiMo-V2-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2-tts","displayName":"MiMo-V2-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"mimo-v2.5":{"metadata":{"displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]}},"entry":{"id":"mimo-v2.5","displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2.5-pro":{"metadata":{"displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2.5-pro","displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2.5-tts":{"metadata":{"displayName":"MiMo-V2.5-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2.5-tts","displayName":"MiMo-V2.5-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"mimo-v2.5-tts-voiceclone":{"metadata":{"displayName":"MiMo-V2.5-TTS-VoiceClone","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2.5-tts-voiceclone","displayName":"MiMo-V2.5-TTS-VoiceClone","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"mimo-v2.5-tts-voicedesign":{"metadata":{"displayName":"MiMo-V2.5-TTS-VoiceDesign","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2.5-tts-voicedesign","displayName":"MiMo-V2.5-TTS-VoiceDesign","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}}}},"xiaomi-token-plan-ams":{"baseUrl":"https://token-plan-ams.xiaomimimo.com/v1","label":"Xiaomi Token Plan (Europe)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["mimo-v2.5-pro","mimo-v2.5"],"models":{"mimo-v2-pro":{"metadata":{"displayName":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","lifecycle":"deprecated","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2-pro","displayName":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2-tts":{"metadata":{"displayName":"MiMo-V2-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2-tts","displayName":"MiMo-V2-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"mimo-v2.5":{"metadata":{"displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]}},"entry":{"id":"mimo-v2.5","displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2.5-pro":{"metadata":{"displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2.5-pro","displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2.5-tts":{"metadata":{"displayName":"MiMo-V2.5-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2.5-tts","displayName":"MiMo-V2.5-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"mimo-v2.5-tts-voiceclone":{"metadata":{"displayName":"MiMo-V2.5-TTS-VoiceClone","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2.5-tts-voiceclone","displayName":"MiMo-V2.5-TTS-VoiceClone","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"mimo-v2.5-tts-voicedesign":{"metadata":{"displayName":"MiMo-V2.5-TTS-VoiceDesign","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2.5-tts-voicedesign","displayName":"MiMo-V2.5-TTS-VoiceDesign","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}}}},"cerebras":{"baseUrl":"https://api.cerebras.ai/v1","label":"Cerebras","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["gpt-oss-120b","qwen-3.8-27b"],"models":{"gpt-oss-120b":{"metadata":{"displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":40960,"structuredOutput":true,"lastUpdated":"2026-06-10","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"gpt-oss-120b","displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"qwen-3.8-27b":{"metadata":{"displayName":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","lifecycle":"active","contextWindow":65536,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-09-03","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen-3.8-27b","displayName":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":65536,"defaultContextWindow":65536}}}},"mistral":{"baseUrl":"https://api.mistral.ai/v1","label":"Mistral","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol","responseShape":"array-or-data"},"fallbackModels":["mistral-large-latest","codestral-latest","magistral-medium-latest","magistral-small","ministral-3b-latest","ministral-8b-latest","mistral-large-2411","mistral-large-2512","mistral-medium-2505","mistral-medium-2508","mistral-medium-2604","mistral-medium-latest","mistral-nemo","mistral-small-2506","mistral-small-2603","mistral-small-latest","open-mistral-7b","open-mixtral-8x22b","open-mixtral-8x7b","pixtral-12b","pixtral-large-latest","voxtral-small-latest","zai-glm-5-2"],"models":{"codestral-latest":{"metadata":{"displayName":"Codestral (latest)","description":"Mistral code model for completions, refactors, and developer IDE workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":4096,"knowledgeCutoff":"2024-10","lastUpdated":"2025-01-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"codestral-latest","displayName":"Codestral (latest)","description":"Mistral code model for completions, refactors, and developer IDE workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-10"}},"devstral-2512":{"metadata":{"displayName":"Devstral 2","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-12","lastUpdated":"2025-12-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"devstral-2512","displayName":"Devstral 2","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-12"}},"devstral-latest":{"metadata":{"displayName":"Devstral 2","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-12","lastUpdated":"2025-12-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"devstral-latest","displayName":"Devstral 2","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-12"}},"devstral-medium-2507":{"metadata":{"displayName":"Devstral Medium","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-05","lastUpdated":"2025-07-10","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"devstral-medium-2507","displayName":"Devstral Medium","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-05"}},"devstral-medium-latest":{"metadata":{"displayName":"Devstral 2 (latest)","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-12","lastUpdated":"2025-12-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"devstral-medium-latest","displayName":"Devstral 2 (latest)","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-12"}},"devstral-small-2505":{"metadata":{"displayName":"Devstral Small 2505","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-05","lastUpdated":"2025-05-07","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"devstral-small-2505","displayName":"Devstral Small 2505","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-05"}},"devstral-small-2507":{"metadata":{"displayName":"Devstral Small","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-05","lastUpdated":"2025-07-10","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"devstral-small-2507","displayName":"Devstral Small","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-05"}},"labs-devstral-small-2512":{"metadata":{"displayName":"Devstral Small 2","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-12","lastUpdated":"2025-12-09","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"labs-devstral-small-2512","displayName":"Devstral Small 2","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-12"}},"magistral-medium-latest":{"metadata":{"displayName":"Magistral Medium (latest)","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2025-06","lastUpdated":"2025-03-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"magistral-medium-latest","displayName":"Magistral Medium (latest)","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-06"}},"magistral-small":{"metadata":{"displayName":"Magistral Small","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-06","lastUpdated":"2025-03-17","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"magistral-small","displayName":"Magistral Small","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-06"}},"ministral-3b-latest":{"metadata":{"displayName":"Ministral 3B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-10","lastUpdated":"2024-10-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"ministral-3b-latest","displayName":"Ministral 3B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-10"}},"ministral-8b-latest":{"metadata":{"displayName":"Ministral 8B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-10","lastUpdated":"2024-10-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"ministral-8b-latest","displayName":"Ministral 8B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-10"}},"mistral-embed":{"metadata":{"displayName":"Mistral Embed","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8000,"maxOutputTokens":3072,"lastUpdated":"2023-12-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistral-embed","displayName":"Mistral Embed","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8000,"defaultContextWindow":8000}},"mistral-large-2411":{"metadata":{"displayName":"Mistral Large 2.1","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2024-11","lastUpdated":"2024-11-18","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistral-large-2411","displayName":"Mistral Large 2.1","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-11"}},"mistral-large-2512":{"metadata":{"displayName":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2024-11","lastUpdated":"2025-12-02","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral-large-2512","displayName":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-11"}},"mistral-large-latest":{"metadata":{"displayName":"Mistral Large (latest)","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2024-11","lastUpdated":"2025-12-02","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral-large-latest","displayName":"Mistral Large (latest)","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-11"}},"mistral-medium-2505":{"metadata":{"displayName":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2025-05","lastUpdated":"2025-05-07","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral-medium-2505","displayName":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-05"}},"mistral-medium-2508":{"metadata":{"displayName":"Mistral Medium 3.1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-05","lastUpdated":"2025-08-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral-medium-2508","displayName":"Mistral Medium 3.1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-05"}},"mistral-medium-2604":{"metadata":{"displayName":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-04-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral-medium-2604","displayName":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","high"],"contextWindow":262144,"defaultContextWindow":262144}},"mistral-medium-latest":{"metadata":{"displayName":"Mistral Medium (latest)","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-04-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral-medium-latest","displayName":"Mistral Medium (latest)","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","high"],"contextWindow":262144,"defaultContextWindow":262144}},"mistral-nemo":{"metadata":{"displayName":"Mistral Nemo","description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-07","lastUpdated":"2024-07-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistral-nemo","displayName":"Mistral Nemo","description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-07"}},"mistral-small-2506":{"metadata":{"displayName":"Mistral Small 3.2","description":"Efficient Mistral model for fast chat, extraction, and production assistants","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2025-03","lastUpdated":"2025-06-20","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral-small-2506","displayName":"Mistral Small 3.2","description":"Efficient Mistral model for fast chat, extraction, and production assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-03"}},"mistral-small-2603":{"metadata":{"displayName":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-06","lastUpdated":"2026-03-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral-small-2603","displayName":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","high"],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-06"}},"mistral-small-latest":{"metadata":{"displayName":"Mistral Small (latest)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-06","lastUpdated":"2026-03-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral-small-latest","displayName":"Mistral Small (latest)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","high"],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-06"}},"open-mistral-7b":{"metadata":{"displayName":"Mistral 7B","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":8000,"maxOutputTokens":8000,"knowledgeCutoff":"2023-12","lastUpdated":"2023-09-27","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"open-mistral-7b","displayName":"Mistral 7B","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8000,"defaultContextWindow":8000,"knowledgeCutoff":"2023-12"}},"open-mistral-nemo":{"metadata":{"displayName":"Open Mistral Nemo","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-07","lastUpdated":"2024-07-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"open-mistral-nemo","displayName":"Open Mistral Nemo","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-07"}},"open-mixtral-8x22b":{"metadata":{"displayName":"Mixtral 8x22B","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":64000,"maxOutputTokens":64000,"knowledgeCutoff":"2024-04","lastUpdated":"2024-04-17","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"open-mixtral-8x22b","displayName":"Mixtral 8x22B","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":64000,"defaultContextWindow":64000,"knowledgeCutoff":"2024-04"}},"open-mixtral-8x7b":{"metadata":{"displayName":"Mixtral 8x7B","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":32000,"maxOutputTokens":32000,"knowledgeCutoff":"2024-01","lastUpdated":"2023-12-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"open-mixtral-8x7b","displayName":"Mixtral 8x7B","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000,"knowledgeCutoff":"2024-01"}},"pixtral-12b":{"metadata":{"displayName":"Pixtral 12B","description":"Mistral vision-language model for image understanding and multimodal chat","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09","lastUpdated":"2024-09-01","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"pixtral-12b","displayName":"Pixtral 12B","description":"Mistral vision-language model for image understanding and multimodal chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-09"}},"pixtral-large-latest":{"metadata":{"displayName":"Pixtral Large (latest)","description":"Mistral's larger vision model for document-heavy image understanding and chat","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-11","lastUpdated":"2024-11-04","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"pixtral-large-latest","displayName":"Pixtral Large (latest)","description":"Mistral's larger vision model for document-heavy image understanding and chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-11"}},"voxtral-mini-latest":{"metadata":{"displayName":"Voxtral Mini (latest)","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2026-02-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"voxtral-mini-latest","displayName":"Voxtral Mini (latest)","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"voxtral-mini-tts-latest":{"metadata":{"displayName":"Voxtral Mini TTS (latest)","description":"Multilingual text-to-speech model with zero-shot voice cloning","lifecycle":"active","lastUpdated":"2026-03-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"voxtral-mini-tts-latest","displayName":"Voxtral Mini TTS (latest)","description":"Multilingual text-to-speech model with zero-shot voice cloning","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"voxtral-small-latest":{"metadata":{"displayName":"Voxtral Small (latest)","description":"Instruct model with native audio input for speech understanding and tool use","lifecycle":"active","contextWindow":32000,"maxOutputTokens":32000,"lastUpdated":"2025-07-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","audio"],"output":["text"]}},"entry":{"id":"voxtral-small-latest","displayName":"Voxtral Small (latest)","description":"Instruct model with native audio input for speech understanding and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"zai-glm-5-2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"beta","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-glm-5-2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}}}},"cohere":{"baseUrl":"https://api.cohere.com/v2","label":"Cohere","authKind":"api_key","runtimeAdapter":{"kind":"cohere"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"cohere"},"fallbackModels":["command-a-plus-05-2026","command-a-03-2025","command-a-reasoning-08-2025","command-a-translate-08-2025","command-r-08-2024","command-r-plus-08-2024","command-r7b-12-2024","command-r7b-arabic-02-2025","north-mini-code-1-0"],"models":{"c4ai-aya-expanse-32b":{"metadata":{"displayName":"Aya Expanse 32B","description":"Open multilingual model optimized for generation across 23 languages","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4000,"lastUpdated":"2024-10-24","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"c4ai-aya-expanse-32b","displayName":"Aya Expanse 32B","description":"Open multilingual model optimized for generation across 23 languages","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"c4ai-aya-expanse-8b":{"metadata":{"displayName":"Aya Expanse 8B","description":"Compact open multilingual model optimized for generation across 23 languages","lifecycle":"active","contextWindow":8000,"maxOutputTokens":4000,"lastUpdated":"2024-10-24","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"c4ai-aya-expanse-8b","displayName":"Aya Expanse 8B","description":"Compact open multilingual model optimized for generation across 23 languages","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8000,"defaultContextWindow":8000}},"c4ai-aya-vision-32b":{"metadata":{"displayName":"Aya Vision 32B","description":"Open multilingual vision model for OCR, visual reasoning, and image question answering","lifecycle":"active","contextWindow":16000,"maxOutputTokens":4000,"lastUpdated":"2025-05-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"c4ai-aya-vision-32b","displayName":"Aya Vision 32B","description":"Open multilingual vision model for OCR, visual reasoning, and image question answering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":16000,"defaultContextWindow":16000}},"c4ai-aya-vision-8b":{"metadata":{"displayName":"Aya Vision 8B","description":"Compact open multilingual vision model for OCR and visual question answering","lifecycle":"active","contextWindow":16000,"maxOutputTokens":4000,"lastUpdated":"2025-05-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"c4ai-aya-vision-8b","displayName":"Aya Vision 8B","description":"Compact open multilingual vision model for OCR and visual question answering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":16000,"defaultContextWindow":16000}},"command-a-03-2025":{"metadata":{"displayName":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","lifecycle":"active","contextWindow":256000,"maxOutputTokens":8000,"knowledgeCutoff":"2024-06-01","lastUpdated":"2025-03-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"command-a-03-2025","displayName":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-06-01"}},"command-a-plus-05-2026":{"metadata":{"displayName":"Command A Plus","description":"Cohere's stronger command model for multilingual agents and enterprise workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-04-01","structuredOutput":true,"lastUpdated":"2026-06-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true,"offBehavior":"cohere-thinking-disabled"},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"command-a-plus-05-2026","displayName":"Command A Plus","description":"Cohere's stronger command model for multilingual agents and enterprise workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-04-01"}},"command-a-reasoning-08-2025":{"metadata":{"displayName":"Command A Reasoning","description":"Cohere reasoning model for multilingual enterprise agents, tools, and complex workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"knowledgeCutoff":"2024-06-01","lastUpdated":"2025-08-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true,"offBehavior":"cohere-thinking-disabled"},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"command-a-reasoning-08-2025","displayName":"Command A Reasoning","description":"Cohere reasoning model for multilingual enterprise agents, tools, and complex workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off"],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-06-01"}},"command-a-translate-08-2025":{"metadata":{"displayName":"Command A Translate","description":"Translation model for multilingual conversion, localization, and cross-language workflows","lifecycle":"active","contextWindow":8000,"maxOutputTokens":8000,"knowledgeCutoff":"2024-06-01","lastUpdated":"2025-08-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"command-a-translate-08-2025","displayName":"Command A Translate","description":"Translation model for multilingual conversion, localization, and cross-language workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8000,"defaultContextWindow":8000,"knowledgeCutoff":"2024-06-01"}},"command-a-vision-07-2025":{"metadata":{"displayName":"Command A Vision","description":"Cohere vision model for multilingual document analysis, OCR, and image understanding","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8000,"knowledgeCutoff":"2024-06-01","lastUpdated":"2025-07-31","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"command-a-vision-07-2025","displayName":"Command A Vision","description":"Cohere vision model for multilingual document analysis, OCR, and image understanding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-06-01"}},"command-r-08-2024":{"metadata":{"displayName":"Command R","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4000,"knowledgeCutoff":"2024-06-01","lastUpdated":"2024-08-30","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"command-r-08-2024","displayName":"Command R","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-06-01"}},"command-r-plus-08-2024":{"metadata":{"displayName":"Command R+","description":"Cohere's RAG workhorse for long-context enterprise search and tool use","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4000,"knowledgeCutoff":"2024-06-01","lastUpdated":"2024-08-30","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"command-r-plus-08-2024","displayName":"Command R+","description":"Cohere's RAG workhorse for long-context enterprise search and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-06-01"}},"command-r7b-12-2024":{"metadata":{"displayName":"Command R7B","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4000,"knowledgeCutoff":"2024-06-01","lastUpdated":"2024-12-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"command-r7b-12-2024","displayName":"Command R7B","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-06-01"}},"command-r7b-arabic-02-2025":{"metadata":{"displayName":"Command R7B Arabic","description":"Open Command R model optimized for Arabic enterprise chat, RAG, and cultural knowledge","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4000,"knowledgeCutoff":"2024-06-01","lastUpdated":"2025-02-27","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"command-r7b-arabic-02-2025","displayName":"Command R7B Arabic","description":"Open Command R model optimized for Arabic enterprise chat, RAG, and cultural knowledge","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-06-01"}},"north-mini-code-1-0":{"metadata":{"displayName":"North Mini Code","description":"Cohere coding model for practical software engineering and agentic edits","lifecycle":"active","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-09-23","structuredOutput":true,"lastUpdated":"2026-06-09","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai-compatible","name":"provider"},"baseUrl":"https://api.cohere.ai/compatibility/v1"},"entry":{"id":"north-mini-code-1-0","displayName":"North Mini Code","description":"Cohere coding model for practical software engineering and agentic edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high"],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-09-23"}}}},"huggingface":{"baseUrl":"https://router.huggingface.co/v1","label":"Hugging Face","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol","filter":"tool-capable"},"fallbackModels":["openai/gpt-oss-120b","meta-llama/Llama-3.3-70B-Instruct","deepseek-ai/DeepSeek-R1","deepseek-ai/DeepSeek-R1-0528","deepseek-ai/DeepSeek-V3","deepseek-ai/DeepSeek-V3-0324","deepseek-ai/DeepSeek-V3.1","deepseek-ai/DeepSeek-V3.2","deepseek-ai/DeepSeek-V4-Flash","deepseek-ai/DeepSeek-V4-Flash-0731","deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","deepseek-ai/DeepSeek-V4-Pro","deepseek-ai/DeepSeek-V4-Pro-0813","deepseek-ai/DeepSeek-V4.1-Flash","google/gemma-3-12b-it","google/gemma-3-27b-it","google/gemma-3-4b-it","google/gemma-4-26B-A4B-it","google/gemma-4-31B-it","meta-llama/Llama-3.1-8B-Instruct","MiniMaxAI/MiniMax-M2","MiniMaxAI/MiniMax-M2.1","MiniMaxAI/MiniMax-M2.5","MiniMaxAI/MiniMax-M2.7","MiniMaxAI/MiniMax-M3","moonshotai/Kimi-K2-Instruct","moonshotai/Kimi-K2-Instruct-0905","moonshotai/Kimi-K2-Thinking","moonshotai/Kimi-K2.5","moonshotai/Kimi-K2.6","moonshotai/Kimi-K2.7-Code","moonshotai/Kimi-K3","openai/gpt-oss-20b","Qwen/Qwen2.5-Coder-32B-Instruct","Qwen/Qwen3-235B-A22B","Qwen/Qwen3-235B-A22B-Instruct-2507","Qwen/Qwen3-235B-A22B-Thinking-2507","Qwen/Qwen3-30B-A3B","Qwen/Qwen3-32B","Qwen/Qwen3-Coder-30B-A3B-Instruct","Qwen/Qwen3-Coder-480B-A35B-Instruct","Qwen/Qwen3-Coder-Next","Qwen/Qwen3-Next-80B-A3B-Instruct","Qwen/Qwen3-Next-80B-A3B-Thinking","Qwen/Qwen3-VL-235B-A22B-Instruct","Qwen/Qwen3-VL-235B-A22B-Thinking","Qwen/Qwen3.5-122B-A10B","Qwen/Qwen3.5-27B","Qwen/Qwen3.5-35B-A3B","Qwen/Qwen3.5-397B-A17B","Qwen/Qwen3.5-9B","Qwen/Qwen3.6-27B","Qwen/Qwen3.6-35B-A3B","Qwen/Qwen3.8-2.4T-A95B","Qwen/Qwen3.8-27B","stepfun-ai/Step-3.5-Flash","stepfun-ai/Step-3.7-Flash","tencent/Hy3","thinkingmachines/Inkling","thinkingmachines/Inkling-Small","XiaomiMiMo/MiMo-V2-Flash","XiaomiMiMo/MiMo-V2.5","XiaomiMiMo/MiMo-V2.5-Pro","zai-org/GLM-4.5","zai-org/GLM-4.5-Air","zai-org/GLM-4.5V","zai-org/GLM-4.6","zai-org/GLM-4.6V-Flash","zai-org/GLM-4.7","zai-org/GLM-4.7-Flash","zai-org/GLM-5","zai-org/GLM-5.1","zai-org/GLM-5.2","zai-org/GLM-5.3","zai-org/GLM-5.3-Flash"],"models":{"deepseek-ai/DeepSeek-R1":{"metadata":{"displayName":"DeepSeek-R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","lifecycle":"active","contextWindow":64000,"maxOutputTokens":32768,"knowledgeCutoff":"2024-07","structuredOutput":true,"lastUpdated":"2025-05-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-R1","displayName":"DeepSeek-R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":64000,"defaultContextWindow":64000,"knowledgeCutoff":"2024-07"}},"deepseek-ai/DeepSeek-R1-0528":{"metadata":{"displayName":"DeepSeek-R1-0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","lifecycle":"active","contextWindow":163840,"maxOutputTokens":163840,"knowledgeCutoff":"2025-05","lastUpdated":"2025-05-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-R1-0528","displayName":"DeepSeek-R1-0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2025-05"}},"deepseek-ai/DeepSeek-V3":{"metadata":{"displayName":"DeepSeek-V3","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":64000,"maxOutputTokens":8192,"structuredOutput":true,"lastUpdated":"2024-12-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3","displayName":"DeepSeek-V3","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":64000,"defaultContextWindow":64000}},"deepseek-ai/DeepSeek-V3-0324":{"metadata":{"displayName":"DeepSeek V3 0324","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":163840,"structuredOutput":true,"lastUpdated":"2025-03-24","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3-0324","displayName":"DeepSeek V3 0324","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840}},"deepseek-ai/DeepSeek-V3.1":{"metadata":{"displayName":"DeepSeek-V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"structuredOutput":true,"lastUpdated":"2025-08-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3.1","displayName":"DeepSeek-V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"deepseek-ai/DeepSeek-V3.2":{"metadata":{"displayName":"DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":65536,"knowledgeCutoff":"2024-07","lastUpdated":"2025-12-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3.2","displayName":"DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2024-07"}},"deepseek-ai/DeepSeek-V4-Flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Flash","displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"deepseek-ai/DeepSeek-V4-Flash-0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp":{"metadata":{"displayName":"DeepSeek V4 Flash Vision Exp","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","displayName":"DeepSeek V4 Flash Vision Exp","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"deepseek-ai/DeepSeek-V4-Pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":393216,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Pro","displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"deepseek-ai/DeepSeek-V4-Pro-0813":{"metadata":{"displayName":"DeepSeek V4 Pro 0813","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","displayName":"DeepSeek V4 Pro 0813","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"deepseek-ai/DeepSeek-V4.1-Flash":{"metadata":{"displayName":"DeepSeek V4.1 Flash","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","high","xhigh","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4.1-Flash","displayName":"DeepSeek V4.1 Flash","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","high","xhigh","max"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"google/gemma-3-12b-it":{"metadata":{"displayName":"Gemma 3 12B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2024-08","structuredOutput":true,"lastUpdated":"2025-03-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3-12b-it","displayName":"Gemma 3 12B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-08"}},"google/gemma-3-27b-it":{"metadata":{"displayName":"Gemma 3 27B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2024-08","structuredOutput":true,"lastUpdated":"2025-03-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3-27b-it","displayName":"Gemma 3 27B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-08"}},"google/gemma-3-4b-it":{"metadata":{"displayName":"Gemma 3 4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2024-08","structuredOutput":true,"lastUpdated":"2025-03-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3-4b-it","displayName":"Gemma 3 4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-08"}},"google/gemma-4-26B-A4B-it":{"metadata":{"displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-4-26B-A4B-it","displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"google/gemma-4-31B-it":{"metadata":{"displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-4-31B-it","displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"meta-llama/Llama-3.1-8B-Instruct":{"metadata":{"displayName":"Llama-3.1-8B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":4096,"knowledgeCutoff":"2023-12","structuredOutput":true,"lastUpdated":"2024-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/Llama-3.1-8B-Instruct","displayName":"Llama-3.1-8B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12"}},"meta-llama/Llama-3.3-70B-Instruct":{"metadata":{"displayName":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","lifecycle":"active","contextWindow":131072,"maxOutputTokens":4096,"knowledgeCutoff":"2023-12","structuredOutput":true,"lastUpdated":"2024-12-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/Llama-3.3-70B-Instruct","displayName":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12"}},"MiniMaxAI/MiniMax-M2":{"metadata":{"displayName":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2025-10-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M2","displayName":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMaxAI/MiniMax-M2.1":{"metadata":{"displayName":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-10","lastUpdated":"2025-12-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M2.1","displayName":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-10"}},"MiniMaxAI/MiniMax-M2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M2.5","displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMaxAI/MiniMax-M2.7":{"metadata":{"displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M2.7","displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMaxAI/MiniMax-M3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","lifecycle":"active","contextWindow":524288,"maxOutputTokens":512000,"structuredOutput":true,"lastUpdated":"2026-06-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M3","displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":524288,"defaultContextWindow":524288}},"moonshotai/Kimi-K2-Instruct":{"metadata":{"displayName":"Kimi-K2-Instruct","description":"Kimi model for long-context chat, coding, and agentic reasoning","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2024-10","lastUpdated":"2025-07-14","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2-Instruct","displayName":"Kimi-K2-Instruct","description":"Kimi model for long-context chat, coding, and agentic reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-10"}},"moonshotai/Kimi-K2-Instruct-0905":{"metadata":{"displayName":"Kimi-K2-Instruct-0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"knowledgeCutoff":"2024-10","lastUpdated":"2025-09-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2-Instruct-0905","displayName":"Kimi-K2-Instruct-0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-10"}},"moonshotai/Kimi-K2-Thinking":{"metadata":{"displayName":"Kimi-K2-Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2024-08","lastUpdated":"2025-11-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2-Thinking","displayName":"Kimi-K2-Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-08"}},"moonshotai/Kimi-K2.5":{"metadata":{"displayName":"Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","lastUpdated":"2026-01-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2.5","displayName":"Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/Kimi-K2.6":{"metadata":{"displayName":"Kimi-K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","lastUpdated":"2026-04-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2.6","displayName":"Kimi-K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/Kimi-K2.7-Code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2.7-Code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/Kimi-K3":{"metadata":{"displayName":"Kimi K3","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K3","displayName":"Kimi K3","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"openai/gpt-oss-120b":{"metadata":{"displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-120b","displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"openai/gpt-oss-20b":{"metadata":{"displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-20b","displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"Qwen/Qwen2.5-Coder-32B-Instruct":{"metadata":{"displayName":"Qwen2.5-Coder-32B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"structuredOutput":true,"lastUpdated":"2024-11-12","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen2.5-Coder-32B-Instruct","displayName":"Qwen2.5-Coder-32B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"Qwen/Qwen3-235B-A22B":{"metadata":{"displayName":"Qwen3 235B-A22B","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","lifecycle":"active","contextWindow":40960,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-235B-A22B","displayName":"Qwen3 235B-A22B","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":40960,"defaultContextWindow":40960,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-235B-A22B-Instruct-2507":{"metadata":{"displayName":"Qwen3 235B-A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-07-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","displayName":"Qwen3 235B-A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3-235B-A22B-Thinking-2507":{"metadata":{"displayName":"Qwen3-235B-A22B-Thinking-2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","displayName":"Qwen3-235B-A22B-Thinking-2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-30B-A3B":{"metadata":{"displayName":"Qwen3 30B A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":40960,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-04-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-30B-A3B","displayName":"Qwen3 30B A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":40960,"defaultContextWindow":40960}},"Qwen/Qwen3-32B":{"metadata":{"displayName":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-32B","displayName":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-Coder-30B-A3B-Instruct":{"metadata":{"displayName":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","displayName":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-Coder-480B-A35B-Instruct":{"metadata":{"displayName":"Qwen3-Coder-480B-A35B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":66536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","displayName":"Qwen3-Coder-480B-A35B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-Coder-Next":{"metadata":{"displayName":"Qwen3-Coder-Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Coder-Next","displayName":"Qwen3-Coder-Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-Embedding-4B":{"metadata":{"displayName":"Qwen 3 Embedding 4B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":32000,"maxOutputTokens":2048,"knowledgeCutoff":"2024-12","lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Embedding-4B","displayName":"Qwen 3 Embedding 4B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000,"knowledgeCutoff":"2024-12"}},"Qwen/Qwen3-Embedding-8B":{"metadata":{"displayName":"Qwen 3 Embedding 8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":32000,"maxOutputTokens":4096,"knowledgeCutoff":"2024-12","lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Embedding-8B","displayName":"Qwen 3 Embedding 8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000,"knowledgeCutoff":"2024-12"}},"Qwen/Qwen3-Next-80B-A3B-Instruct":{"metadata":{"displayName":"Qwen3-Next-80B-A3B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":66536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Next-80B-A3B-Instruct","displayName":"Qwen3-Next-80B-A3B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-Next-80B-A3B-Thinking":{"metadata":{"displayName":"Qwen3-Next-80B-A3B-Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Next-80B-A3B-Thinking","displayName":"Qwen3-Next-80B-A3B-Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-VL-235B-A22B-Instruct":{"metadata":{"displayName":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-09-23","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-VL-235B-A22B-Instruct","displayName":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-03-31"}},"Qwen/Qwen3-VL-235B-A22B-Thinking":{"metadata":{"displayName":"Qwen3 VL 235B A22B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-09-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-VL-235B-A22B-Thinking","displayName":"Qwen3 VL 235B A22B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-03-31"}},"Qwen/Qwen3.5-122B-A10B":{"metadata":{"displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-122B-A10B","displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.5-27B":{"metadata":{"displayName":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-27B","displayName":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.5-35B-A3B":{"metadata":{"displayName":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-35B-A3B","displayName":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.5-397B-A17B":{"metadata":{"displayName":"Qwen3.5-397B-A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-397B-A17B","displayName":"Qwen3.5-397B-A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3.5-9B":{"metadata":{"displayName":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-9B","displayName":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.6-27B":{"metadata":{"displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.6-27B","displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.6-35B-A3B":{"metadata":{"displayName":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.6-35B-A3B","displayName":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.8-2.4T-A95B":{"metadata":{"displayName":"Qwen3.8 2.4T A95B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.8-2.4T-A95B","displayName":"Qwen3.8 2.4T A95B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","xhigh"],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.8-27B":{"metadata":{"displayName":"Qwen3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.8-27B","displayName":"Qwen3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":262144,"defaultContextWindow":262144}},"stepfun-ai/Step-3.5-Flash":{"metadata":{"displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","lifecycle":"active","contextWindow":262144,"maxOutputTokens":256000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"stepfun-ai/Step-3.5-Flash","displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"stepfun-ai/Step-3.7-Flash":{"metadata":{"displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","lifecycle":"active","contextWindow":262144,"maxOutputTokens":256000,"knowledgeCutoff":"2026-03-01","lastUpdated":"2026-05-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"stepfun-ai/Step-3.7-Flash","displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2026-03-01"}},"tencent/Hy3":{"metadata":{"displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":262144,"inputLimit":192000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-07-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/Hy3","displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","high"],"contextWindow":262144,"inputLimit":192000,"defaultContextWindow":262144,"defaultInputLimit":192000}},"thinkingmachines/Inkling":{"metadata":{"displayName":"Inkling","description":"Multimodal model for analyzing text, images, documents, and rich media","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"structuredOutput":true,"lastUpdated":"2026-07-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"thinkingmachines/Inkling","displayName":"Inkling","description":"Multimodal model for analyzing text, images, documents, and rich media","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576}},"thinkingmachines/Inkling-Small":{"metadata":{"displayName":"Inkling Small","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":524288,"maxOutputTokens":1048576,"lastUpdated":"2026-07-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"thinkingmachines/Inkling-Small","displayName":"Inkling Small","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":524288,"defaultContextWindow":524288}},"XiaomiMiMo/MiMo-V2-Flash":{"metadata":{"displayName":"MiMo-V2-Flash","description":"MiMo flash model for fast multimodal assistance and agent workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":4096,"knowledgeCutoff":"2024-12","lastUpdated":"2025-12-16","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"XiaomiMiMo/MiMo-V2-Flash","displayName":"MiMo-V2-Flash","description":"MiMo flash model for fast multimodal assistance and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-12"}},"XiaomiMiMo/MiMo-V2.5":{"metadata":{"displayName":"MiMo-V2.5","description":"MiMo model for long-context reasoning, perception, and agentic tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"XiaomiMiMo/MiMo-V2.5","displayName":"MiMo-V2.5","description":"MiMo model for long-context reasoning, perception, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-12"}},"XiaomiMiMo/MiMo-V2.5-Pro":{"metadata":{"displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"XiaomiMiMo/MiMo-V2.5-Pro","displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"zai-org/GLM-4.5":{"metadata":{"displayName":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","lifecycle":"active","contextWindow":131072,"maxOutputTokens":98304,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-4.5","displayName":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"zai-org/GLM-4.5-Air":{"metadata":{"displayName":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":98304,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-4.5-Air","displayName":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"zai-org/GLM-4.5V":{"metadata":{"displayName":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":65536,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","lastUpdated":"2025-08-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"zai-org/GLM-4.5V","displayName":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-04"}},"zai-org/GLM-4.6":{"metadata":{"displayName":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-4.6","displayName":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"zai-org/GLM-4.6V-Flash":{"metadata":{"displayName":"GLM-4.6V-Flash","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"lastUpdated":"2025-12-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"zai-org/GLM-4.6V-Flash","displayName":"GLM-4.6V-Flash","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"zai-org/GLM-4.7":{"metadata":{"displayName":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2025-12-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-4.7","displayName":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"zai-org/GLM-4.7-Flash":{"metadata":{"displayName":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":200000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-04","lastUpdated":"2025-08-08","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-4.7-Flash","displayName":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-04"}},"zai-org/GLM-5":{"metadata":{"displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":131072,"lastUpdated":"2026-02-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5","displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"zai-org/GLM-5.1":{"metadata":{"displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":131072,"lastUpdated":"2026-04-03","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.1","displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"zai-org/GLM-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"zai-org/GLM-5.3":{"metadata":{"displayName":"GLM-5.3","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.3","displayName":"GLM-5.3","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"zai-org/GLM-5.3-Flash":{"metadata":{"displayName":"GLM-5.3-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.3-Flash","displayName":"GLM-5.3-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}}}},"zenmux":{"baseUrl":"https://zenmux.ai/api/v1","label":"ZenMux","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider","replayAssistantReasoningAs":"reasoning","replayAssistantReasoningDetails":true},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol","auth":"none"},"fallbackModels":["moonshotai/kimi-k2.5","baidu/ernie-5.0-thinking-preview","deepseek/deepseek-v3.2","deepseek/deepseek-v3.2-exp","deepseek/deepseek-v4-flash","deepseek/deepseek-v4-pro","google/gemini-2.5-flash","google/gemini-2.5-flash-lite","google/gemini-2.5-pro","google/gemini-3-flash-preview","google/gemini-3.1-flash-lite","google/gemini-3.1-flash-lite-preview","google/gemini-3.1-pro-preview","google/gemini-3.5-flash","inclusionai/ring-2.6-1t","kuaishou/kat-coder-pro-v2","moonshotai/kimi-k2.6","moonshotai/kimi-k2.7-code","moonshotai/kimi-k2.7-code-free","moonshotai/kimi-k3","moonshotai/kimi-k3-free","openai/gpt-5.5","openai/gpt-5.5-instant","openai/gpt-5.5-pro","openai/gpt-5.6-luna","openai/gpt-5.6-sol","openai/gpt-5.6-terra","qwen/qwen3-coder-plus","qwen/qwen3-max","qwen/qwen3.5-flash","qwen/qwen3.5-plus","qwen/qwen3.6-plus","qwen/qwen3.7-max","qwen/qwen3.7-plus","sapiens-ai/agnes-1.5-lite","sapiens-ai/agnes-1.5-pro","stepfun/step-3.5-flash","stepfun/step-3.7-flash","stepfun/step-3.7-flash-free","tencent/hy3-preview","volcengine/doubao-seed-1.8","volcengine/doubao-seed-2.0-code","volcengine/doubao-seed-2.0-lite","volcengine/doubao-seed-2.0-mini","volcengine/doubao-seed-2.0-pro","x-ai/grok-4.2-fast","x-ai/grok-4.2-fast-non-reasoning","x-ai/grok-4.3","x-ai/grok-4.5","x-ai/grok-build-0.1","xiaomi/mimo-v2-flash","xiaomi/mimo-v2-omni","xiaomi/mimo-v2-pro","xiaomi/mimo-v2.5","xiaomi/mimo-v2.5-pro","z-ai/glm-4.5","z-ai/glm-4.5-air","z-ai/glm-4.6","z-ai/glm-4.6v","z-ai/glm-4.6v-flash","z-ai/glm-4.6v-flash-free","z-ai/glm-4.7","z-ai/glm-4.7-flash-free","z-ai/glm-4.7-flashx","z-ai/glm-5","z-ai/glm-5-turbo","z-ai/glm-5.1","z-ai/glm-5.2","z-ai/glm-5.2-free","z-ai/glm-5v-turbo"],"models":{"anthropic/claude-3.5-haiku":{"metadata":{"displayName":"Claude 3.5 Haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2024-11-04","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-3.5-haiku","displayName":"Claude 3.5 Haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"anthropic/claude-3.7-sonnet":{"metadata":{"displayName":"Claude 3.7 Sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-02-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-3.7-sonnet","displayName":"Claude 3.7 Sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"anthropic/claude-fable-5":{"metadata":{"displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-06-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-fable-5","displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"anthropic/claude-haiku-4.5":{"metadata":{"displayName":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-10-15","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["image","text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-haiku-4.5","displayName":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"anthropic/claude-opus-4":{"metadata":{"displayName":"Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-05-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-opus-4","displayName":"Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"anthropic/claude-opus-4.1":{"metadata":{"displayName":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-08-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-opus-4.1","displayName":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"anthropic/claude-opus-4.5":{"metadata":{"displayName":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-11-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-opus-4.5","displayName":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"anthropic/claude-opus-4.6":{"metadata":{"displayName":"Claude Opus 4.6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-05-31","lastUpdated":"2026-02-06","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["image","text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-opus-4.6","displayName":"Claude Opus 4.6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05-31"}},"anthropic/claude-opus-4.7":{"metadata":{"displayName":"Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-opus-4.7","displayName":"Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"anthropic/claude-opus-4.8":{"metadata":{"displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01","lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-opus-4.8","displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01"}},"anthropic/claude-sonnet-4":{"metadata":{"displayName":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-05-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-sonnet-4","displayName":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-01-01"}},"anthropic/claude-sonnet-4.5":{"metadata":{"displayName":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-09-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-sonnet-4.5","displayName":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-01-01"}},"anthropic/claude-sonnet-4.6":{"metadata":{"displayName":"Claude Sonnet 4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-02-18","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-sonnet-4.6","displayName":"Claude Sonnet 4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-08-31"}},"anthropic/claude-sonnet-5":{"metadata":{"displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-sonnet-5","displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"anthropic/claude-sonnet-5-free":{"metadata":{"displayName":"Claude Sonnet 5 (Free)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-sonnet-5-free","displayName":"Claude Sonnet 5 (Free)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"baidu/ernie-5.0-thinking-preview":{"metadata":{"displayName":"ERNIE 5.0","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-01-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"baidu/ernie-5.0-thinking-preview","displayName":"ERNIE 5.0","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-01-01"}},"deepseek/deepseek-chat":{"metadata":{"displayName":"DeepSeek-V3.2 (Non-thinking Mode)","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-12-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-chat","displayName":"DeepSeek-V3.2 (Non-thinking Mode)","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-01-01"}},"deepseek/deepseek-v3.2":{"metadata":{"displayName":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-12-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v3.2","displayName":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-01-01"}},"deepseek/deepseek-v3.2-exp":{"metadata":{"displayName":"DeepSeek-V3.2-Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-09-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v3.2-exp","displayName":"DeepSeek-V3.2-Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163000,"defaultContextWindow":163000,"knowledgeCutoff":"2025-01-01"}},"deepseek/deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-flash","displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek/deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-pro","displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"google/gemini-2.5-flash":{"metadata":{"displayName":"Gemini 2.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-06-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["pdf","image","text","audio"],"output":["text"]}},"entry":{"id":"google/gemini-2.5-flash","displayName":"Gemini 2.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048000,"defaultContextWindow":1048000,"knowledgeCutoff":"2025-01-01"}},"google/gemini-2.5-flash-lite":{"metadata":{"displayName":"Gemini 2.5 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","lifecycle":"active","contextWindow":1048000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-07-22","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["pdf","image","text","audio"],"output":["text"]}},"entry":{"id":"google/gemini-2.5-flash-lite","displayName":"Gemini 2.5 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048000,"defaultContextWindow":1048000,"knowledgeCutoff":"2025-01-01"}},"google/gemini-2.5-pro":{"metadata":{"displayName":"Gemini 2.5 Pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","lifecycle":"active","contextWindow":1048000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-06-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["pdf","image","text","audio","video"],"output":["text"]}},"entry":{"id":"google/gemini-2.5-pro","displayName":"Gemini 2.5 Pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048000,"defaultContextWindow":1048000,"knowledgeCutoff":"2025-01-01"}},"google/gemini-3-flash-preview":{"metadata":{"displayName":"Gemini 3 Flash Preview","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-12-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf","audio"],"output":["text"]}},"entry":{"id":"google/gemini-3-flash-preview","displayName":"Gemini 3 Flash Preview","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048000,"defaultContextWindow":1048000,"knowledgeCutoff":"2025-01-01"}},"google/gemini-3.1-flash-lite":{"metadata":{"displayName":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.1-flash-lite","displayName":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-flash-lite-preview":{"metadata":{"displayName":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":65530,"lastUpdated":"2025-03-20","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]}},"entry":{"id":"google/gemini-3.1-flash-lite-preview","displayName":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1050000,"defaultContextWindow":1050000}},"google/gemini-3.1-pro-preview":{"metadata":{"displayName":"Gemini 3.1 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","lifecycle":"active","contextWindow":1048000,"maxOutputTokens":64000,"knowledgeCutoff":"2026-02-19","lastUpdated":"2026-02-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf","audio","video"],"output":["text"]}},"entry":{"id":"google/gemini-3.1-pro-preview","displayName":"Gemini 3.1 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048000,"defaultContextWindow":1048000,"knowledgeCutoff":"2026-02-19"}},"google/gemini-3.5-flash":{"metadata":{"displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.5-flash","displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"inclusionai/ling-1t":{"metadata":{"displayName":"Ling-1T","description":"Tool-capable chat model for instruction following and agentic application workflows","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-10-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ling-1t","displayName":"Ling-1T","description":"Tool-capable chat model for instruction following and agentic application workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-01-01"}},"inclusionai/ring-1t":{"metadata":{"displayName":"Ring-1T","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-10-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ring-1t","displayName":"Ring-1T","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-01-01"}},"inclusionai/ring-2.6-1t":{"metadata":{"displayName":"inclusionAI: Ring-2.6-1T","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":262000,"maxOutputTokens":65000,"knowledgeCutoff":"2025-12-31","lastUpdated":"2026-05-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ring-2.6-1t","displayName":"inclusionAI: Ring-2.6-1T","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000,"knowledgeCutoff":"2025-12-31"}},"kuaishou/kat-coder-pro-v2":{"metadata":{"displayName":"KAT-Coder-Pro-V2","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":80000,"lastUpdated":"2026-03-30","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"kuaishou/kat-coder-pro-v2","displayName":"KAT-Coder-Pro-V2","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"minimax/minimax-m2":{"metadata":{"displayName":"MiniMax M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-10-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"minimax/minimax-m2","displayName":"MiniMax M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204000,"defaultContextWindow":204000,"knowledgeCutoff":"2025-01-01"}},"minimax/minimax-m2.1":{"metadata":{"displayName":"MiniMax M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-12-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"minimax/minimax-m2.1","displayName":"MiniMax M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204000,"defaultContextWindow":204000,"knowledgeCutoff":"2025-01-01"}},"minimax/minimax-m2.5":{"metadata":{"displayName":"MiniMax M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"minimax/minimax-m2.5","displayName":"MiniMax M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01-01"}},"minimax/minimax-m2.5-lightning":{"metadata":{"displayName":"MiniMax M2.5 highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"minimax/minimax-m2.5-lightning","displayName":"MiniMax M2.5 highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01-01"}},"minimax/minimax-m2.7":{"metadata":{"displayName":"MiniMax M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131070,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-03-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"minimax/minimax-m2.7","displayName":"MiniMax M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01-01"}},"minimax/minimax-m2.7-highspeed":{"metadata":{"displayName":"MiniMax M2.7 highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131070,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-03-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"minimax/minimax-m2.7-highspeed","displayName":"MiniMax M2.7 highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01-01"}},"minimax/minimax-m3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":512000,"lastUpdated":"2026-06-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"minimax/minimax-m3","displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}},"moonshotai/kimi-k2-0905":{"metadata":{"displayName":"Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","lifecycle":"deprecated","contextWindow":262000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-09-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2-0905","displayName":"Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000,"knowledgeCutoff":"2025-01-01"}},"moonshotai/kimi-k2-thinking":{"metadata":{"displayName":"Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","lifecycle":"deprecated","contextWindow":262000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-11-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2-thinking","displayName":"Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000,"knowledgeCutoff":"2025-01-01"}},"moonshotai/kimi-k2-thinking-turbo":{"metadata":{"displayName":"Kimi K2 Thinking Turbo","description":"Kimi reasoning model for long-horizon research, planning, and tool use","lifecycle":"deprecated","contextWindow":262000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-11-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2-thinking-turbo","displayName":"Kimi K2 Thinking Turbo","description":"Kimi reasoning model for long-horizon research, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000,"knowledgeCutoff":"2025-01-01"}},"moonshotai/kimi-k2.5":{"metadata":{"displayName":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.5","displayName":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000,"knowledgeCutoff":"2025-01-01"}},"moonshotai/kimi-k2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262140,"maxOutputTokens":262140,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-04-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.6","displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262140,"defaultContextWindow":262140,"knowledgeCutoff":"2025-01-01"}},"moonshotai/kimi-k2.7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.7-code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/kimi-k2.7-code-free":{"metadata":{"displayName":"Kimi K2.7 Code (Free)","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.7-code-free","displayName":"Kimi K2.7 Code (Free)","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/kimi-k3":{"metadata":{"displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["max"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k3","displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"moonshotai/kimi-k3-free":{"metadata":{"displayName":"Kimi K3 (Free)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["max"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k3-free","displayName":"Kimi K3 (Free)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"openai/gpt-5":{"metadata":{"displayName":"GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":400000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5","displayName":"GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-01-01"}},"openai/gpt-5-codex":{"metadata":{"displayName":"GPT-5 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-09-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5-codex","displayName":"GPT-5 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-01-01"}},"openai/gpt-5.1":{"metadata":{"displayName":"GPT-5.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":400000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.1","displayName":"GPT-5.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-01-01"}},"openai/gpt-5.1-chat":{"metadata":{"displayName":"GPT-5.1 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.1-chat","displayName":"GPT-5.1 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-01-01"}},"openai/gpt-5.1-codex":{"metadata":{"displayName":"GPT-5.1-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.1-codex","displayName":"GPT-5.1-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-01-01"}},"openai/gpt-5.1-codex-mini":{"metadata":{"displayName":"GPT-5.1-Codex-Mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["image","text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.1-codex-mini","displayName":"GPT-5.1-Codex-Mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-01-01"}},"openai/gpt-5.2":{"metadata":{"displayName":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":400000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.2","displayName":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-01-01"}},"openai/gpt-5.2-codex":{"metadata":{"displayName":"GPT-5.2-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-01-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.2-codex","displayName":"GPT-5.2-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-01-01"}},"openai/gpt-5.2-pro":{"metadata":{"displayName":"GPT-5.2-Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.2-pro","displayName":"GPT-5.2-Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.3-chat":{"metadata":{"displayName":"GPT-5.3 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16380,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-03-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.3-chat","displayName":"GPT-5.3 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.3-codex":{"metadata":{"displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-03-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.3-codex","displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4":{"metadata":{"displayName":"GPT-5.4","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-03-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.4","displayName":"GPT-5.4","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4-mini":{"metadata":{"displayName":"GPT-5.4 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-03-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.4-mini","displayName":"GPT-5.4 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4-nano":{"metadata":{"displayName":"GPT-5.4 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-03-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.4-nano","displayName":"GPT-5.4 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4-pro":{"metadata":{"displayName":"GPT-5.4 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-03-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.4-pro","displayName":"GPT-5.4 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.5":{"metadata":{"displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.5","displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-12-01"}},"openai/gpt-5.5-instant":{"metadata":{"displayName":"GPT-5.5 Instant","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":400000,"inputLimit":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.5-instant","displayName":"GPT-5.5 Instant","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"inputLimit":400000,"defaultContextWindow":400000,"defaultInputLimit":400000,"knowledgeCutoff":"2025-12-01"}},"openai/gpt-5.5-pro":{"metadata":{"displayName":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.5-pro","displayName":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-12-01"}},"openai/gpt-5.6-luna":{"metadata":{"displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-luna","displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-sol":{"metadata":{"displayName":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-sol","displayName":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-terra":{"metadata":{"displayName":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-terra","displayName":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"qwen/qwen3-coder-plus":{"metadata":{"displayName":"Qwen3-Coder-Plus","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-coder-plus","displayName":"Qwen3-Coder-Plus","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-01-01"}},"qwen/qwen3-max":{"metadata":{"displayName":"Qwen3-Max-Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-01-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-max","displayName":"Qwen3-Max-Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-01-01"}},"qwen/qwen3.5-flash":{"metadata":{"displayName":"Qwen3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1020000,"maxOutputTokens":1020000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-03-20","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-flash","displayName":"Qwen3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1020000,"defaultContextWindow":1020000,"knowledgeCutoff":"2025-01-01"}},"qwen/qwen3.5-plus":{"metadata":{"displayName":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-03-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-plus","displayName":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-01-01"}},"qwen/qwen3.6-plus":{"metadata":{"displayName":"Qwen3.6-Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"lastUpdated":"2026-03-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3.6-plus","displayName":"Qwen3.6-Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen/qwen3.7-max":{"metadata":{"displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3.7-max","displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen/qwen3.7-plus":{"metadata":{"displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-04","lastUpdated":"2026-06-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.7-plus","displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"sapiens-ai/agnes-1.5-lite":{"metadata":{"displayName":"Agnes 1.5 Lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"lastUpdated":"2026-03-26","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"sapiens-ai/agnes-1.5-lite","displayName":"Agnes 1.5 Lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"sapiens-ai/agnes-1.5-pro":{"metadata":{"displayName":"Agnes 1.5 Pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"lastUpdated":"2026-03-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"sapiens-ai/agnes-1.5-pro","displayName":"Agnes 1.5 Pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"stepfun/step-3":{"metadata":{"displayName":"Step-3","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"deprecated","contextWindow":65536,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-07-31","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["image","text"],"output":["text"]}},"entry":{"id":"stepfun/step-3","displayName":"Step-3","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-01-01"}},"stepfun/step-3.5-flash":{"metadata":{"displayName":"Step 3.5 Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-02-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"stepfun/step-3.5-flash","displayName":"Step 3.5 Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-01-01"}},"stepfun/step-3.7-flash":{"metadata":{"displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2026-03-01","lastUpdated":"2026-05-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"stepfun/step-3.7-flash","displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2026-03-01"}},"stepfun/step-3.7-flash-free":{"metadata":{"displayName":"Step 3.7 Flash (Free)","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2026-03-01","lastUpdated":"2026-05-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"stepfun/step-3.7-flash-free","displayName":"Step 3.7 Flash (Free)","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2026-03-01"}},"tencent/hy3-preview":{"metadata":{"displayName":"Hy3 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":64000,"lastUpdated":"2026-04-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy3-preview","displayName":"Hy3 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","high"],"contextWindow":256000,"defaultContextWindow":256000}},"volcengine/doubao-seed-1.8":{"metadata":{"displayName":"Doubao-Seed-1.8","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-12-18","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"volcengine/doubao-seed-1.8","displayName":"Doubao-Seed-1.8","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-01-01"}},"volcengine/doubao-seed-2.0-code":{"metadata":{"displayName":"Doubao Seed 2.0 Code","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-03-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"volcengine/doubao-seed-2.0-code","displayName":"Doubao Seed 2.0 Code","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-01-01"}},"volcengine/doubao-seed-2.0-lite":{"metadata":{"displayName":"Doubao-Seed-2.0-lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2026-02-14","lastUpdated":"2026-02-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"volcengine/doubao-seed-2.0-lite","displayName":"Doubao-Seed-2.0-lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2026-02-14"}},"volcengine/doubao-seed-2.0-mini":{"metadata":{"displayName":"Doubao-Seed-2.0-mini","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2026-02-14","lastUpdated":"2026-02-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"volcengine/doubao-seed-2.0-mini","displayName":"Doubao-Seed-2.0-mini","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2026-02-14"}},"volcengine/doubao-seed-2.0-pro":{"metadata":{"displayName":"Doubao-Seed-2.0-pro","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2026-02-14","lastUpdated":"2026-02-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"volcengine/doubao-seed-2.0-pro","displayName":"Doubao-Seed-2.0-pro","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2026-02-14"}},"volcengine/doubao-seed-code":{"metadata":{"displayName":"Doubao-Seed-Code","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"deprecated","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-11-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"volcengine/doubao-seed-code","displayName":"Doubao-Seed-Code","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-01-01"}},"x-ai/grok-4":{"metadata":{"displayName":"Grok 4","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"deprecated","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["image","text"],"output":["text"]}},"entry":{"id":"x-ai/grok-4","displayName":"Grok 4","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-01-01"}},"x-ai/grok-4-fast":{"metadata":{"displayName":"Grok 4 Fast","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","lifecycle":"deprecated","contextWindow":2000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-09-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"x-ai/grok-4-fast","displayName":"Grok 4 Fast","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000,"knowledgeCutoff":"2025-01-01"}},"x-ai/grok-4.1-fast":{"metadata":{"displayName":"Grok 4.1 Fast","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","lifecycle":"deprecated","contextWindow":2000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-11-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"x-ai/grok-4.1-fast","displayName":"Grok 4.1 Fast","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000,"knowledgeCutoff":"2025-01-01"}},"x-ai/grok-4.1-fast-non-reasoning":{"metadata":{"displayName":"Grok 4.1 Fast Non Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","lifecycle":"deprecated","contextWindow":2000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-11-20","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"x-ai/grok-4.1-fast-non-reasoning","displayName":"Grok 4.1 Fast Non Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000,"knowledgeCutoff":"2025-01-01"}},"x-ai/grok-4.2-fast":{"metadata":{"displayName":"Grok 4.2 Fast","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":30000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-03-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"x-ai/grok-4.2-fast","displayName":"Grok 4.2 Fast","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000,"knowledgeCutoff":"2025-08-31"}},"x-ai/grok-4.2-fast-non-reasoning":{"metadata":{"displayName":"Grok 4.2 Fast Non Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":30000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-03-20","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"x-ai/grok-4.2-fast-non-reasoning","displayName":"Grok 4.2 Fast Non Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000,"knowledgeCutoff":"2025-08-31"}},"x-ai/grok-4.3":{"metadata":{"displayName":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":1000000,"structuredOutput":true,"lastUpdated":"2026-04-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"x-ai/grok-4.3","displayName":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000}},"x-ai/grok-4.5":{"metadata":{"displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","lifecycle":"active","contextWindow":500000,"maxOutputTokens":500000,"structuredOutput":true,"lastUpdated":"2026-07-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"x-ai/grok-4.5","displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":500000,"defaultContextWindow":500000}},"x-ai/grok-build-0.1":{"metadata":{"displayName":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"structuredOutput":true,"lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"x-ai/grok-build-0.1","displayName":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"x-ai/grok-code-fast-1":{"metadata":{"displayName":"Grok Code Fast 1","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","lifecycle":"deprecated","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-08-26","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"x-ai/grok-code-fast-1","displayName":"Grok Code Fast 1","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-01-01"}},"xiaomi/mimo-v2-flash":{"metadata":{"displayName":"MiMo-V2-Flash","description":"MiMo flash model for fast multimodal assistance and agent workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2024-12-01","lastUpdated":"2026-02-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"xiaomi/mimo-v2-flash","displayName":"MiMo-V2-Flash","description":"MiMo flash model for fast multimodal assistance and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-12-01"}},"xiaomi/mimo-v2-omni":{"metadata":{"displayName":"MiMo V2 Omni","description":"MiMo omni model for text, image, video, audio, and agents","lifecycle":"active","contextWindow":265000,"maxOutputTokens":265000,"knowledgeCutoff":"2024-12","lastUpdated":"2026-03-18","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]}},"entry":{"id":"xiaomi/mimo-v2-omni","displayName":"MiMo V2 Omni","description":"MiMo omni model for text, image, video, audio, and agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":265000,"defaultContextWindow":265000,"knowledgeCutoff":"2024-12"}},"xiaomi/mimo-v2-pro":{"metadata":{"displayName":"MiMo V2 Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":256000,"knowledgeCutoff":"2024-12","lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"xiaomi/mimo-v2-pro","displayName":"MiMo V2 Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-12"}},"xiaomi/mimo-v2.5":{"metadata":{"displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]}},"entry":{"id":"xiaomi/mimo-v2.5","displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"xiaomi/mimo-v2.5-pro":{"metadata":{"displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"xiaomi/mimo-v2.5-pro","displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"z-ai/glm-4.5":{"metadata":{"displayName":"GLM 4.5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-07-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.5","displayName":"GLM 4.5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-01-01"}},"z-ai/glm-4.5-air":{"metadata":{"displayName":"GLM 4.5 Air","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-07-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.5-air","displayName":"GLM 4.5 Air","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-01-01"}},"z-ai/glm-4.6":{"metadata":{"displayName":"GLM 4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-09-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.6","displayName":"GLM 4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"z-ai/glm-4.6v":{"metadata":{"displayName":"GLM 4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-12-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.6v","displayName":"GLM 4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"z-ai/glm-4.6v-flash":{"metadata":{"displayName":"GLM 4.6V FlashX","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-12-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.6v-flash","displayName":"GLM 4.6V FlashX","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"z-ai/glm-4.6v-flash-free":{"metadata":{"displayName":"GLM 4.6V Flash (Free)","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-12-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.6v-flash-free","displayName":"GLM 4.6V Flash (Free)","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"z-ai/glm-4.7":{"metadata":{"displayName":"GLM 4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-12-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.7","displayName":"GLM 4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"z-ai/glm-4.7-flash-free":{"metadata":{"displayName":"GLM 4.7 Flash (Free)","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.7-flash-free","displayName":"GLM 4.7 Flash (Free)","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"z-ai/glm-4.7-flashx":{"metadata":{"displayName":"GLM 4.7 FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.7-flashx","displayName":"GLM 4.7 FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"z-ai/glm-5":{"metadata":{"displayName":"GLM 5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":200000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-5","displayName":"GLM 5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"z-ai/glm-5-turbo":{"metadata":{"displayName":"GLM 5 Turbo","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":200000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-03-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-5-turbo","displayName":"GLM 5 Turbo","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"z-ai/glm-5.1":{"metadata":{"displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":200000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-04-03","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-5.1","displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}},"z-ai/glm-5.2":{"metadata":{"displayName":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-5.2","displayName":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"z-ai/glm-5.2-free":{"metadata":{"displayName":"GLM 5.2 (Free)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-5.2-free","displayName":"GLM 5.2 (Free)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"z-ai/glm-5v-turbo":{"metadata":{"displayName":"GLM 5V Turbo","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":128000,"lastUpdated":"2026-04-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"z-ai/glm-5v-turbo","displayName":"GLM 5V Turbo","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}}}},"opencode":{"baseUrl":"https://opencode.ai/zen/v1","label":"OpenCode Zen","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{"anthropic-messages":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"openai-responses":{"kind":"openai","apiProtocol":"openai-responses","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["gpt-5.5","big-pickle","claude-fable-5","claude-fable-5-1","claude-haiku-4-5","claude-opus-4-5","claude-opus-4-6","claude-opus-4-7","claude-opus-4-8","claude-opus-5","claude-sonnet-4","claude-sonnet-4-5","claude-sonnet-4-6","claude-sonnet-5","deepseek-v4-flash","deepseek-v4-flash-vision-exp","deepseek-v4-pro","gemini-3-flash","gemini-3.1-pro","gemini-3.5-flash","gemini-3.5-flash-lite","gemini-3.6-flash","gemini-3.7-flash","gemini-3.8-flash","glm-5","glm-5.1","glm-5.2","glm-5.3","glm-5.3-flash","gpt-5","gpt-5-codex","gpt-5-nano","gpt-5.1","gpt-5.1-codex","gpt-5.1-codex-max","gpt-5.1-codex-mini","gpt-5.2","gpt-5.2-codex","gpt-5.3-codex","gpt-5.3-codex-spark","gpt-5.4","gpt-5.4-mini","gpt-5.4-nano","gpt-5.4-pro","gpt-5.5-pro","gpt-5.6-luna","gpt-5.6-sol","gpt-5.6-terra","gpt-6-astra","grok-4.5","grok-4.6","grok-build-0.1","kimi-k2.5","kimi-k2.6","kimi-k2.7-code","kimi-k3","ling-3.0-flash-fin-free","mimo-v2.5-free","minimax-m2.5","minimax-m2.7","minimax-m3","muse-spark-1.2","muse-spark-1.2-contributor-free","muse-spark-1.3","muse-spark-1.3-contributor-free","nemotron-3-ultra-free","nemotron-3.5-lightning-free","qwen3.5-plus","qwen3.6-plus"],"models":{"big-pickle":{"metadata":{"displayName":"Big Pickle","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":200000,"inputLimit":160000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-10-17","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"big-pickle","displayName":"Big Pickle","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"inputLimit":160000,"defaultContextWindow":200000,"defaultInputLimit":160000,"knowledgeCutoff":"2025-01"}},"claude-3-5-haiku":{"metadata":{"displayName":"Claude Haiku 3.5","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":8192,"knowledgeCutoff":"2024-07-31","lastUpdated":"2024-10-22","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-3-5-haiku","displayName":"Claude Haiku 3.5","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-07-31"}},"claude-fable-5":{"metadata":{"displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-06-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-fable-5","displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"claude-fable-5-1":{"metadata":{"displayName":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-06","lastUpdated":"2026-09-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-fable-5-1","displayName":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-06"}},"claude-haiku-4-5":{"metadata":{"displayName":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-02-28","lastUpdated":"2025-10-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-haiku-4-5","displayName":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-02-28"}},"claude-opus-4-1":{"metadata":{"displayName":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-03-31","lastUpdated":"2025-08-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-opus-4-1","displayName":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-03-31"}},"claude-opus-4-5":{"metadata":{"displayName":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-03-31","lastUpdated":"2025-11-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-opus-4-5","displayName":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-03-31"}},"claude-opus-4-6":{"metadata":{"displayName":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-05-31","lastUpdated":"2026-03-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-opus-4-6","displayName":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05-31"}},"claude-opus-4-7":{"metadata":{"displayName":"Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-opus-4-7","displayName":"Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"claude-opus-4-8":{"metadata":{"displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01","lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-opus-4-8","displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01"}},"claude-opus-5":{"metadata":{"displayName":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-05","lastUpdated":"2026-07-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-opus-5","displayName":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-05"}},"claude-sonnet-4":{"metadata":{"displayName":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-03-31","lastUpdated":"2025-05-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-sonnet-4","displayName":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-03-31"}},"claude-sonnet-4-5":{"metadata":{"displayName":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-07-31","lastUpdated":"2025-09-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-sonnet-4-5","displayName":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-07-31"}},"claude-sonnet-4-6":{"metadata":{"displayName":"Claude Sonnet 4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-02-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-sonnet-4-6","displayName":"Claude Sonnet 4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-08-31"}},"claude-sonnet-5":{"metadata":{"displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-sonnet-5","displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash","displayName":"DeepSeek V4 Flash","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-flash-free":{"metadata":{"displayName":"DeepSeek V4 Flash Free","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash-free","displayName":"DeepSeek V4 Flash Free","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-flash-vision-exp":{"metadata":{"displayName":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash-vision-exp","displayName":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-pro","displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"gemini-3-flash":{"metadata":{"displayName":"Gemini 3 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-12-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"google","normalizeBaseUrl":false}},"entry":{"id":"gemini-3-flash","displayName":"Gemini 3 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-3-pro":{"metadata":{"displayName":"Gemini 3 Pro","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-11-18","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"google","normalizeBaseUrl":false}},"entry":{"id":"gemini-3-pro","displayName":"Gemini 3 Pro","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-3.1-pro":{"metadata":{"displayName":"Gemini 3.1 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-02-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"google","normalizeBaseUrl":false}},"entry":{"id":"gemini-3.1-pro","displayName":"Gemini 3.1 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-3.5-flash":{"metadata":{"displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"google","normalizeBaseUrl":false}},"entry":{"id":"gemini-3.5-flash","displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-3.5-flash-lite":{"metadata":{"displayName":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-07-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"google","normalizeBaseUrl":false}},"entry":{"id":"gemini-3.5-flash-lite","displayName":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2026-03"}},"gemini-3.6-flash":{"metadata":{"displayName":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-07-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"google","normalizeBaseUrl":false}},"entry":{"id":"gemini-3.6-flash","displayName":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2026-03"}},"gemini-3.7-flash":{"metadata":{"displayName":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-08-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"google","normalizeBaseUrl":false}},"entry":{"id":"gemini-3.7-flash","displayName":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2026-03"}},"gemini-3.8-flash":{"metadata":{"displayName":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"google","normalizeBaseUrl":false}},"entry":{"id":"gemini-3.8-flash","displayName":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576}},"glm-4.6":{"metadata":{"displayName":"GLM-4.6","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.6","displayName":"GLM-4.6","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"glm-4.7":{"metadata":{"displayName":"GLM-4.7","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2025-12-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.7","displayName":"GLM-4.7","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"glm-4.7-free":{"metadata":{"displayName":"GLM-4.7 Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2025-12-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.7-free","displayName":"GLM-4.7 Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"glm-5":{"metadata":{"displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5","displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"glm-5-free":{"metadata":{"displayName":"GLM-5 Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5-free","displayName":"GLM-5 Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"glm-5.1":{"metadata":{"displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.1","displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"glm-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5.3":{"metadata":{"displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.3","displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5.3-flash":{"metadata":{"displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"glm-5.3-flash","displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"gpt-5":{"metadata":{"displayName":"GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5","displayName":"GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"gpt-5-codex":{"metadata":{"displayName":"GPT-5 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-09-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5-codex","displayName":"GPT-5 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"gpt-5-nano":{"metadata":{"displayName":"GPT-5 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-05-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5-nano","displayName":"GPT-5 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-05-30"}},"gpt-5.1":{"metadata":{"displayName":"GPT-5.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.1","displayName":"GPT-5.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"gpt-5.1-codex":{"metadata":{"displayName":"GPT-5.1 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.1-codex","displayName":"GPT-5.1 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"gpt-5.1-codex-max":{"metadata":{"displayName":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.1-codex-max","displayName":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"gpt-5.1-codex-mini":{"metadata":{"displayName":"GPT-5.1 Codex Mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.1-codex-mini","displayName":"GPT-5.1 Codex Mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"gpt-5.2":{"metadata":{"displayName":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.2","displayName":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.2-codex":{"metadata":{"displayName":"GPT-5.2 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-01-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.2-codex","displayName":"GPT-5.2 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.3-codex":{"metadata":{"displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-02-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.3-codex","displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.3-codex-spark":{"metadata":{"displayName":"GPT-5.3 Codex Spark","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":128000,"inputLimit":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.3-codex-spark","displayName":"GPT-5.3 Codex Spark","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":128000,"inputLimit":128000,"defaultContextWindow":128000,"defaultInputLimit":128000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4":{"metadata":{"displayName":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.4","displayName":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4-mini":{"metadata":{"displayName":"GPT-5.4 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.4-mini","displayName":"GPT-5.4 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4-nano":{"metadata":{"displayName":"GPT-5.4 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.4-nano","displayName":"GPT-5.4 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4-pro":{"metadata":{"displayName":"GPT-5.4 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":false,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.4-pro","displayName":"GPT-5.4 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.5":{"metadata":{"displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.5","displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-12-01"}},"gpt-5.5-pro":{"metadata":{"displayName":"GPT-5.5 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":false,"lastUpdated":"2026-04-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.5-pro","displayName":"GPT-5.5 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-12-01"}},"gpt-5.6-luna":{"metadata":{"displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.6-luna","displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"gpt-5.6-sol":{"metadata":{"displayName":"GPT-5.6 Sol (50% Off)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.6-sol","displayName":"GPT-5.6 Sol (50% Off)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"gpt-5.6-terra":{"metadata":{"displayName":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.6-terra","displayName":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"gpt-6-astra":{"metadata":{"displayName":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-04-30","structuredOutput":true,"lastUpdated":"2026-09-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-6-astra","displayName":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-04-30"}},"grok-4.5":{"metadata":{"displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","lifecycle":"active","contextWindow":500000,"maxOutputTokens":500000,"structuredOutput":true,"lastUpdated":"2026-07-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"grok-4.5","displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":500000,"defaultContextWindow":500000}},"grok-4.6":{"metadata":{"displayName":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","lifecycle":"active","contextWindow":500000,"maxOutputTokens":500000,"knowledgeCutoff":"2026-02-01","structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"grok-4.6","displayName":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":500000,"defaultContextWindow":500000,"knowledgeCutoff":"2026-02-01"}},"grok-build-0.1":{"metadata":{"displayName":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"structuredOutput":true,"lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"grok-build-0.1","displayName":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"grok-code":{"metadata":{"displayName":"Grok Code Fast 1","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":256000,"maxOutputTokens":256000,"lastUpdated":"2025-08-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"grok-code","displayName":"Grok Code Fast 1","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"hy3-free":{"metadata":{"displayName":"Hy3 Free","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"deprecated","contextWindow":190000,"inputLimit":192000,"maxOutputTokens":64000,"structuredOutput":true,"lastUpdated":"2026-07-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hy3-free","displayName":"Hy3 Free","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":190000,"inputLimit":192000,"defaultContextWindow":190000,"defaultInputLimit":192000}},"hy3-preview-free":{"metadata":{"displayName":"Hy3 preview Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-06","lastUpdated":"2026-04-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hy3-preview-free","displayName":"Hy3 preview Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-06"}},"kimi-k2":{"metadata":{"displayName":"Kimi K2","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2024-10","lastUpdated":"2025-09-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"kimi-k2","displayName":"Kimi K2","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-10"}},"kimi-k2-thinking":{"metadata":{"displayName":"Kimi K2 Thinking","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2024-10","lastUpdated":"2025-09-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"kimi-k2-thinking","displayName":"Kimi K2 Thinking","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-10"}},"kimi-k2.5":{"metadata":{"displayName":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2024-10","lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.5","displayName":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-10"}},"kimi-k2.5-free":{"metadata":{"displayName":"Kimi K2.5 Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2024-10","lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.5-free","displayName":"Kimi K2.5 Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-10"}},"kimi-k2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2024-10","lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.6","displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-10"}},"kimi-k2.7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.7-code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k3":{"metadata":{"displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["max"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k3","displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"laguna-s-2.1-free":{"metadata":{"displayName":"Laguna S 2.1 Free","description":"Agentic coding model from Poolside in the XS size class for local deployment","lifecycle":"deprecated","contextWindow":256000,"maxOutputTokens":32000,"structuredOutput":false,"lastUpdated":"2026-07-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"laguna-s-2.1-free","displayName":"Laguna S 2.1 Free","description":"Agentic coding model from Poolside in the XS size class for local deployment","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000}},"ling-2.6-flash-free":{"metadata":{"displayName":"Ling 2.6 Flash Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262100,"maxOutputTokens":32800,"knowledgeCutoff":"2025-06","lastUpdated":"2026-04-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"ling-2.6-flash-free","displayName":"Ling 2.6 Flash Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262100,"defaultContextWindow":262100,"knowledgeCutoff":"2025-06"}},"ling-3.0-flash-fin-free":{"metadata":{"displayName":"Ling 3.0 Flash Fin Free","description":"Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-08-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"ling-3.0-flash-fin-free","displayName":"Ling 3.0 Flash Fin Free","description":"Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"ling-3.0-flash-free":{"metadata":{"displayName":"Ling-3.0-flash Free","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-07-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"ling-3.0-flash-free","displayName":"Ling-3.0-flash Free","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":262144,"defaultContextWindow":262144}},"ling-3.0-tiny-free":{"metadata":{"displayName":"Ling-3.0-tiny Free","description":"Compact MoE model for responsive agents, instruction following, and multi-turn conversations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-08-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"ling-3.0-tiny-free","displayName":"Ling-3.0-tiny Free","description":"Compact MoE model for responsive agents, instruction following, and multi-turn conversations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"longcat-2.0-free":{"metadata":{"displayName":"LongCat-2.0 Free","description":"Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window","lifecycle":"deprecated","contextWindow":1000000,"maxOutputTokens":131072,"lastUpdated":"2026-06-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"longcat-2.0-free","displayName":"LongCat-2.0 Free","description":"Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"mimo-v2-flash-free":{"metadata":{"displayName":"MiMo V2 Flash Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2024-12","lastUpdated":"2025-12-16","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2-flash-free","displayName":"MiMo V2 Flash Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-12"}},"mimo-v2-omni-free":{"metadata":{"displayName":"MiMo V2 Omni Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":64000,"knowledgeCutoff":"2024-12","lastUpdated":"2026-03-18","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio","pdf"],"output":["text"]}},"entry":{"id":"mimo-v2-omni-free","displayName":"MiMo V2 Omni Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-12"}},"mimo-v2-pro-free":{"metadata":{"displayName":"MiMo V2 Pro Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":1048576,"maxOutputTokens":64000,"knowledgeCutoff":"2024-12","lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2-pro-free","displayName":"MiMo V2 Pro Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2.5-free":{"metadata":{"displayName":"MiMo V2.5 Free","description":"MiMo omni model for text, image, video, audio, and agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":32000,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]}},"entry":{"id":"mimo-v2.5-free","displayName":"MiMo V2.5 Free","description":"MiMo omni model for text, image, video, audio, and agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-12"}},"minimax-m2.1":{"metadata":{"displayName":"MiniMax-M2.1","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01","lastUpdated":"2025-12-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax-m2.1","displayName":"MiniMax-M2.1","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01"}},"minimax-m2.1-free":{"metadata":{"displayName":"MiniMax-M2.1 Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01","lastUpdated":"2025-12-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"minimax-m2.1-free","displayName":"MiniMax-M2.1 Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01"}},"minimax-m2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01","lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax-m2.5","displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01"}},"minimax-m2.5-free":{"metadata":{"displayName":"MiniMax-M2.5 Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01","lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"minimax-m2.5-free","displayName":"MiniMax-M2.5 Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01"}},"minimax-m2.7":{"metadata":{"displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01","lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax-m2.7","displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01"}},"minimax-m3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","lifecycle":"active","contextWindow":512000,"maxOutputTokens":128000,"lastUpdated":"2026-06-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"minimax-m3","displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":512000,"defaultContextWindow":512000}},"minimax-m3-free":{"metadata":{"displayName":"MiniMax-M3 Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-05-31","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"minimax-m3-free","displayName":"MiniMax-M3 Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01"}},"muse-spark-1.2":{"metadata":{"displayName":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"muse-spark-1.2","displayName":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"muse-spark-1.2-contributor-free":{"metadata":{"displayName":"Muse Spark 1.2 Free","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"muse-spark-1.2-contributor-free","displayName":"Muse Spark 1.2 Free","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"muse-spark-1.3":{"metadata":{"displayName":"Muse Spark 1.3","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"muse-spark-1.3","displayName":"Muse Spark 1.3","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"muse-spark-1.3-contributor-free":{"metadata":{"displayName":"Muse Spark 1.3 Free","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for coding and agentic workflows.","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"muse-spark-1.3-contributor-free","displayName":"Muse Spark 1.3 Free","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for coding and agentic workflows.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"nemotron-3-super-free":{"metadata":{"displayName":"Nemotron 3 Super Free","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","lifecycle":"deprecated","contextWindow":204800,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02","lastUpdated":"2026-03-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nemotron-3-super-free","displayName":"Nemotron 3 Super Free","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2026-02"}},"nemotron-3-ultra-free":{"metadata":{"displayName":"Nemotron 3 Ultra Free","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02","lastUpdated":"2026-06-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nemotron-3-ultra-free","displayName":"Nemotron 3 Ultra Free","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-02"}},"nemotron-3.5-lightning-free":{"metadata":{"displayName":"Nemotron 3.5 Lightning Free","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-08-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nemotron-3.5-lightning-free","displayName":"Nemotron 3.5 Lightning Free","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"north-mini-code-free":{"metadata":{"displayName":"North Mini Code Free","description":"Cohere coding model for practical software engineering and agentic edits","lifecycle":"deprecated","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-09-23","structuredOutput":true,"lastUpdated":"2026-06-09","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"north-mini-code-free","displayName":"North Mini Code Free","description":"Cohere coding model for practical software engineering and agentic edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high"],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-09-23"}},"qwen3-coder":{"metadata":{"displayName":"Qwen3 Coder","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder","displayName":"Qwen3 Coder","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3.5-plus":{"metadata":{"displayName":"Qwen3.5 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"qwen3.5-plus","displayName":"Qwen3.5 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3.6-plus":{"metadata":{"displayName":"Qwen3.6 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"qwen3.6-plus","displayName":"Qwen3.6 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3.6-plus-free":{"metadata":{"displayName":"Qwen3.6 Plus Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"qwen3.6-plus-free","displayName":"Qwen3.6 Plus Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"ring-2.6-1t-free":{"metadata":{"displayName":"Ring 2.6 1T Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262000,"maxOutputTokens":66000,"knowledgeCutoff":"2025-06","lastUpdated":"2026-05-08","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"ring-2.6-1t-free","displayName":"Ring 2.6 1T Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000,"knowledgeCutoff":"2025-06"}},"trinity-large-preview-free":{"metadata":{"displayName":"Trinity Large Preview","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2025-06","lastUpdated":"2026-01-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"trinity-large-preview-free","displayName":"Trinity Large Preview","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-06"}},"x-preview-f-free":{"metadata":{"displayName":"Ox Alpha Free (Unlimited)","description":"Stealth reasoning model for coding, agentic tasks, and tool use","lifecycle":"deprecated","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"x-preview-f-free","displayName":"Ox Alpha Free (Unlimited)","description":"Stealth reasoning model for coding, agentic tasks, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}}}},"opencode-go":{"baseUrl":"https://opencode.ai/zen/go/v1","label":"OpenCode Go","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{"anthropic-messages":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"openai-responses":{"kind":"openai","apiProtocol":"openai-responses","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["minimax-m3","deepseek-v4-flash","deepseek-v4-flash-vision-exp","deepseek-v4-pro","deepseek-v4.1-flash","glm-5.1","glm-5.2","glm-5.3","glm-5.3-flash","gpt-5.6-luna","grok-4.6","hy3","hy4-preview","kimi-k2.6","kimi-k2.7-code","kimi-k3","longcat-2.0","mimo-v2.5","mimo-v2.5-pro","minimax-m2.7","muse-spark-1.2-contributor","muse-spark-1.3-contributor","qwen3.6-plus","qwen3.7-max","qwen3.7-plus","qwen3.8-flash","qwen3.8-max"],"models":{"deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash","displayName":"DeepSeek V4 Flash","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-flash-vision-exp":{"metadata":{"displayName":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash-vision-exp","displayName":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek V4 Pro (New)","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-pro","displayName":"DeepSeek V4 Pro (New)","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4.1-flash":{"metadata":{"displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-v4.1-flash","displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"glm-5":{"metadata":{"displayName":"GLM-5","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":202752,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5","displayName":"GLM-5","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752,"knowledgeCutoff":"2025-04"}},"glm-5.1":{"metadata":{"displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.1","displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752,"knowledgeCutoff":"2025-04"}},"glm-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5.3":{"metadata":{"displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.3","displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5.3-flash":{"metadata":{"displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"glm-5.3-flash","displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"gpt-5.6-luna":{"metadata":{"displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.6-luna","displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"grok-4.5":{"metadata":{"displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","lifecycle":"deprecated","contextWindow":500000,"maxOutputTokens":500000,"structuredOutput":true,"lastUpdated":"2026-07-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"grok-4.5","displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":500000,"defaultContextWindow":500000}},"grok-4.6":{"metadata":{"displayName":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","lifecycle":"active","contextWindow":500000,"maxOutputTokens":500000,"knowledgeCutoff":"2026-02-01","structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"grok-4.6","displayName":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":500000,"defaultContextWindow":500000,"knowledgeCutoff":"2026-02-01"}},"hy3":{"metadata":{"displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":256000,"inputLimit":192000,"maxOutputTokens":128000,"lastUpdated":"2026-07-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hy3","displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","high"],"contextWindow":256000,"inputLimit":192000,"defaultContextWindow":256000,"defaultInputLimit":192000}},"hy4-preview":{"metadata":{"displayName":"Hy4 preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":64000,"lastUpdated":"2026-08-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hy4-preview","displayName":"Hy4 preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high"],"contextWindow":1024000,"defaultContextWindow":1024000}},"kimi-k2.5":{"metadata":{"displayName":"Kimi K2.5","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2024-10","lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.5","displayName":"Kimi K2.5","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-10"}},"kimi-k2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2024-10","lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.6","displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-10"}},"kimi-k2.7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.7-code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k3":{"metadata":{"displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["max"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k3","displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"longcat-2.0":{"metadata":{"displayName":"LongCat-2.0","description":"Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"lastUpdated":"2026-06-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"longcat-2.0","displayName":"LongCat-2.0","description":"Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"mimo-v2-omni":{"metadata":{"displayName":"MiMo V2 Omni","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":128000,"knowledgeCutoff":"2024-12","lastUpdated":"2026-03-18","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio","pdf"],"output":["text"]}},"entry":{"id":"mimo-v2-omni","displayName":"MiMo V2 Omni","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-12"}},"mimo-v2-pro":{"metadata":{"displayName":"MiMo V2 Pro","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":1048576,"maxOutputTokens":128000,"knowledgeCutoff":"2024-12","lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2-pro","displayName":"MiMo V2 Pro","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2.5":{"metadata":{"displayName":"MiMo V2.5","description":"MiMo omni model for text, image, video, audio, and agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]}},"entry":{"id":"mimo-v2.5","displayName":"MiMo V2.5","description":"MiMo omni model for text, image, video, audio, and agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-12"}},"mimo-v2.5-pro":{"metadata":{"displayName":"MiMo V2.5 Pro","description":"MiMo pro model for strong multimodal reasoning and agent execution","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":128000,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2.5-pro","displayName":"MiMo V2.5 Pro","description":"MiMo pro model for strong multimodal reasoning and agent execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"minimax-m2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":204800,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"minimax-m2.5","displayName":"MiniMax-M2.5","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01"}},"minimax-m2.7":{"metadata":{"displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01","lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"minimax-m2.7","displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01"}},"minimax-m3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01","lastUpdated":"2026-05-31","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"minimax-m3","displayName":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-01"}},"muse-spark-1.2-contributor":{"metadata":{"displayName":"Muse Spark 1.2 Contributor","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"muse-spark-1.2-contributor","displayName":"Muse Spark 1.2 Contributor","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"muse-spark-1.3-contributor":{"metadata":{"displayName":"Muse Spark 1.3 Contributor","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for coding and agentic workflows.","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"muse-spark-1.3-contributor","displayName":"Muse Spark 1.3 Contributor","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for coding and agentic workflows.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"omen-alpha":{"metadata":{"displayName":"Omen Alpha","description":"oH man anothEr aLPha ModEl","lifecycle":"deprecated","contextWindow":500000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-09-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"omen-alpha","displayName":"Omen Alpha","description":"oH man anothEr aLPha ModEl","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high"],"contextWindow":500000,"defaultContextWindow":500000}},"ox-alpha-free":{"metadata":{"displayName":"Ox Alpha Free (Unlimited)","description":"Stealth reasoning model for coding, agentic tasks, and tool use","lifecycle":"deprecated","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"ox-alpha-free","displayName":"Ox Alpha Free (Unlimited)","description":"Stealth reasoning model for coding, agentic tasks, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.5-plus":{"metadata":{"displayName":"Qwen3.5 Plus","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.5-plus","displayName":"Qwen3.5 Plus","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3.6-plus":{"metadata":{"displayName":"Qwen3.6 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-plus","displayName":"Qwen3.6 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.7-max":{"metadata":{"displayName":"Qwen3.7 Max","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3.7-max","displayName":"Qwen3.7 Max","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.7-plus":{"metadata":{"displayName":"Qwen3.7 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"lastUpdated":"2026-06-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.7-plus","displayName":"Qwen3.7 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.8-flash":{"metadata":{"displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"qwen3.8-flash","displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.8-max":{"metadata":{"displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter multimodal flagship for coding, professional work, and long-horizon agentic workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-03","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.8-max","displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter multimodal flagship for coding, professional work, and long-horizon agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}}}},"togetherai":{"baseUrl":"https://api.together.ai/v1","label":"Together AI","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["MiniMaxAI/MiniMax-M3","deepseek-ai/DeepSeek-V4-Flash-0731","deepseek-ai/DeepSeek-V4-Pro","deepseek-ai/DeepSeek-V4-Pro-0813","deepseek-ai/DeepSeek-V4.1-Flash","google/gemma-4-31B-it","meta-llama/Llama-3.3-70B-Instruct-Turbo","MiniMaxAI/MiniMax-M2.7","moonshotai/Kimi-K2.6","moonshotai/Kimi-K2.7-Code","moonshotai/Kimi-K3","nvidia/nemotron-3-ultra-550b-a55b","openai/gpt-oss-120b","openai/gpt-oss-20b","Qwen/Qwen2.5-7B-Instruct-Turbo","Qwen/Qwen3.5-9B","Qwen/Qwen3.6-Plus","Qwen/Qwen3.7-Max","thinkingmachines/Inkling","zai-org/GLM-5.2","zai-org/GLM-5.3","zai-org/GLM-5.3-Flash"],"models":{"deepcogito/cogito-v2-1-671b":{"metadata":{"displayName":"Cogito v2.1 671B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":163840,"maxOutputTokens":163840,"lastUpdated":"2025-11-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepcogito/cogito-v2-1-671b","displayName":"Cogito v2.1 671B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840}},"deepseek-ai/DeepSeek-R1":{"metadata":{"displayName":"DeepSeek-R1","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":163839,"maxOutputTokens":163839,"knowledgeCutoff":"2024-07","lastUpdated":"2025-03-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-R1","displayName":"DeepSeek-R1","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163839,"defaultContextWindow":163839,"knowledgeCutoff":"2024-07"}},"deepseek-ai/DeepSeek-V3":{"metadata":{"displayName":"DeepSeek-V3","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2024-07","lastUpdated":"2025-05-29","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3","displayName":"DeepSeek-V3","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-07"}},"deepseek-ai/DeepSeek-V3-1":{"metadata":{"displayName":"DeepSeek V3.1","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2025-08","lastUpdated":"2025-08-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3-1","displayName":"DeepSeek V3.1","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-08"}},"deepseek-ai/DeepSeek-V4-Flash-0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-ai/DeepSeek-V4-Pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","lifecycle":"active","contextWindow":512000,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Pro","displayName":"DeepSeek V4 Pro","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":512000,"defaultContextWindow":512000}},"deepseek-ai/DeepSeek-V4-Pro-0813":{"metadata":{"displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"deepseek-ai/DeepSeek-V4.1-Flash":{"metadata":{"displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4.1-Flash","displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"essentialai/Rnj-1-Instruct":{"metadata":{"displayName":"Rnj-1 Instruct","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","lifecycle":"deprecated","contextWindow":32768,"maxOutputTokens":32768,"knowledgeCutoff":"2024-10","lastUpdated":"2025-12-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"essentialai/Rnj-1-Instruct","displayName":"Rnj-1 Instruct","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-10"}},"google/gemma-3n-E4B-it":{"metadata":{"displayName":"Gemma 3N E4B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":32768,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2025-05-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"google/gemma-3n-E4B-it","displayName":"Gemma 3N E4B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"google/gemma-4-31B-it":{"metadata":{"displayName":"Gemma 4 31B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-4-31B-it","displayName":"Gemma 4 31B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"LiquidAI/LFM2-24B-A2B":{"metadata":{"displayName":"LFM2-24B-A2B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","lifecycle":"active","contextWindow":32768,"maxOutputTokens":32768,"lastUpdated":"2026-02-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"LiquidAI/LFM2-24B-A2B","displayName":"LFM2-24B-A2B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"meta-llama/Llama-3.3-70B-Instruct-Turbo":{"metadata":{"displayName":"Llama 3.3 70B","description":"Compact Llama instruction model for fast chat and local deployment","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2023-12","lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","displayName":"Llama 3.3 70B","description":"Compact Llama instruction model for fast chat and local deployment","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12"}},"meta-llama/Meta-Llama-3-8B-Instruct-Lite":{"metadata":{"displayName":"Meta Llama 3 8B Instruct Lite","description":"Compact Llama instruction model for fast chat and local deployment","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2024-04-18","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/Meta-Llama-3-8B-Instruct-Lite","displayName":"Meta Llama 3 8B Instruct Lite","description":"Compact Llama instruction model for fast chat and local deployment","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"MiniMaxAI/MiniMax-M2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M2.5","displayName":"MiniMax-M2.5","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMaxAI/MiniMax-M2.7":{"metadata":{"displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":202752,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M2.7","displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"MiniMaxAI/MiniMax-M3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","lifecycle":"active","contextWindow":524288,"maxOutputTokens":250000,"structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M3","displayName":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":524288,"defaultContextWindow":524288}},"moonshotai/Kimi-K2.5":{"metadata":{"displayName":"Kimi K2.5","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2026-01","lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2.5","displayName":"Kimi K2.5","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2026-01"}},"moonshotai/Kimi-K2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131000,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2.6","displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/Kimi-K2.7-Code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Kimi coding model for software agents, refactors, and repository reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2.7-Code","displayName":"Kimi K2.7 Code","description":"Kimi coding model for software agents, refactors, and repository reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"moonshotai/Kimi-K3":{"metadata":{"displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K3","displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"nvidia/nemotron-3-ultra-550b-a55b":{"metadata":{"displayName":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","lifecycle":"active","contextWindow":512300,"maxOutputTokens":512300,"structuredOutput":true,"lastUpdated":"2026-06-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-ultra-550b-a55b","displayName":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":512300,"defaultContextWindow":512300}},"openai/gpt-oss-120b":{"metadata":{"displayName":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2025-08","lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-120b","displayName":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-08"}},"openai/gpt-oss-20b":{"metadata":{"displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-20b","displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"pearl-ai/gemma-4-31b-it":{"metadata":{"displayName":"Pearl AI Gemma 4 31B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":32000,"maxOutputTokens":32000,"lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"pearl-ai/gemma-4-31b-it","displayName":"Pearl AI Gemma 4 31B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"Qwen/Qwen2.5-7B-Instruct-Turbo":{"metadata":{"displayName":"Qwen 2.5 7B Instruct Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","lifecycle":"active","contextWindow":32768,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2024-09-19","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen2.5-7B-Instruct-Turbo","displayName":"Qwen 2.5 7B Instruct Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"Qwen/Qwen3-235B-A22B-Instruct-2507-tput":{"metadata":{"displayName":"Qwen3 235B A22B Instruct 2507 FP8","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-07","lastUpdated":"2025-07-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507-tput","displayName":"Qwen3 235B A22B Instruct 2507 FP8","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-07"}},"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8":{"metadata":{"displayName":"Qwen3 Coder 480B A35B Instruct","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","displayName":"Qwen3 Coder 480B A35B Instruct","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-Coder-Next-FP8":{"metadata":{"displayName":"Qwen3 Coder Next FP8","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2026-02-03","lastUpdated":"2026-02-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Coder-Next-FP8","displayName":"Qwen3 Coder Next FP8","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2026-02-03"}},"Qwen/Qwen3.5-397B-A17B":{"metadata":{"displayName":"Qwen3.5 397B A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":130000,"lastUpdated":"2026-06-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-397B-A17B","displayName":"Qwen3.5 397B A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.5-9B":{"metadata":{"displayName":"Qwen3.5 9B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-03-03","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-9B","displayName":"Qwen3.5 9B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.6-Plus":{"metadata":{"displayName":"Qwen3.6 Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":500000,"lastUpdated":"2026-04-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.6-Plus","displayName":"Qwen3.6 Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"Qwen/Qwen3.7-Max":{"metadata":{"displayName":"Qwen3.7 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":500000,"lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.7-Max","displayName":"Qwen3.7 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"thinkingmachines/Inkling":{"metadata":{"displayName":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","lifecycle":"active","contextWindow":524288,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["max","xhigh","high","medium","low","none"]},"modalities":{"input":["text","image","audio"],"output":["text"]}},"entry":{"id":"thinkingmachines/Inkling","displayName":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":524288,"defaultContextWindow":524288}},"zai-org/GLM-5":{"metadata":{"displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","lifecycle":"deprecated","contextWindow":202752,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-02-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5","displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"zai-org/GLM-5.1":{"metadata":{"displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"deprecated","contextWindow":202752,"maxOutputTokens":131072,"knowledgeCutoff":"2025-11","structuredOutput":true,"lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.1","displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752,"knowledgeCutoff":"2025-11"}},"zai-org/GLM-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":512000,"maxOutputTokens":164000,"structuredOutput":true,"lastUpdated":"2026-06-16","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":512000,"defaultContextWindow":512000}},"zai-org/GLM-5.3":{"metadata":{"displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.3","displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"zai-org/GLM-5.3-Flash":{"metadata":{"displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","lifecycle":"active","contextWindow":1048575,"maxOutputTokens":400000,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.3-Flash","displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048575,"defaultContextWindow":1048575}}}},"fireworks-ai":{"baseUrl":"https://api.fireworks.ai/inference/v1/","label":"Fireworks AI","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"fireworks","accountsPath":"/v1/accounts","publicAccount":"accounts/fireworks","query":{"filter":"supports_serverless=true","pageSize":"200"}},"fallbackModels":["accounts/fireworks/models/kimi-k2p6","accounts/fireworks/models/deepseek-v4-flash-0731","accounts/fireworks/models/deepseek-v4-flash-vision-exp","accounts/fireworks/models/deepseek-v4-pro-0813","accounts/fireworks/models/deepseek-v4p1-flash","accounts/fireworks/models/glm-5p2","accounts/fireworks/models/glm-5p3","accounts/fireworks/models/glm-5p3-flash","accounts/fireworks/models/gpt-oss-120b","accounts/fireworks/models/inkling","accounts/fireworks/models/kimi-k2p7-code","accounts/fireworks/models/kimi-k3","accounts/fireworks/models/minimax-m3","accounts/fireworks/models/mistral-large-3-fp8","accounts/fireworks/models/muse-glimmer-30b","accounts/fireworks/models/nemotron-3-ultra-nvfp4","accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b","accounts/fireworks/models/qwen3p7-plus","accounts/fireworks/models/qwen3p8-2p4t-a95b","accounts/fireworks/models/qwen3p8-max","accounts/fireworks/routers/glm-5p2-fast","accounts/fireworks/routers/glm-5p3-fast","accounts/fireworks/routers/kimi-k3-fast"],"models":{"accounts/fireworks/models/deepseek-v4-flash-0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/deepseek-v4-flash-0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"accounts/fireworks/models/deepseek-v4-flash-vision-exp":{"metadata":{"displayName":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/deepseek-v4-flash-vision-exp","displayName":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"accounts/fireworks/models/deepseek-v4-pro-0813":{"metadata":{"displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/deepseek-v4-pro-0813","displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"accounts/fireworks/models/deepseek-v4p1-flash":{"metadata":{"displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/deepseek-v4p1-flash","displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"accounts/fireworks/models/glm-5p2":{"metadata":{"displayName":"GLM 5.2","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":1048575,"maxOutputTokens":131072,"lastUpdated":"2026-06-16","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/glm-5p2","displayName":"GLM 5.2","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1048575,"defaultContextWindow":1048575}},"accounts/fireworks/models/glm-5p3":{"metadata":{"displayName":"GLM 5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1048573,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-09-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/glm-5p3","displayName":"GLM 5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1048573,"defaultContextWindow":1048573}},"accounts/fireworks/models/glm-5p3-flash":{"metadata":{"displayName":"GLM 5.3 Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","lifecycle":"active","contextWindow":1048573,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-09-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/glm-5p3-flash","displayName":"GLM 5.3 Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048573,"defaultContextWindow":1048573}},"accounts/fireworks/models/gpt-oss-120b":{"metadata":{"displayName":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"lastUpdated":"2026-06-16","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/gpt-oss-120b","displayName":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"accounts/fireworks/models/inkling":{"metadata":{"displayName":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"lastUpdated":"2026-07-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/inkling","displayName":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}},"accounts/fireworks/models/kimi-k2p6":{"metadata":{"displayName":"Kimi K2.6","description":"Kimi reasoning model for long-horizon research, planning, and tool use","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"lastUpdated":"2026-04-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/kimi-k2p6","displayName":"Kimi K2.6","description":"Kimi reasoning model for long-horizon research, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"accounts/fireworks/models/kimi-k2p7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Kimi coding model for software agents, refactors, and repository reasoning","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"lastUpdated":"2026-06-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/kimi-k2p7-code","displayName":"Kimi K2.7 Code","description":"Kimi coding model for software agents, refactors, and repository reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"accounts/fireworks/models/kimi-k3":{"metadata":{"displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/kimi-k3","displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"accounts/fireworks/models/minimax-m3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","lifecycle":"active","contextWindow":512000,"maxOutputTokens":512000,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/minimax-m3","displayName":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":512000,"defaultContextWindow":512000}},"accounts/fireworks/models/mistral-large-3-fp8":{"metadata":{"displayName":"Mistral Large 3 675B Instruct 2512","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2024-11","lastUpdated":"2025-12-02","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/mistral-large-3-fp8","displayName":"Mistral Large 3 675B Instruct 2512","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-11"}},"accounts/fireworks/models/muse-glimmer-30b":{"metadata":{"displayName":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2026-01-04","structuredOutput":true,"lastUpdated":"2026-08-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/muse-glimmer-30b","displayName":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2026-01-04"}},"accounts/fireworks/models/nemotron-3-ultra-nvfp4":{"metadata":{"displayName":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","lifecycle":"active","contextWindow":262144,"maxOutputTokens":128000,"lastUpdated":"2026-06-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/nemotron-3-ultra-nvfp4","displayName":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b":{"metadata":{"displayName":"Nemotron 3.5 Lightning 30B A3B","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-08-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b","displayName":"Nemotron 3.5 Lightning 30B A3B","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"accounts/fireworks/models/qwen3p7-plus":{"metadata":{"displayName":"Qwen 3.7 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/qwen3p7-plus","displayName":"Qwen 3.7 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":262144,"defaultContextWindow":262144}},"accounts/fireworks/models/qwen3p8-2p4t-a95b":{"metadata":{"displayName":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/qwen3p8-2p4t-a95b","displayName":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","xhigh"],"contextWindow":262144,"defaultContextWindow":262144}},"accounts/fireworks/models/qwen3p8-max":{"metadata":{"displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"lastUpdated":"2026-08-03","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/qwen3p8-max","displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"accounts/fireworks/routers/glm-5p2-fast":{"metadata":{"displayName":"GLM 5.2 Fast","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":1048575,"maxOutputTokens":131072,"lastUpdated":"2026-06-26","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"accounts/fireworks/routers/glm-5p2-fast","displayName":"GLM 5.2 Fast","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1048575,"defaultContextWindow":1048575}},"accounts/fireworks/routers/glm-5p3-fast":{"metadata":{"displayName":"GLM 5.3 Fast","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1048572,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-09-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"accounts/fireworks/routers/glm-5p3-fast","displayName":"GLM 5.3 Fast","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1048572,"defaultContextWindow":1048572}},"accounts/fireworks/routers/kimi-k3-fast":{"metadata":{"displayName":"Kimi K3 Fast","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"accounts/fireworks/routers/kimi-k3-fast","displayName":"Kimi K3 Fast","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}}}},"nvidia":{"baseUrl":"https://integrate.api.nvidia.com/v1","label":"NVIDIA","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["nvidia/nemotron-3-super-120b-a12b","abacusai/dracarys-llama-3.1-70b-instruct","bytedance/seed-oss-36b-instruct","deepseek-ai/deepseek-v4-flash","deepseek-ai/deepseek-v4-flash-0731","deepseek-ai/deepseek-v4-pro","deepseek-ai/deepseek-v4-pro-0813","google/gemma-2-2b-it","google/gemma-3-12b-it","google/gemma-3-4b-it","google/gemma-3n-e2b-it","google/gemma-3n-e4b-it","google/gemma-4-31b-it","meta/llama-3.1-70b-instruct","meta/llama-3.1-8b-instruct","meta/llama-3.2-11b-vision-instruct","meta/llama-3.2-1b-instruct","meta/llama-3.2-90b-vision-instruct","meta/llama-3.3-70b-instruct","meta/llama-4-maverick-17b-128e-instruct","meta/muse-glimmer-30b","microsoft/phi-4-mini-instruct","minimaxai/minimax-m2.7","minimaxai/minimax-m3","mistralai/ministral-14b-instruct-2512","mistralai/mistral-7b-instruct-v0.3","mistralai/mistral-large-3-675b-instruct-2512","mistralai/mistral-medium-3.5-128b","mistralai/mistral-nemotron","mistralai/mistral-small-4-119b-2603","mistralai/mixtral-8x22b-instruct","mistralai/mixtral-8x7b-instruct","moonshotai/kimi-k3","nvidia/cosmos-reason2-8b","nvidia/llama-3.1-nemotron-70b-instruct","nvidia/llama-3.1-nemotron-nano-8b-v1","nvidia/llama-3.1-nemotron-nano-vl-8b-v1","nvidia/llama-3.1-nemotron-ultra-253b-v1","nvidia/llama-3.3-nemotron-super-49b-v1","nvidia/llama-3.3-nemotron-super-49b-v1.5","nvidia/nemotron-3-nano-30b-a3b","nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","nvidia/nemotron-3-ultra-550b-a55b","nvidia/nemotron-3.5-lightning-30b-a3b","nvidia/nemotron-mini-4b-instruct","nvidia/nemotron-nano-12b-v2-vl","nvidia/nemotron-voicechat","nvidia/nvidia-nemotron-nano-9b-v2","openai/gpt-oss-120b","openai/gpt-oss-20b","poolside/laguna-xs-2.1","qwen/qwen2.5-coder-32b-instruct","qwen/qwen3-coder-480b-a35b-instruct","qwen/qwen3-next-80b-a3b-instruct","qwen/qwen3.5-122b-a10b","qwen/qwen3.5-397b-a17b","sarvamai/sarvam-m","stepfun-ai/step-3.5-flash","stepfun-ai/step-3.7-flash","thinkingmachines/inkling","upstage/solar-10.7b-instruct","z-ai/glm-5.2","z-ai/glm-5.3-flash"],"models":{"abacusai/dracarys-llama-3.1-70b-instruct":{"metadata":{"displayName":"dracarys-llama-3.1-70b-instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2025-05-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"abacusai/dracarys-llama-3.1-70b-instruct","displayName":"dracarys-llama-3.1-70b-instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"baai/bge-m3":{"metadata":{"displayName":"BGE M3","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1024,"lastUpdated":"2026-04-30","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"baai/bge-m3","displayName":"BGE M3","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"black-forest-labs/flux_1-kontext-dev":{"metadata":{"displayName":"FLUX.1-Kontext-dev","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":40960,"maxOutputTokens":40960,"lastUpdated":"2025-08-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["image"]}},"entry":{"id":"black-forest-labs/flux_1-kontext-dev","displayName":"FLUX.1-Kontext-dev","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":40960,"defaultContextWindow":40960}},"black-forest-labs/flux_1-schnell":{"metadata":{"displayName":"FLUX.1-schnell","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":77,"inputLimit":77,"knowledgeCutoff":"2024-07","structuredOutput":false,"lastUpdated":"2026-02-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"black-forest-labs/flux_1-schnell","displayName":"FLUX.1-schnell","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":77,"inputLimit":77,"defaultContextWindow":77,"defaultInputLimit":77,"knowledgeCutoff":"2024-07"}},"black-forest-labs/flux_2-klein-4b":{"metadata":{"displayName":"FLUX.2 Klein 4B","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":40960,"maxOutputTokens":40960,"knowledgeCutoff":"2025-06","lastUpdated":"2026-01-31","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["image","text"],"output":["image"]}},"entry":{"id":"black-forest-labs/flux_2-klein-4b","displayName":"FLUX.2 Klein 4B","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":40960,"defaultContextWindow":40960,"knowledgeCutoff":"2025-06"}},"black-forest-labs/flux.1-dev":{"metadata":{"displayName":"FLUX.1-dev","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":4096,"knowledgeCutoff":"2024-08","lastUpdated":"2025-09-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"black-forest-labs/flux.1-dev","displayName":"FLUX.1-dev","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":4096,"defaultContextWindow":4096,"knowledgeCutoff":"2024-08"}},"bytedance/seed-oss-36b-instruct":{"metadata":{"displayName":"ByteDance-Seed/Seed-OSS-36B-Instruct","description":"Tool-capable chat model for instruction following and agentic application workflows","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"bytedance/seed-oss-36b-instruct","displayName":"ByteDance-Seed/Seed-OSS-36B-Instruct","description":"Tool-capable chat model for instruction following and agentic application workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"deepseek-ai/deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":393216,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/deepseek-v4-flash","displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"deepseek-ai/deepseek-v4-flash-0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/deepseek-v4-flash-0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-ai/deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":393216,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/deepseek-v4-pro","displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"deepseek-ai/deepseek-v4-pro-0813":{"metadata":{"displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/deepseek-v4-pro-0813","displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"google/gemma-2-2b-it":{"metadata":{"displayName":"Gemma 2 2b It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"structuredOutput":true,"lastUpdated":"2024-07-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"google/gemma-2-2b-it","displayName":"Gemma 2 2b It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"google/gemma-3-12b-it":{"metadata":{"displayName":"Gemma 3 12B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"lastUpdated":"2025-03-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3-12b-it","displayName":"Gemma 3 12B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"google/gemma-3-4b-it":{"metadata":{"displayName":"Gemma 3 4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"lastUpdated":"2025-03-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3-4b-it","displayName":"Gemma 3 4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"google/gemma-3n-e2b-it":{"metadata":{"displayName":"Gemma 3n E2b It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2024-06","structuredOutput":true,"lastUpdated":"2025-06-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3n-e2b-it","displayName":"Gemma 3n E2b It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-06"}},"google/gemma-3n-e4b-it":{"metadata":{"displayName":"Gemma 3n E4b It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2024-06","structuredOutput":true,"lastUpdated":"2025-06-03","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3n-e4b-it","displayName":"Gemma 3n E4b It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-06"}},"google/gemma-4-31b-it":{"metadata":{"displayName":"Gemma-4-31B-IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":256000,"maxOutputTokens":16384,"knowledgeCutoff":"2025-01","lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"google/gemma-4-31b-it","displayName":"Gemma-4-31B-IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-01"}},"google/google-paligemma":{"metadata":{"displayName":"paligemma","description":"Gemini multimodal model for text, image, audio, video, and document tasks","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2024-08-26","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/google-paligemma","displayName":"paligemma","description":"Gemini multimodal model for text, image, audio, video, and document tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"meta/esm2-650m":{"metadata":{"displayName":"esm2-650m","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2025-03-10","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta/esm2-650m","displayName":"esm2-650m","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"meta/esmfold":{"metadata":{"displayName":"esmfold","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2025-06-12","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta/esmfold","displayName":"esmfold","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"meta/llama-3.1-70b-instruct":{"metadata":{"displayName":"Llama 3.1 70b Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"structuredOutput":true,"lastUpdated":"2024-07-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta/llama-3.1-70b-instruct","displayName":"Llama 3.1 70b Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"meta/llama-3.1-8b-instruct":{"metadata":{"displayName":"Llama 3.1 8B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":16000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-12","lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta/llama-3.1-8b-instruct","displayName":"Llama 3.1 8B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16000,"defaultContextWindow":16000,"knowledgeCutoff":"2023-12"}},"meta/llama-3.2-11b-vision-instruct":{"metadata":{"displayName":"Llama 3.2 11b Vision Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-12","structuredOutput":true,"lastUpdated":"2024-09-18","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta/llama-3.2-11b-vision-instruct","displayName":"Llama 3.2 11b Vision Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-12"}},"meta/llama-3.2-1b-instruct":{"metadata":{"displayName":"Llama 3.2 1b Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-12","structuredOutput":true,"lastUpdated":"2024-09-18","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta/llama-3.2-1b-instruct","displayName":"Llama 3.2 1b Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-12"}},"meta/llama-3.2-3b-instruct":{"metadata":{"displayName":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":32768,"maxOutputTokens":32000,"structuredOutput":true,"lastUpdated":"2024-09-18","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta/llama-3.2-3b-instruct","displayName":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"meta/llama-3.2-90b-vision-instruct":{"metadata":{"displayName":"Llama-3.2-90B-Vision-Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"knowledgeCutoff":"2023-12","lastUpdated":"2024-09-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta/llama-3.2-90b-vision-instruct","displayName":"Llama-3.2-90B-Vision-Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-12"}},"meta/llama-3.3-70b-instruct":{"metadata":{"displayName":"Llama 3.3 70b Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"structuredOutput":true,"lastUpdated":"2024-11-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta/llama-3.3-70b-instruct","displayName":"Llama 3.3 70b Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"meta/llama-4-maverick-17b-128e-instruct":{"metadata":{"displayName":"Llama 4 Maverick 17b 128e Instruct","description":"Open multimodal Llama model for strong reasoning and fast responses","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2024-02","structuredOutput":true,"lastUpdated":"2025-04-01","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta/llama-4-maverick-17b-128e-instruct","displayName":"Llama 4 Maverick 17b 128e Instruct","description":"Open multimodal Llama model for strong reasoning and fast responses","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-02"}},"meta/llama-guard-4-12b":{"metadata":{"displayName":"Llama Guard 4 12B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"lastUpdated":"2026-04-30","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta/llama-guard-4-12b","displayName":"Llama Guard 4 12B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"meta/muse-glimmer-30b":{"metadata":{"displayName":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2026-01-04","structuredOutput":true,"lastUpdated":"2026-08-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","minimal","low","medium","high","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta/muse-glimmer-30b","displayName":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","minimal","low","medium","high","max"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2026-01-04"}},"microsoft/phi-4-mini-instruct":{"metadata":{"displayName":"Phi-4-Mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-12","lastUpdated":"2025-09-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"microsoft/phi-4-mini-instruct","displayName":"Phi-4-Mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-12"}},"microsoft/phi-4-multimodal-instruct":{"metadata":{"displayName":"Phi 4 Multimodal","description":"General-purpose chat model for instruction following, writing, and analysis","lifecycle":"active","contextWindow":128000,"inputLimit":128000,"maxOutputTokens":16384,"structuredOutput":false,"lastUpdated":"2025-07-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"microsoft/phi-4-multimodal-instruct","displayName":"Phi 4 Multimodal","description":"General-purpose chat model for instruction following, writing, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"inputLimit":128000,"defaultContextWindow":128000,"defaultInputLimit":128000}},"minimaxai/minimax-m2.7":{"metadata":{"displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-04-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimaxai/minimax-m2.7","displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"minimaxai/minimax-m3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":16384,"lastUpdated":"2026-06-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"minimaxai/minimax-m3","displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"mistralai/magistral-small-2506":{"metadata":{"displayName":"Magistral Small 2506","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","lifecycle":"active","contextWindow":32768,"inputLimit":32768,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2025-09-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistralai/magistral-small-2506","displayName":"Magistral Small 2506","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"inputLimit":32768,"defaultContextWindow":32768,"defaultInputLimit":32768}},"mistralai/ministral-14b-instruct-2512":{"metadata":{"displayName":"Ministral 3 14B Instruct 2512","description":"Compact Mistral VLM for chat and instruction-based workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"lastUpdated":"2025-12-02","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistralai/ministral-14b-instruct-2512","displayName":"Ministral 3 14B Instruct 2512","description":"Compact Mistral VLM for chat and instruction-based workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"mistralai/mistral-7b-instruct-v0.3":{"metadata":{"displayName":"Mistral-7B-Instruct-v0.3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":65536,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2025-04-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistralai/mistral-7b-instruct-v0.3","displayName":"Mistral-7B-Instruct-v0.3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536}},"mistralai/mistral-large-3-675b-instruct-2512":{"metadata":{"displayName":"Mistral Large 3 675B Instruct 2512","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-12-02","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistralai/mistral-large-3-675b-instruct-2512","displayName":"Mistral Large 3 675B Instruct 2512","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"mistralai/mistral-medium-3-instruct":{"metadata":{"displayName":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":131072,"inputLimit":131072,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2025-09-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistralai/mistral-medium-3-instruct","displayName":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"inputLimit":131072,"defaultContextWindow":131072,"defaultInputLimit":131072}},"mistralai/mistral-medium-3.5-128b":{"metadata":{"displayName":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-04-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistralai/mistral-medium-3.5-128b","displayName":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","high"],"contextWindow":262144,"defaultContextWindow":262144}},"mistralai/mistral-nemotron":{"metadata":{"displayName":"mistral-nemotron","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2025-06-12","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistralai/mistral-nemotron","displayName":"mistral-nemotron","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"mistralai/mistral-small-4-119b-2603":{"metadata":{"displayName":"mistral-small-4-119b-2603","description":"Efficient Mistral model for fast chat, extraction, and production assistants","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"structuredOutput":true,"lastUpdated":"2026-03-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistralai/mistral-small-4-119b-2603","displayName":"mistral-small-4-119b-2603","description":"Efficient Mistral model for fast chat, extraction, and production assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","high"],"contextWindow":128000,"defaultContextWindow":128000}},"mistralai/mixtral-8x22b-instruct":{"metadata":{"displayName":"Mistral: Mixtral 8x22B Instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":65536,"maxOutputTokens":13108,"lastUpdated":"2024-04-17","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistralai/mixtral-8x22b-instruct","displayName":"Mistral: Mixtral 8x22B Instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536}},"mistralai/mixtral-8x7b-instruct":{"metadata":{"displayName":"Mistral: Mixtral 8x7B Instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":32768,"maxOutputTokens":16384,"lastUpdated":"2026-03-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistralai/mixtral-8x7b-instruct","displayName":"Mistral: Mixtral 8x7B Instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"moonshotai/kimi-k2-instruct-0905":{"metadata":{"displayName":"Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2024-10","lastUpdated":"2025-09-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2-instruct-0905","displayName":"Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-10"}},"moonshotai/kimi-k2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","minimal","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.6","displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","minimal","low","medium","high","xhigh","max"],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/kimi-k3":{"metadata":{"displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k3","displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"nvidia/active-speaker-detection":{"metadata":{"displayName":"Active Speaker Detection","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","lifecycle":"active","maxOutputTokens":4096,"lastUpdated":"2026-04-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["video"],"output":["text"]}},"entry":{"id":"nvidia/active-speaker-detection","displayName":"Active Speaker Detection","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"nvidia/bevformer":{"metadata":{"displayName":"bevformer","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2025-07-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["video"],"output":["text"]}},"entry":{"id":"nvidia/bevformer","displayName":"bevformer","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/cosmos-predict1-5b":{"metadata":{"displayName":"cosmos-predict1-5b","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","maxOutputTokens":4096,"lastUpdated":"2025-03-18","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","video"],"output":["video"]}},"entry":{"id":"nvidia/cosmos-predict1-5b","displayName":"cosmos-predict1-5b","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"nvidia/cosmos-reason2-8b":{"metadata":{"displayName":"Cosmos Reason2 8B","description":"Vision language model for physical-world understanding with structured reasoning on video and images","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"lastUpdated":"2025-12-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"nvidia/cosmos-reason2-8b","displayName":"Cosmos Reason2 8B","description":"Vision language model for physical-world understanding with structured reasoning on video and images","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"nvidia/cosmos-transfer1-7b":{"metadata":{"displayName":"cosmos-transfer1-7b","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","maxOutputTokens":4096,"lastUpdated":"2025-06-30","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","video"],"output":["video"]}},"entry":{"id":"nvidia/cosmos-transfer1-7b","displayName":"cosmos-transfer1-7b","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"nvidia/cosmos-transfer2_5-2b":{"metadata":{"displayName":"cosmos-transfer2.5-2b","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","maxOutputTokens":4096,"lastUpdated":"2026-02-26","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","video"],"output":["video"]}},"entry":{"id":"nvidia/cosmos-transfer2_5-2b","displayName":"cosmos-transfer2.5-2b","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"nvidia/gliner-pii":{"metadata":{"displayName":"gliner-pii","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"lastUpdated":"2026-03-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/gliner-pii","displayName":"gliner-pii","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/llama-3_2-nemoretriever-300m-embed-v1":{"metadata":{"displayName":"llama-3_2-nemoretriever-300m-embed-v1","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":32768,"maxOutputTokens":2048,"lastUpdated":"2025-07-24","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/llama-3_2-nemoretriever-300m-embed-v1","displayName":"llama-3_2-nemoretriever-300m-embed-v1","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"nvidia/llama-3.1-nemotron-70b-instruct":{"metadata":{"displayName":"Llama 3.1 Nemotron 70B Instruct","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2025-04-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/llama-3.1-nemotron-70b-instruct","displayName":"Llama 3.1 Nemotron 70B Instruct","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/llama-3.1-nemotron-nano-8b-v1":{"metadata":{"displayName":"Llama 3.1 Nemotron Nano 8B v1","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"lastUpdated":"2025-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/llama-3.1-nemotron-nano-8b-v1","displayName":"Llama 3.1 Nemotron Nano 8B v1","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"nvidia/llama-3.1-nemotron-nano-vl-8b-v1":{"metadata":{"displayName":"Llama 3.1 Nemotron Nano VL 8B v1","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","lifecycle":"active","contextWindow":32768,"maxOutputTokens":16384,"lastUpdated":"2025-04-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"nvidia/llama-3.1-nemotron-nano-vl-8b-v1","displayName":"Llama 3.1 Nemotron Nano VL 8B v1","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"nvidia/llama-3.1-nemotron-safety-guard-8b-v3":{"metadata":{"displayName":"llama-3.1-nemotron-safety-guard-8b-v3","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"lastUpdated":"2025-10-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/llama-3.1-nemotron-safety-guard-8b-v3","displayName":"llama-3.1-nemotron-safety-guard-8b-v3","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/llama-3.1-nemotron-ultra-253b-v1":{"metadata":{"displayName":"Llama 3.1 Nemotron Ultra 253B","description":"Flagship Nemotron model for high-throughput reasoning and complex agents","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"lastUpdated":"2025-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/llama-3.1-nemotron-ultra-253b-v1","displayName":"Llama 3.1 Nemotron Ultra 253B","description":"Flagship Nemotron model for high-throughput reasoning and complex agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/llama-3.3-nemotron-super-49b-v1":{"metadata":{"displayName":"Llama 3.3 Nemotron Super 49B v1","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"lastUpdated":"2025-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/llama-3.3-nemotron-super-49b-v1","displayName":"Llama 3.3 Nemotron Super 49B v1","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"nvidia/llama-3.3-nemotron-super-49b-v1.5":{"metadata":{"displayName":"Llama 3.3 Nemotron Super 49B v1.5","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"lastUpdated":"2025-07-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/llama-3.3-nemotron-super-49b-v1.5","displayName":"Llama 3.3 Nemotron Super 49B v1.5","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"nvidia/llama-nemotron-embed-vl-1b-v2":{"metadata":{"displayName":"llama-nemotron-embed-vl-1b-v2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":32768,"maxOutputTokens":2048,"lastUpdated":"2026-02-10","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"nvidia/llama-nemotron-embed-vl-1b-v2","displayName":"llama-nemotron-embed-vl-1b-v2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"nvidia/llama-nemotron-rerank-vl-1b-v2":{"metadata":{"displayName":"llama-nemotron-rerank-vl-1b-v2","description":"Reranking model for improving retrieval quality in search and recommendation systems","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"lastUpdated":"2026-03-31","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"nvidia/llama-nemotron-rerank-vl-1b-v2","displayName":"llama-nemotron-rerank-vl-1b-v2","description":"Reranking model for improving retrieval quality in search and recommendation systems","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/magpie-tts-zeroshot":{"metadata":{"displayName":"magpie-tts-zeroshot","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","maxOutputTokens":4096,"lastUpdated":"2025-06-12","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","audio"],"output":["audio"]}},"entry":{"id":"nvidia/magpie-tts-zeroshot","displayName":"magpie-tts-zeroshot","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"nvidia/nemotron-3-content-safety":{"metadata":{"displayName":"nemotron-3-content-safety","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"lastUpdated":"2026-04-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-content-safety","displayName":"nemotron-3-content-safety","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/nemotron-3-nano-30b-a3b":{"metadata":{"displayName":"nemotron-3-nano-30b-a3b","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2024-09","lastUpdated":"2024-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-nano-30b-a3b","displayName":"nemotron-3-nano-30b-a3b","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-09"}},"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning":{"metadata":{"displayName":"Nemotron 3 Nano Omni","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","lifecycle":"active","contextWindow":256000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","displayName":"Nemotron 3 Nano Omni","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"nvidia/nemotron-3-super-120b-a12b":{"metadata":{"displayName":"Nemotron 3 Super","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2024-04","lastUpdated":"2026-03-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-super-120b-a12b","displayName":"Nemotron 3 Super","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-04"}},"nvidia/nemotron-3-ultra-550b-a55b":{"metadata":{"displayName":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-06-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-ultra-550b-a55b","displayName":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"nvidia/nemotron-3.5-lightning-30b-a3b":{"metadata":{"displayName":"Nemotron 3.5 Lightning 30B A3B","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-08-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3.5-lightning-30b-a3b","displayName":"Nemotron 3.5 Lightning 30B A3B","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"nvidia/nemotron-content-safety-reasoning-4b":{"metadata":{"displayName":"nemotron-content-safety-reasoning-4b","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"lastUpdated":"2026-01-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-content-safety-reasoning-4b","displayName":"nemotron-content-safety-reasoning-4b","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/nemotron-mini-4b-instruct":{"metadata":{"displayName":"nemotron-mini-4b-instruct","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2024-08-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-mini-4b-instruct","displayName":"nemotron-mini-4b-instruct","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/nemotron-nano-12b-v2-vl":{"metadata":{"displayName":"Nemotron Nano 12B v2 VL","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"lastUpdated":"2025-10-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-nano-12b-v2-vl","displayName":"Nemotron Nano 12B v2 VL","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/nemotron-voicechat":{"metadata":{"displayName":"nemotron-voicechat","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2026-03-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","audio"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-voicechat","displayName":"nemotron-voicechat","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/nv-embed-v1":{"metadata":{"displayName":"nv-embed-v1","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":32768,"maxOutputTokens":2048,"lastUpdated":"2025-07-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nv-embed-v1","displayName":"nv-embed-v1","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"nvidia/nv-embedcode-7b-v1":{"metadata":{"displayName":"nv-embedcode-7b-v1","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","contextWindow":32768,"maxOutputTokens":2048,"lastUpdated":"2025-05-29","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nv-embedcode-7b-v1","displayName":"nv-embedcode-7b-v1","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"nvidia/nvidia-nemotron-nano-9b-v2":{"metadata":{"displayName":"nvidia-nemotron-nano-9b-v2","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2024-09","lastUpdated":"2025-08-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nvidia-nemotron-nano-9b-v2","displayName":"nvidia-nemotron-nano-9b-v2","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-09"}},"nvidia/rerank-qa-mistral-4b":{"metadata":{"displayName":"rerank-qa-mistral-4b","description":"Reranking model for improving retrieval quality in search and recommendation systems","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"lastUpdated":"2025-01-17","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/rerank-qa-mistral-4b","displayName":"rerank-qa-mistral-4b","description":"Reranking model for improving retrieval quality in search and recommendation systems","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/riva-translate-4b-instruct-v1.1":{"metadata":{"displayName":"riva-translate-4b-instruct-v1_1","description":"Translation model for multilingual conversion, localization, and cross-language workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"lastUpdated":"2025-12-12","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/riva-translate-4b-instruct-v1.1","displayName":"riva-translate-4b-instruct-v1_1","description":"Translation model for multilingual conversion, localization, and cross-language workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/sparsedrive":{"metadata":{"displayName":"sparsedrive","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2025-07-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["video"],"output":["text"]}},"entry":{"id":"nvidia/sparsedrive","displayName":"sparsedrive","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/streampetr":{"metadata":{"displayName":"streampetr","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2025-11-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["video"],"output":["text"]}},"entry":{"id":"nvidia/streampetr","displayName":"streampetr","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/studiovoice":{"metadata":{"displayName":"studiovoice","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2025-06-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/studiovoice","displayName":"studiovoice","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/synthetic-video-detector":{"metadata":{"displayName":"synthetic-video-detector","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","maxOutputTokens":4096,"lastUpdated":"2026-04-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["video"],"output":["text"]}},"entry":{"id":"nvidia/synthetic-video-detector","displayName":"synthetic-video-detector","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"nvidia/usdcode":{"metadata":{"displayName":"usdcode","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"lastUpdated":"2026-01-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/usdcode","displayName":"usdcode","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/usdvalidate":{"metadata":{"displayName":"usdvalidate","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","maxOutputTokens":4096,"lastUpdated":"2025-01-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/usdvalidate","displayName":"usdvalidate","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-oss-120b":{"metadata":{"displayName":"GPT-OSS-120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"knowledgeCutoff":"2025-08","structuredOutput":true,"lastUpdated":"2025-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-120b","displayName":"GPT-OSS-120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-08"}},"openai/gpt-oss-20b":{"metadata":{"displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-20b","displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"openai/whisper-large-v3":{"metadata":{"displayName":"Whisper Large v3","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","maxOutputTokens":4096,"knowledgeCutoff":"2023-09","lastUpdated":"2025-09-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"openai/whisper-large-v3","displayName":"Whisper Large v3","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"knowledgeCutoff":"2023-09"}},"poolside/laguna-xs-2.1":{"metadata":{"displayName":"Laguna XS 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"structuredOutput":false,"lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"poolside/laguna-xs-2.1","displayName":"Laguna XS 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen-image":{"metadata":{"displayName":"Qwen Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","structuredOutput":false,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["image"]}},"entry":{"id":"qwen/qwen-image","displayName":"Qwen Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"qwen/qwen-image-edit":{"metadata":{"displayName":"Qwen Image Edit","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","structuredOutput":false,"lastUpdated":"2025-08-19","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["image"]}},"entry":{"id":"qwen/qwen-image-edit","displayName":"Qwen Image Edit","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"qwen/qwen2.5-coder-32b-instruct":{"metadata":{"displayName":"Qwen2.5 Coder 32b Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"structuredOutput":true,"lastUpdated":"2024-11-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen2.5-coder-32b-instruct","displayName":"Qwen2.5 Coder 32b Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"qwen/qwen3-coder-480b-a35b-instruct":{"metadata":{"displayName":"Qwen3 Coder 480B A35B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":66536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-coder-480b-a35b-instruct","displayName":"Qwen3 Coder 480B A35B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen/qwen3-next-80b-a3b-instruct":{"metadata":{"displayName":"Qwen3-Next-80B-A3B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"knowledgeCutoff":"2024-12","lastUpdated":"2025-09-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-next-80b-a3b-instruct","displayName":"Qwen3-Next-80B-A3B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-12"}},"qwen/qwen3.5-122b-a10b":{"metadata":{"displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-122b-a10b","displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen3.5-397b-a17b":{"metadata":{"displayName":"Qwen3.5-397B-A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":8192,"knowledgeCutoff":"2026-01","structuredOutput":true,"lastUpdated":"2026-02-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-397b-a17b","displayName":"Qwen3.5-397B-A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2026-01"}},"sarvamai/sarvam-m":{"metadata":{"displayName":"sarvam-m","description":"Efficient Indian-language reasoning model for chat, coding, and multilingual work","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2025-07-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"sarvamai/sarvam-m","displayName":"sarvam-m","description":"Efficient Indian-language reasoning model for chat, coding, and multilingual work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"stepfun-ai/step-3.5-flash":{"metadata":{"displayName":"Step 3.5 Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":16384,"lastUpdated":"2026-02-02","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"stepfun-ai/step-3.5-flash","displayName":"Step 3.5 Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000}},"stepfun-ai/step-3.7-flash":{"metadata":{"displayName":"Step 3.7 Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":16384,"lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"stepfun-ai/step-3.7-flash","displayName":"Step 3.7 Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh","max"],"contextWindow":256000,"defaultContextWindow":256000}},"thinkingmachines/inkling":{"metadata":{"displayName":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":16384,"lastUpdated":"2026-07-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio"],"output":["text"]}},"entry":{"id":"thinkingmachines/inkling","displayName":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}},"upstage/solar-10.7b-instruct":{"metadata":{"displayName":"solar-10.7b-instruct","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2025-04-10","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"upstage/solar-10.7b-instruct","displayName":"solar-10.7b-instruct","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"z-ai/glm-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"z-ai/glm-5.3-flash":{"metadata":{"displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"z-ai/glm-5.3-flash","displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}}}},"tencent-tokenhub":{"baseUrl":"https://tokenhub.tencentmaas.com/v1","label":"Tencent TokenHub","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["hy3","hy3-preview","hy4-preview"],"models":{"hy3":{"metadata":{"displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":256000,"inputLimit":192000,"maxOutputTokens":128000,"lastUpdated":"2026-07-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hy3","displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high"],"contextWindow":256000,"inputLimit":192000,"defaultContextWindow":256000,"defaultInputLimit":192000}},"hy3-preview":{"metadata":{"displayName":"Hy3 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":64000,"lastUpdated":"2026-04-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hy3-preview","displayName":"Hy3 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000}},"hy4-preview":{"metadata":{"displayName":"Hy4 preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":64000,"lastUpdated":"2026-08-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hy4-preview","displayName":"Hy4 preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high"],"contextWindow":1024000,"defaultContextWindow":1024000}}}},"stepfun":{"baseUrl":"https://api.stepfun.com/v1","label":"StepFun (China)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["step-3.7-flash","step-3.5-flash-2603","step-3.5-flash","step-1-32k","step-2-16k"],"models":{"step-1-32k":{"metadata":{"displayName":"Step 1 (32K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":32768,"inputLimit":32768,"maxOutputTokens":32768,"knowledgeCutoff":"2024-06","lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-1-32k","displayName":"Step 1 (32K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"inputLimit":32768,"defaultContextWindow":32768,"defaultInputLimit":32768,"knowledgeCutoff":"2024-06"}},"step-2-16k":{"metadata":{"displayName":"Step 2 (16K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":16384,"inputLimit":16384,"maxOutputTokens":8192,"knowledgeCutoff":"2024-06","lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-2-16k","displayName":"Step 2 (16K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16384,"inputLimit":16384,"defaultContextWindow":16384,"defaultInputLimit":16384,"knowledgeCutoff":"2024-06"}},"step-3.5-flash":{"metadata":{"displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-06-15","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-3.5-flash","displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2025-01"}},"step-3.5-flash-2603":{"metadata":{"displayName":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-04-02","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-3.5-flash-2603","displayName":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2025-01"}},"step-3.7-flash":{"metadata":{"displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2026-03-01","lastUpdated":"2026-06-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"step-3.7-flash","displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2026-03-01"}},"step-tts-2":{"metadata":{"displayName":"Step TTS 2","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"step-tts-2","displayName":"Step TTS 2","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"stepaudio-2.5-asr":{"metadata":{"displayName":"StepAudio 2.5 ASR","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"stepaudio-2.5-asr","displayName":"StepAudio 2.5 ASR","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"stepaudio-2.5-tts":{"metadata":{"displayName":"StepAudio 2.5 TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"stepaudio-2.5-tts","displayName":"StepAudio 2.5 TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}}}},"stepfun-step-plan":{"baseUrl":"https://api.stepfun.com/step_plan/v1","label":"StepFun Step Plan (China)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["step-3.7-flash","step-3.5-flash-2603","step-3.5-flash","step-router-v1"],"models":{"step-3.5-flash":{"metadata":{"displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-3.5-flash","displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2025-01"}},"step-3.5-flash-2603":{"metadata":{"displayName":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-04-02","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-3.5-flash-2603","displayName":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2025-01"}},"step-3.7-flash":{"metadata":{"displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2026-03-01","lastUpdated":"2026-05-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"step-3.7-flash","displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2026-03-01"}},"step-router-v1":{"metadata":{"displayName":"Step Router v1","description":"StepFun routing model that dispatches requests to the appropriate Step model.","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-05-29","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-router-v1","displayName":"Step Router v1","description":"StepFun routing model that dispatches requests to the appropriate Step model.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2025-01"}}}},"stepfun-ai-step-plan":{"baseUrl":"https://api.stepfun.ai/step_plan/v1","label":"StepFun Step Plan (Global)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["step-3.7-flash","step-3.5-flash-2603","step-3.5-flash"],"models":{"step-3.5-flash":{"metadata":{"displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-3.5-flash","displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2025-01"}},"step-3.5-flash-2603":{"metadata":{"displayName":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-04-02","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-3.5-flash-2603","displayName":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2025-01"}},"step-3.7-flash":{"metadata":{"displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2026-03-01","lastUpdated":"2026-05-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"step-3.7-flash","displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2026-03-01"}}}},"stepfun-ai":{"baseUrl":"https://api.stepfun.ai/v1","label":"StepFun (Global)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["step-3.7-flash","step-3.5-flash-2603","step-3.5-flash"],"models":{"step-1-32k":{"metadata":{"displayName":"Step 1 (32K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":32768,"inputLimit":32768,"maxOutputTokens":32768,"knowledgeCutoff":"2024-06","lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-1-32k","displayName":"Step 1 (32K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"inputLimit":32768,"defaultContextWindow":32768,"defaultInputLimit":32768,"knowledgeCutoff":"2024-06"}},"step-2-16k":{"metadata":{"displayName":"Step 2 (16K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":16384,"inputLimit":16384,"maxOutputTokens":8192,"knowledgeCutoff":"2024-06","lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-2-16k","displayName":"Step 2 (16K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16384,"inputLimit":16384,"defaultContextWindow":16384,"defaultInputLimit":16384,"knowledgeCutoff":"2024-06"}},"step-3.5-flash":{"metadata":{"displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-06-15","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-3.5-flash","displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2025-01"}},"step-3.5-flash-2603":{"metadata":{"displayName":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-04-02","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-3.5-flash-2603","displayName":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2025-01"}},"step-3.7-flash":{"metadata":{"displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2026-03-01","lastUpdated":"2026-06-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"step-3.7-flash","displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2026-03-01"}},"step-tts-2":{"metadata":{"displayName":"Step TTS 2","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"step-tts-2","displayName":"Step TTS 2","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"stepaudio-2.5-asr":{"metadata":{"displayName":"StepAudio 2.5 ASR","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"stepaudio-2.5-asr","displayName":"StepAudio 2.5 ASR","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"stepaudio-2.5-tts":{"metadata":{"displayName":"StepAudio 2.5 TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"stepaudio-2.5-tts","displayName":"StepAudio 2.5 TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}}}},"volcengine-ark":{"baseUrl":"https://ark.cn-beijing.volces.com/api/v3","label":"Volcengine Ark (China)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":false,"modelDiscovery":{"kind":"fallback","reason":"Ark model discovery is a control-plane API that requires AK/SK signing; inference API keys cannot call it"},"fallbackModels":["doubao-seed-2-0-pro-260215"],"models":{"doubao-seed-2-0-pro-260215":{"metadata":{"displayName":"Doubao Seed 2.0 Pro","lifecycle":"active","capabilities":{"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"],"toggle":true,"offBehavior":"volcengine-thinking-disabled"}},"entry":{"id":"doubao-seed-2-0-pro-260215","displayName":"Doubao Seed 2.0 Pro","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","minimal","low","medium","high"]}}}},"deepinfra":{"baseUrl":"https://api.deepinfra.com/v1/openai","label":"Deep Infra","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol","path":"/v1/models"},"fallbackModels":["moonshotai/Kimi-K2.7-Code","moonshotai/Kimi-K2.6","ByteDance/Seed-2.0-code","ByteDance/Seed-2.0-mini","ByteDance/Seed-2.0-pro","deepseek-ai/DeepSeek-R1-0528","deepseek-ai/DeepSeek-V3","deepseek-ai/DeepSeek-V3-0324","deepseek-ai/DeepSeek-V3.1","deepseek-ai/DeepSeek-V3.2","deepseek-ai/DeepSeek-V4-Flash","deepseek-ai/DeepSeek-V4-Flash-0731","deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","deepseek-ai/DeepSeek-V4-Pro","deepseek-ai/DeepSeek-V4-Pro-0813","deepseek-ai/DeepSeek-V4.1-Flash","google/gemma-3-12b-it","google/gemma-3-27b-it","google/gemma-3-4b-it","google/gemma-4-26B-A4B-it","google/gemma-4-31B-it","google/gemma-4-E4B-it","meta-llama/Llama-3.3-70B-Instruct-Turbo","meta-llama/Llama-4-Scout-17B-16E-Instruct","MiniMaxAI/MiniMax-M3","moonshotai/Kimi-K3","nvidia/Nemotron-3-Nano-30B-A3B","openai/gpt-oss-120b","openai/gpt-oss-20b","Qwen/Qwen3-235B-A22B-Instruct-2507","Qwen/Qwen3-30B-A3B","Qwen/Qwen3-32B","Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","Qwen/Qwen3-Max","Qwen/Qwen3-Next-80B-A3B-Instruct","Qwen/Qwen3-VL-235B-A22B-Instruct","Qwen/Qwen3.5-122B-A10B","Qwen/Qwen3.5-27B","Qwen/Qwen3.5-35B-A3B","Qwen/Qwen3.5-397B-A17B","Qwen/Qwen3.5-9B","Qwen/Qwen3.6-27B","Qwen/Qwen3.6-35B-A3B","Qwen/Qwen3.7-Max","Qwen/Qwen3.8-2.4T-A95B","Qwen/Qwen3.8-27B","Qwen/Qwen3.8-Flash","Qwen/Qwen3.8-Max","stepfun-ai/Step-3.7-Flash","tencent/Hy3","thinkingmachines/Inkling","thinkingmachines/Inkling-Small","XiaomiMiMo/MiMo-V2.5","XiaomiMiMo/MiMo-V2.5-Pro","zai-org/GLM-4.6","zai-org/GLM-4.7","zai-org/GLM-5.1","zai-org/GLM-5.2","zai-org/GLM-5.3","zai-org/GLM-5.3-Flash"],"models":{"ByteDance/Seed-2.0-code":{"metadata":{"displayName":"Seed 2.0 Code","description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","lifecycle":"active","contextWindow":256000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-02-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"ByteDance/Seed-2.0-code","displayName":"Seed 2.0 Code","description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000}},"ByteDance/Seed-2.0-mini":{"metadata":{"displayName":"Seed 2.0 Mini","description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"structuredOutput":true,"lastUpdated":"2026-02-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"ByteDance/Seed-2.0-mini","displayName":"Seed 2.0 Mini","description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"ByteDance/Seed-2.0-pro":{"metadata":{"displayName":"Seed 2.0 Pro","description":"Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-02-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"ByteDance/Seed-2.0-pro","displayName":"Seed 2.0 Pro","description":"Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"deepseek-ai/DeepSeek-R1-0528":{"metadata":{"displayName":"DeepSeek-R1-0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","lifecycle":"active","contextWindow":163840,"maxOutputTokens":64000,"knowledgeCutoff":"2024-07","structuredOutput":true,"lastUpdated":"2025-05-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-R1-0528","displayName":"DeepSeek-R1-0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2024-07"}},"deepseek-ai/DeepSeek-V3":{"metadata":{"displayName":"DeepSeek-V3","description":"Open DeepSeek MoE chat model for coding, math, and general reasoning","lifecycle":"active","contextWindow":163840,"maxOutputTokens":8192,"structuredOutput":true,"lastUpdated":"2024-12-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3","displayName":"DeepSeek-V3","description":"Open DeepSeek MoE chat model for coding, math, and general reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840}},"deepseek-ai/DeepSeek-V3-0324":{"metadata":{"displayName":"DeepSeek V3 0324","description":"March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding","lifecycle":"active","contextWindow":163840,"maxOutputTokens":163840,"structuredOutput":true,"lastUpdated":"2025-03-24","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3-0324","displayName":"DeepSeek V3 0324","description":"March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840}},"deepseek-ai/DeepSeek-V3.1":{"metadata":{"displayName":"DeepSeek-V3.1","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes","lifecycle":"active","contextWindow":163840,"maxOutputTokens":8192,"structuredOutput":true,"lastUpdated":"2025-08-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3.1","displayName":"DeepSeek-V3.1","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840}},"deepseek-ai/DeepSeek-V3.2":{"metadata":{"displayName":"DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":64000,"knowledgeCutoff":"2024-12","structuredOutput":true,"lastUpdated":"2025-12-02","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3.2","displayName":"DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2024-12"}},"deepseek-ai/DeepSeek-V4-Flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":16384,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Flash","displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"deepseek-ai/DeepSeek-V4-Flash-0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp":{"metadata":{"displayName":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","high","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","displayName":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"deepseek-ai/DeepSeek-V4-Pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":16384,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Pro","displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"deepseek-ai/DeepSeek-V4-Pro-0813":{"metadata":{"displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"deepseek-ai/DeepSeek-V4.1-Flash":{"metadata":{"displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","high","xhigh","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4.1-Flash","displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","high","xhigh","max"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"google/gemma-3-12b-it":{"metadata":{"displayName":"Gemma 3 12B IT","description":"Open multimodal Gemma instruction model for multilingual text generation and image understanding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2024-08","structuredOutput":true,"lastUpdated":"2025-03-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3-12b-it","displayName":"Gemma 3 12B IT","description":"Open multimodal Gemma instruction model for multilingual text generation and image understanding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-08"}},"google/gemma-3-27b-it":{"metadata":{"displayName":"Gemma 3 27B IT","description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2024-08","structuredOutput":true,"lastUpdated":"2025-03-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3-27b-it","displayName":"Gemma 3 27B IT","description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-08"}},"google/gemma-3-4b-it":{"metadata":{"displayName":"Gemma 3 4B IT","description":"Open multimodal Gemma instruction model for efficient text generation and image understanding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2024-08","structuredOutput":true,"lastUpdated":"2025-03-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3-4b-it","displayName":"Gemma 3 4B IT","description":"Open multimodal Gemma instruction model for efficient text generation and image understanding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-08"}},"google/gemma-4-26B-A4B-it":{"metadata":{"displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-4-26B-A4B-it","displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"google/gemma-4-31B-it":{"metadata":{"displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"google/gemma-4-31B-it","displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"google/gemma-4-E4B-it":{"metadata":{"displayName":"Gemma 4 E4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio"],"output":["text"]}},"entry":{"id":"google/gemma-4-E4B-it","displayName":"Gemma 4 E4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"meta-llama/Llama-3.3-70B-Instruct-Turbo":{"metadata":{"displayName":"Llama 3.3 70B Turbo","description":"Compact Llama instruction model for fast chat and local deployment","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2024-12-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","displayName":"Llama 3.3 70B Turbo","description":"Compact Llama instruction model for fast chat and local deployment","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8":{"metadata":{"displayName":"Llama 4 Maverick 17B FP8","description":"Open multimodal Llama model for strong reasoning and fast responses","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-04-05","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","displayName":"Llama 4 Maverick 17B FP8","description":"Open multimodal Llama model for strong reasoning and fast responses","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}},"meta-llama/Llama-4-Scout-17B-16E-Instruct":{"metadata":{"displayName":"Llama 4 Scout 17B","description":"Open multimodal Llama model for long-context analysis and efficient agents","lifecycle":"active","contextWindow":327680,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-04-05","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","displayName":"Llama 4 Scout 17B","description":"Open multimodal Llama model for long-context analysis and efficient agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":327680,"defaultContextWindow":327680}},"MiniMaxAI/MiniMax-M2.5":{"metadata":{"displayName":"MiniMax M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"deprecated","contextWindow":196608,"maxOutputTokens":131072,"knowledgeCutoff":"2025-06","lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M2.5","displayName":"MiniMax M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":196608,"defaultContextWindow":196608,"knowledgeCutoff":"2025-06"}},"MiniMaxAI/MiniMax-M2.7":{"metadata":{"displayName":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","lifecycle":"deprecated","contextWindow":196608,"maxOutputTokens":131072,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M2.7","displayName":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":196608,"defaultContextWindow":196608}},"MiniMaxAI/MiniMax-M3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","lifecycle":"active","contextWindow":524288,"maxOutputTokens":512000,"structuredOutput":true,"lastUpdated":"2026-06-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M3","displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":524288,"defaultContextWindow":524288}},"moonshotai/Kimi-K2.5":{"metadata":{"displayName":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2.5","displayName":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/Kimi-K2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2.6","displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-04"}},"moonshotai/Kimi-K2.7-Code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2.7-Code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/Kimi-K3":{"metadata":{"displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K3","displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"nvidia/Llama-3.3-Nemotron-Super-49B-v1.5":{"metadata":{"displayName":"Llama 3.3 Nemotron Super 49B v1.5","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"deprecated","contextWindow":131072,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2025-07-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/Llama-3.3-Nemotron-Super-49B-v1.5","displayName":"Llama 3.3 Nemotron Super 49B v1.5","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"nvidia/Nemotron-3-Nano-30B-A3B":{"metadata":{"displayName":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"lastUpdated":"2025-12-15","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/Nemotron-3-Nano-30B-A3B","displayName":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning":{"metadata":{"displayName":"Nemotron 3 Nano Omni 30B A3B Reasoning","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning","displayName":"Nemotron 3 Nano Omni 30B A3B Reasoning","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"openai/gpt-oss-120b":{"metadata":{"displayName":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-120b","displayName":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"openai/gpt-oss-20b":{"metadata":{"displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-20b","displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"Qwen/Qwen3-235B-A22B-Instruct-2507":{"metadata":{"displayName":"Qwen3 235B-A22B Instruct 2507","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-07-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","displayName":"Qwen3 235B-A22B Instruct 2507","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3-30B-A3B":{"metadata":{"displayName":"Qwen3 30B A3B","description":"Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning","lifecycle":"active","contextWindow":40960,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-04-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-30B-A3B","displayName":"Qwen3 30B A3B","description":"Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":40960,"defaultContextWindow":40960}},"Qwen/Qwen3-32B":{"metadata":{"displayName":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","lifecycle":"active","contextWindow":40960,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-32B","displayName":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":40960,"defaultContextWindow":40960,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo":{"metadata":{"displayName":"Qwen3 Coder 480B A35B Instruct Turbo","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":66536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","displayName":"Qwen3 Coder 480B A35B Instruct Turbo","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-Max":{"metadata":{"displayName":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-09-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Max","displayName":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-Next-80B-A3B-Instruct":{"metadata":{"displayName":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Next-80B-A3B-Instruct","displayName":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-VL-235B-A22B-Instruct":{"metadata":{"displayName":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-09-23","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-VL-235B-A22B-Instruct","displayName":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-03-31"}},"Qwen/Qwen3.5-122B-A10B":{"metadata":{"displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-122B-A10B","displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.5-27B":{"metadata":{"displayName":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-27B","displayName":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.5-35B-A3B":{"metadata":{"displayName":"Qwen 3.5 35B A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":81920,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-35B-A3B","displayName":"Qwen 3.5 35B A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"Qwen/Qwen3.5-397B-A17B":{"metadata":{"displayName":"Qwen 3.5 397B A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":81920,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-397B-A17B","displayName":"Qwen 3.5 397B A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"Qwen/Qwen3.5-9B":{"metadata":{"displayName":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-9B","displayName":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.6-27B":{"metadata":{"displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.6-27B","displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.6-35B-A3B":{"metadata":{"displayName":"Qwen3.6 35B A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":81920,"structuredOutput":true,"lastUpdated":"2026-04-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.6-35B-A3B","displayName":"Qwen3.6 35B A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.7-Max":{"metadata":{"displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.7-Max","displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"Qwen/Qwen3.8-2.4T-A95B":{"metadata":{"displayName":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.8-2.4T-A95B","displayName":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","xhigh"],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.8-27B":{"metadata":{"displayName":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.8-27B","displayName":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.8-Flash":{"metadata":{"displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.8-Flash","displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"Qwen/Qwen3.8-Max":{"metadata":{"displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-03","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.8-Max","displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"stepfun-ai/Step-3.7-Flash":{"metadata":{"displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","lifecycle":"active","contextWindow":262144,"maxOutputTokens":256000,"knowledgeCutoff":"2026-03-01","lastUpdated":"2026-05-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"stepfun-ai/Step-3.7-Flash","displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2026-03-01"}},"tencent/Hy3":{"metadata":{"displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":262144,"inputLimit":192000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-07-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/Hy3","displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"inputLimit":192000,"defaultContextWindow":262144,"defaultInputLimit":192000}},"thinkingmachines/Inkling":{"metadata":{"displayName":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","lifecycle":"active","contextWindow":524288,"maxOutputTokens":1048576,"lastUpdated":"2026-07-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio"],"output":["text"]}},"entry":{"id":"thinkingmachines/Inkling","displayName":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":524288,"defaultContextWindow":524288}},"thinkingmachines/Inkling-Small":{"metadata":{"displayName":"Inkling Small","description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","lifecycle":"active","contextWindow":524288,"maxOutputTokens":1048576,"structuredOutput":true,"lastUpdated":"2026-07-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio"],"output":["text"]}},"entry":{"id":"thinkingmachines/Inkling-Small","displayName":"Inkling Small","description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":524288,"defaultContextWindow":524288}},"XiaomiMiMo/MiMo-V2.5":{"metadata":{"displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"knowledgeCutoff":"2024-12","structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]}},"entry":{"id":"XiaomiMiMo/MiMo-V2.5","displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-12"}},"XiaomiMiMo/MiMo-V2.5-Pro":{"metadata":{"displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":16384,"knowledgeCutoff":"2024-12","structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","audio"],"output":["text"]}},"entry":{"id":"XiaomiMiMo/MiMo-V2.5-Pro","displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"zai-org/GLM-4.6":{"metadata":{"displayName":"GLM-4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-09-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-4.6","displayName":"GLM-4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752,"knowledgeCutoff":"2025-04"}},"zai-org/GLM-4.7":{"metadata":{"displayName":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-12-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-4.7","displayName":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752,"knowledgeCutoff":"2025-04"}},"zai-org/GLM-4.7-Flash":{"metadata":{"displayName":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"deprecated","contextWindow":202752,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-4.7-Flash","displayName":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752,"knowledgeCutoff":"2025-04"}},"zai-org/GLM-5":{"metadata":{"displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"deprecated","contextWindow":202752,"maxOutputTokens":16384,"knowledgeCutoff":"2025-12","structuredOutput":true,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5","displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752,"knowledgeCutoff":"2025-12"}},"zai-org/GLM-5.1":{"metadata":{"displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.1","displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752,"knowledgeCutoff":"2025-04"}},"zai-org/GLM-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"zai-org/GLM-5.3":{"metadata":{"displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.3","displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"zai-org/GLM-5.3-Flash":{"metadata":{"displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.3-Flash","displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}}}},"groq":{"baseUrl":"https://api.groq.com/openai/v1","label":"Groq","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["llama-3.3-70b-versatile","llama-3.1-8b-instant","openai/gpt-oss-120b","openai/gpt-oss-20b","openai/gpt-oss-safeguard-20b","qwen/qwen3.6-27b","qwen/qwen3.8-27b"],"models":{"allam-2-7b":{"metadata":{"displayName":"ALLaM-2-7b","description":"ALLaM-2-7b instruction tuned model by SDAIA","lifecycle":"active","contextWindow":4096,"maxOutputTokens":4096,"lastUpdated":"2025-01-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"allam-2-7b","displayName":"ALLaM-2-7b","description":"ALLaM-2-7b instruction tuned model by SDAIA","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":4096,"defaultContextWindow":4096}},"canopylabs/orpheus-arabic-saudi":{"metadata":{"displayName":"Canopy Labs Orpheus Arabic Saudi","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"beta","contextWindow":4000,"maxOutputTokens":50000,"lastUpdated":"2025-12-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"canopylabs/orpheus-arabic-saudi","displayName":"Canopy Labs Orpheus Arabic Saudi","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":4000,"defaultContextWindow":4000}},"canopylabs/orpheus-v1-english":{"metadata":{"displayName":"Canopy Labs Orpheus V1 English","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"beta","contextWindow":4000,"maxOutputTokens":50000,"lastUpdated":"2025-12-19","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"canopylabs/orpheus-v1-english","displayName":"Canopy Labs Orpheus V1 English","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":4000,"defaultContextWindow":4000}},"groq/compound":{"metadata":{"displayName":"Compound","description":"General-purpose chat model for instruction following, writing, and analysis","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"lastUpdated":"2025-09-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"groq/compound","displayName":"Compound","description":"General-purpose chat model for instruction following, writing, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"groq/compound-mini":{"metadata":{"displayName":"Compound Mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"lastUpdated":"2025-09-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"groq/compound-mini","displayName":"Compound Mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"llama-3.1-8b-instant":{"metadata":{"displayName":"Llama 3.1 8B","description":"Compact Llama instruction model for fast chat and local deployment","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2023-12","lastUpdated":"2024-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"llama-3.1-8b-instant","displayName":"Llama 3.1 8B","description":"Compact Llama instruction model for fast chat and local deployment","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12"}},"llama-3.3-70b-versatile":{"metadata":{"displayName":"Llama 3.3 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2023-12","lastUpdated":"2024-12-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"llama-3.3-70b-versatile","displayName":"Llama 3.3 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12"}},"meta-llama/llama-prompt-guard-2-22m":{"metadata":{"displayName":"Llama Prompt Guard 2 22M","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"beta","contextWindow":512,"maxOutputTokens":512,"lastUpdated":"2025-05-29","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/llama-prompt-guard-2-22m","displayName":"Llama Prompt Guard 2 22M","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":512,"defaultContextWindow":512}},"meta-llama/llama-prompt-guard-2-86m":{"metadata":{"displayName":"Prompt Guard 2 86M","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"beta","contextWindow":512,"maxOutputTokens":512,"lastUpdated":"2025-05-29","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/llama-prompt-guard-2-86m","displayName":"Prompt Guard 2 86M","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":512,"defaultContextWindow":512}},"openai/gpt-oss-120b":{"metadata":{"displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2025-10-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-120b","displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"openai/gpt-oss-20b":{"metadata":{"displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2025-09-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-20b","displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"openai/gpt-oss-safeguard-20b":{"metadata":{"displayName":"Safety GPT OSS 20B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"beta","contextWindow":131072,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-06-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-safeguard-20b","displayName":"Safety GPT OSS 20B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"qwen/qwen3.6-27b":{"metadata":{"displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","default"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen3.6-27b","displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"],"contextWindow":131072,"defaultContextWindow":131072}},"qwen/qwen3.8-27b":{"metadata":{"displayName":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","lifecycle":"active","contextWindow":131042,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","default","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen3.8-27b","displayName":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":131042,"defaultContextWindow":131042}},"whisper-large-v3":{"metadata":{"displayName":"Whisper","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2025-09-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"whisper-large-v3","displayName":"Whisper","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"whisper-large-v3-turbo":{"metadata":{"displayName":"Whisper Large V3 Turbo","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2024-10-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"whisper-large-v3-turbo","displayName":"Whisper Large V3 Turbo","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"qwen/qwen3-32b":{"metadata":{"thinkingOptions":{"efforts":[]}},"entry":{"id":"qwen/qwen3-32b","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}}}},"openrouter":{"baseUrl":"https://openrouter.ai/api/v1","label":"OpenRouter","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["anthropic/claude-sonnet-5","openai/gpt-5.6-sol","x-ai/grok-4.5","deepseek/deepseek-v4-pro","~anthropic/claude-fable-latest","~anthropic/claude-haiku-latest","~anthropic/claude-opus-latest","~anthropic/claude-sonnet-latest","~deepseek/deepseek-flash-latest","~deepseek/deepseek-pro-latest","~deepseek/deepseek-v4-flash-latest","~google/gemini-flash-latest","~google/gemini-pro-latest","~moonshotai/kimi-latest","~openai/gpt-astra-latest","~openai/gpt-luna-latest","~openai/gpt-mini-latest","~openai/gpt-sol-latest","~openai/gpt-terra-latest","~x-ai/grok-latest","~z-ai/glm-flash-latest","~z-ai/glm-latest","aion-labs/aion-2.0","aion-labs/aion-3.0","aion-labs/aion-3.0-mini","amazon/nova-2-lite-v1","amazon/nova-lite-v1","amazon/nova-micro-v1","amazon/nova-premier-v1","amazon/nova-pro-v1","anthropic/claude-3-haiku","anthropic/claude-fable-5","anthropic/claude-fable-5.1","anthropic/claude-haiku-4.5","anthropic/claude-opus-4","anthropic/claude-opus-4.1","anthropic/claude-opus-4.5","anthropic/claude-opus-4.6","anthropic/claude-opus-4.7","anthropic/claude-opus-4.8","anthropic/claude-opus-5","anthropic/claude-sonnet-4","anthropic/claude-sonnet-4.5","anthropic/claude-sonnet-4.6","arcee-ai/trinity-large-thinking","bytedance-seed/seed-1.6","bytedance-seed/seed-1.6-flash","bytedance-seed/seed-2-1-turbo","bytedance-seed/seed-2.0-code","bytedance-seed/seed-2.0-lite","bytedance-seed/seed-2.0-mini","cohere/command-r-08-2024","cohere/command-r-plus-08-2024","cohere/north-mini-code:free","deepseek/deepseek-chat","deepseek/deepseek-chat-v3-0324","deepseek/deepseek-chat-v3.1","deepseek/deepseek-r1","deepseek/deepseek-r1-0528","deepseek/deepseek-v3.1-terminus","deepseek/deepseek-v3.2","deepseek/deepseek-v3.2-exp","deepseek/deepseek-v4-flash","deepseek/deepseek-v4-flash-0731","deepseek/deepseek-v4-flash-vision-exp","deepseek/deepseek-v4-pro-0813","deepseek/deepseek-v4.1-flash","dots-studio/dots-3-note-preview:free","google/gemini-2.5-flash","google/gemini-2.5-flash-lite","google/gemini-2.5-pro","google/gemini-2.5-pro-preview","google/gemini-3-flash-preview","google/gemini-3-pro-image","google/gemini-3.1-flash-lite","google/gemini-3.1-flash-lite-preview","google/gemini-3.1-pro-preview","google/gemini-3.1-pro-preview-customtools","google/gemini-3.5-flash","google/gemini-3.5-flash-lite","google/gemini-3.6-flash","google/gemini-3.7-flash","google/gemini-3.8-flash","google/gemma-3-12b-it","google/gemma-3-27b-it","google/gemma-4-26b-a4b-it","google/gemma-4-26b-a4b-it:free","google/gemma-4-31b-it","google/gemma-4-31b-it:free","ibm-granite/granite-4.2-8b","inception/mercury-2","inception/mercury-2.5","inclusionai/ling-3.0-flash","inclusionai/ling-3.0-flash-fin","inclusionai/ling-3.0-flash-fin:free","inclusionai/ling-3.0-flash-sante:free","inclusionai/ling-3.0-flash-vl","inclusionai/ling-3.0-flash-vl:free","kwaipilot/kat-coder-pro-v2","kwaipilot/kat-coder-pro-v2.5","liquid/lfm-2.5-2.6b:free","meituan/longcat-2.0","meta-llama/llama-3.1-70b-instruct","meta-llama/llama-3.1-8b-instruct","meta-llama/llama-3.3-70b-instruct","meta-llama/llama-4-maverick","meta-llama/llama-4-scout","meta/muse-glimmer-30b","meta/muse-spark-1.1","meta/muse-spark-1.2","meta/muse-spark-1.2-contributor","meta/muse-spark-1.3","meta/muse-spark-1.3-contributor","minimax/minimax-m1","minimax/minimax-m2","minimax/minimax-m2.1","minimax/minimax-m2.5","minimax/minimax-m2.7","minimax/minimax-m3","mistralai/codestral-2508","mistralai/devstral-2512","mistralai/ministral-14b-2512","mistralai/ministral-3b-2512","mistralai/ministral-8b-2512","mistralai/mistral-large","mistralai/mistral-large-2407","mistralai/mistral-large-2512","mistralai/mistral-medium-3","mistralai/mistral-medium-3-5","mistralai/mistral-medium-3.1","mistralai/mistral-nemo","mistralai/mistral-saba","mistralai/mistral-small-2603","mistralai/mistral-small-3.2-24b-instruct","mistralai/mixtral-8x22b-instruct","mistralai/voxtral-small-24b-2507","moonshotai/kimi-k2","moonshotai/kimi-k2-0905","moonshotai/kimi-k2-thinking","moonshotai/kimi-k2.5","moonshotai/kimi-k2.6","moonshotai/kimi-k2.7-code","moonshotai/kimi-k3","nex-agi/nex-n2.5-mini:free","nex-agi/nex-n2.5-pro:free","nvidia/nemotron-3-nano-30b-a3b","nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","nvidia/nemotron-3-super-120b-a12b","nvidia/nemotron-3-super-120b-a12b:free","nvidia/nemotron-3-ultra-550b-a55b","nvidia/nemotron-3-ultra-550b-a55b:free","nvidia/nemotron-3.5-lightning","nvidia/nemotron-3.5-lightning:free","openai/gpt-3.5-turbo","openai/gpt-3.5-turbo-0613","openai/gpt-3.5-turbo-16k","openai/gpt-4","openai/gpt-4-turbo","openai/gpt-4.1","openai/gpt-4.1-mini","openai/gpt-4.1-nano","openai/gpt-4o","openai/gpt-4o-2024-05-13","openai/gpt-4o-2024-08-06","openai/gpt-4o-2024-11-20","openai/gpt-4o-mini","openai/gpt-4o-mini-2024-07-18","openai/gpt-5","openai/gpt-5-mini","openai/gpt-5-nano","openai/gpt-5-pro","openai/gpt-5.1","openai/gpt-5.1-codex","openai/gpt-5.1-codex-max","openai/gpt-5.1-codex-mini","openai/gpt-5.2","openai/gpt-5.2-chat","openai/gpt-5.2-codex","openai/gpt-5.2-pro","openai/gpt-5.3-codex","openai/gpt-5.4","openai/gpt-5.4-mini","openai/gpt-5.4-nano","openai/gpt-5.4-pro","openai/gpt-5.5","openai/gpt-5.5-pro","openai/gpt-5.6-luna","openai/gpt-5.6-luna-pro","openai/gpt-5.6-sol-pro","openai/gpt-5.6-terra","openai/gpt-5.6-terra-pro","openai/gpt-6-astra","openai/gpt-6-astra-pro","openai/gpt-audio","openai/gpt-audio-mini","openai/gpt-chat-latest","openai/gpt-oss-120b","openai/gpt-oss-20b","openai/gpt-oss-safeguard-20b","openai/o1","openai/o3","openai/o3-mini","openai/o3-mini-high","openai/o3-pro","openai/o4-mini","openai/o4-mini-high","openrouter/auto","openrouter/free","poolside/laguna-s-2.1","poolside/laguna-s-2.1:free","poolside/laguna-xs-2.1","poolside/laguna-xs-2.1:free","qwen/qwen-2.5-72b-instruct","qwen/qwen-2.5-7b-instruct","qwen/qwen-plus","qwen/qwen-plus-2025-07-28","qwen/qwen3-14b","qwen/qwen3-235b-a22b","qwen/qwen3-235b-a22b-2507","qwen/qwen3-235b-a22b-thinking-2507","qwen/qwen3-30b-a3b","qwen/qwen3-30b-a3b-instruct-2507","qwen/qwen3-30b-a3b-thinking-2507","qwen/qwen3-32b","qwen/qwen3-8b","qwen/qwen3-coder","qwen/qwen3-coder-30b-a3b-instruct","qwen/qwen3-coder-flash","qwen/qwen3-coder-next","qwen/qwen3-coder-plus","qwen/qwen3-max","qwen/qwen3-max-thinking","qwen/qwen3-next-80b-a3b-instruct","qwen/qwen3-next-80b-a3b-thinking","qwen/qwen3-vl-235b-a22b-instruct","qwen/qwen3-vl-235b-a22b-thinking","qwen/qwen3-vl-30b-a3b-instruct","qwen/qwen3-vl-30b-a3b-thinking","qwen/qwen3-vl-32b-instruct","qwen/qwen3-vl-8b-instruct","qwen/qwen3-vl-8b-thinking","qwen/qwen3.5-122b-a10b","qwen/qwen3.5-27b","qwen/qwen3.5-35b-a3b","qwen/qwen3.5-397b-a17b","qwen/qwen3.5-9b","qwen/qwen3.5-flash-02-23","qwen/qwen3.5-plus-02-15","qwen/qwen3.5-plus-20260420","qwen/qwen3.6-27b","qwen/qwen3.6-35b-a3b","qwen/qwen3.6-flash","qwen/qwen3.6-max-preview","qwen/qwen3.6-plus","qwen/qwen3.7-flash","qwen/qwen3.7-max","qwen/qwen3.7-plus","qwen/qwen3.8-2.4t-a95b","qwen/qwen3.8-27b","qwen/qwen3.8-flash","qwen/qwen3.8-max-0902","rekaai/reka-edge","relace/relace-search","sakana/fugu-max","sakana/fugu-ultra","sakana/fugu-ultra-v2","sakana/sakana-namazu","sao10k/l3.1-euryale-70b","stepfun/step-3.5-flash","stepfun/step-3.7-flash","tencent/hy3","tencent/hy3-preview","tencent/hy4-preview","thedrummer/unslopnemo-12b","thinkingmachines/inkling","thinkingmachines/inkling-small","thinkingmachines/inkling-small:free","thinkingmachines/inkling:free","upstage/solar-pro-3","upstage/solar-pro4","x-ai/grok-4.20","x-ai/grok-4.3","x-ai/grok-4.6","x-ai/grok-build-0.1","xiaomi/mimo-v2.5","xiaomi/mimo-v2.5-pro","z-ai/glm-4.5","z-ai/glm-4.5-air","z-ai/glm-4.5v","z-ai/glm-4.6","z-ai/glm-4.6v","z-ai/glm-4.7","z-ai/glm-4.7-flash","z-ai/glm-5","z-ai/glm-5-turbo","z-ai/glm-5.1","z-ai/glm-5.2","z-ai/glm-5.3","z-ai/glm-5.3-flash","z-ai/glm-5v-turbo"],"models":{"~anthropic/claude-fable-latest":{"metadata":{"displayName":"Claude Fable Latest","description":"Claude model for creative writing, analysis, and controlled agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-06-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"~anthropic/claude-fable-latest","displayName":"Claude Fable Latest","description":"Claude model for creative writing, analysis, and controlled agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"~anthropic/claude-haiku-latest":{"metadata":{"displayName":"Claude Haiku Latest","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"~anthropic/claude-haiku-latest","displayName":"Claude Haiku Latest","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}},"~anthropic/claude-opus-latest":{"metadata":{"displayName":"Claude Opus Latest","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"~anthropic/claude-opus-latest","displayName":"Claude Opus Latest","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"~anthropic/claude-sonnet-latest":{"metadata":{"displayName":"Claude Sonnet Latest","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"~anthropic/claude-sonnet-latest","displayName":"Claude Sonnet Latest","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"~deepseek/deepseek-flash-latest":{"metadata":{"displayName":"DeepSeek Flash Latest","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":943718,"structuredOutput":true,"lastUpdated":"2026-09-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"~deepseek/deepseek-flash-latest","displayName":"DeepSeek Flash Latest","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"~deepseek/deepseek-pro-latest":{"metadata":{"displayName":"DeepSeek Pro Latest","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":943718,"structuredOutput":true,"lastUpdated":"2026-09-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"~deepseek/deepseek-pro-latest","displayName":"DeepSeek Pro Latest","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"~deepseek/deepseek-v4-flash-latest":{"metadata":{"displayName":"DeepSeek V4 Flash Latest","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","lifecycle":"active","contextWindow":1310720,"maxOutputTokens":393216,"structuredOutput":true,"lastUpdated":"2026-08-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"~deepseek/deepseek-v4-flash-latest","displayName":"DeepSeek V4 Flash Latest","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1310720,"defaultContextWindow":1310720}},"~google/gemini-flash-latest":{"metadata":{"displayName":"Gemini Flash Latest","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01-01","structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"entry":{"id":"~google/gemini-flash-latest","displayName":"Gemini Flash Latest","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01-01"}},"~google/gemini-pro-latest":{"metadata":{"displayName":"Gemini Pro Latest","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["audio","pdf","image","text","video"],"output":["text"]}},"entry":{"id":"~google/gemini-pro-latest","displayName":"Gemini Pro Latest","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"~moonshotai/kimi-latest":{"metadata":{"displayName":"Kimi Latest","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":943718,"structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"~moonshotai/kimi-latest","displayName":"Kimi Latest","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"~openai/gpt-astra-latest":{"metadata":{"displayName":"GPT Astra Latest","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-09-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"entry":{"id":"~openai/gpt-astra-latest","displayName":"GPT Astra Latest","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1050000,"defaultContextWindow":1050000}},"~openai/gpt-luna-latest":{"metadata":{"displayName":"GPT Luna Latest","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-09-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"entry":{"id":"~openai/gpt-luna-latest","displayName":"GPT Luna Latest","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2026-02-16"}},"~openai/gpt-mini-latest":{"metadata":{"displayName":"GPT Mini Latest","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"entry":{"id":"~openai/gpt-mini-latest","displayName":"GPT Mini Latest","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-08-31"}},"~openai/gpt-sol-latest":{"metadata":{"displayName":"GPT Sol Latest","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-09-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"entry":{"id":"~openai/gpt-sol-latest","displayName":"GPT Sol Latest","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2026-02-16"}},"~openai/gpt-terra-latest":{"metadata":{"displayName":"GPT Terra Latest","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-09-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"entry":{"id":"~openai/gpt-terra-latest","displayName":"GPT Terra Latest","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2026-02-16"}},"~x-ai/grok-latest":{"metadata":{"displayName":"Grok Latest","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":500000,"maxOutputTokens":450000,"structuredOutput":true,"lastUpdated":"2026-07-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"~x-ai/grok-latest","displayName":"Grok Latest","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":500000,"defaultContextWindow":500000}},"~z-ai/glm-flash-latest":{"metadata":{"displayName":"GLM Flash Latest","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":1310720,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"~z-ai/glm-flash-latest","displayName":"GLM Flash Latest","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1310720,"defaultContextWindow":1310720}},"~z-ai/glm-latest":{"metadata":{"displayName":"GLM Latest","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":1310720,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"~z-ai/glm-latest","displayName":"GLM Latest","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1310720,"defaultContextWindow":1310720}},"aion-labs/aion-2.0":{"metadata":{"displayName":"Aion-2.0","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-02-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"aion-labs/aion-2.0","displayName":"Aion-2.0","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"aion-labs/aion-3.0":{"metadata":{"displayName":"Aion-3.0","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-07-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"aion-labs/aion-3.0","displayName":"Aion-3.0","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"aion-labs/aion-3.0-mini":{"metadata":{"displayName":"Aion-3.0-Mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-07-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"aion-labs/aion-3.0-mini","displayName":"Aion-3.0-Mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"aion-labs/aion-rp-llama-3.1-8b":{"metadata":{"displayName":"Aion-RP 1.0 (8B)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":32768,"maxOutputTokens":29491,"knowledgeCutoff":"2023-12-31","structuredOutput":false,"lastUpdated":"2025-02-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"aion-labs/aion-rp-llama-3.1-8b","displayName":"Aion-RP 1.0 (8B)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2023-12-31"}},"amazon/nova-2-lite-v1":{"metadata":{"displayName":"Nova 2 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65535,"structuredOutput":false,"lastUpdated":"2025-12-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"amazon/nova-2-lite-v1","displayName":"Nova 2 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"amazon/nova-lite-v1":{"metadata":{"displayName":"Nova Lite 1.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":300000,"maxOutputTokens":5120,"knowledgeCutoff":"2024-10-31","structuredOutput":false,"lastUpdated":"2024-12-05","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"amazon/nova-lite-v1","displayName":"Nova Lite 1.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":300000,"defaultContextWindow":300000,"knowledgeCutoff":"2024-10-31"}},"amazon/nova-micro-v1":{"metadata":{"displayName":"Nova Micro 1.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":128000,"maxOutputTokens":5120,"knowledgeCutoff":"2024-10-31","structuredOutput":false,"lastUpdated":"2024-12-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"amazon/nova-micro-v1","displayName":"Nova Micro 1.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-10-31"}},"amazon/nova-premier-v1":{"metadata":{"displayName":"Nova Premier 1.0","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":32000,"structuredOutput":false,"lastUpdated":"2025-10-31","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"amazon/nova-premier-v1","displayName":"Nova Premier 1.0","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"amazon/nova-pro-v1":{"metadata":{"displayName":"Nova Pro 1.0","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":300000,"maxOutputTokens":5120,"knowledgeCutoff":"2024-10-31","structuredOutput":false,"lastUpdated":"2024-12-05","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"amazon/nova-pro-v1","displayName":"Nova Pro 1.0","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":300000,"defaultContextWindow":300000,"knowledgeCutoff":"2024-10-31"}},"anthracite-org/magnum-v4-72b":{"metadata":{"displayName":"Magnum v4 72B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","lifecycle":"active","contextWindow":32768,"maxOutputTokens":4096,"knowledgeCutoff":"2024-06-30","structuredOutput":true,"lastUpdated":"2024-10-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"anthracite-org/magnum-v4-72b","displayName":"Magnum v4 72B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-06-30"}},"anthropic/claude-3-haiku":{"metadata":{"displayName":"Claude 3 Haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-08-31","structuredOutput":false,"lastUpdated":"2024-03-13","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"anthropic/claude-3-haiku","displayName":"Claude 3 Haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2023-08-31"}},"anthropic/claude-fable-5":{"metadata":{"displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","structuredOutput":true,"lastUpdated":"2026-06-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-fable-5","displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"anthropic/claude-fable-5.1":{"metadata":{"displayName":"Claude Fable 5.1","description":"Claude model for creative writing, analysis, and controlled agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-06","structuredOutput":true,"lastUpdated":"2026-09-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-fable-5.1","displayName":"Claude Fable 5.1","description":"Claude model for creative writing, analysis, and controlled agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-06"}},"anthropic/claude-haiku-4.5":{"metadata":{"displayName":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-02-28","structuredOutput":true,"lastUpdated":"2025-10-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-haiku-4.5","displayName":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-02-28"}},"anthropic/claude-opus-4":{"metadata":{"displayName":"Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-01-31","structuredOutput":false,"lastUpdated":"2025-05-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4","displayName":"Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-31"}},"anthropic/claude-opus-4.1":{"metadata":{"displayName":"Claude Opus 4.1 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-03-31","structuredOutput":false,"lastUpdated":"2025-08-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4.1","displayName":"Claude Opus 4.1 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-03-31"}},"anthropic/claude-opus-4.5":{"metadata":{"displayName":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2025-11-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4.5","displayName":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-05"}},"anthropic/claude-opus-4.6":{"metadata":{"displayName":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-05-31","structuredOutput":true,"lastUpdated":"2026-03-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4.6","displayName":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05-31"}},"anthropic/claude-opus-4.7":{"metadata":{"displayName":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","structuredOutput":true,"lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4.7","displayName":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"anthropic/claude-opus-4.8":{"metadata":{"displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01","structuredOutput":true,"lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4.8","displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01"}},"anthropic/claude-opus-5":{"metadata":{"displayName":"Claude Opus 5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-05","structuredOutput":true,"lastUpdated":"2026-07-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-5","displayName":"Claude Opus 5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-05"}},"anthropic/claude-sonnet-4":{"metadata":{"displayName":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-31","structuredOutput":false,"lastUpdated":"2025-05-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-sonnet-4","displayName":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-01-31"}},"anthropic/claude-sonnet-4.5":{"metadata":{"displayName":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-07-31","structuredOutput":true,"lastUpdated":"2025-09-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-sonnet-4.5","displayName":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-07-31"}},"anthropic/claude-sonnet-4.6":{"metadata":{"displayName":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-sonnet-4.6","displayName":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-08-31"}},"anthropic/claude-sonnet-5":{"metadata":{"displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","structuredOutput":true,"lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-sonnet-5","displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"arcee-ai/trinity-large-thinking":{"metadata":{"displayName":"Trinity Large Thinking","description":"Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":80000,"structuredOutput":false,"lastUpdated":"2026-05-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"arcee-ai/trinity-large-thinking","displayName":"Trinity Large Thinking","description":"Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"baidu/ernie-4.5-vl-424b-a47b":{"metadata":{"displayName":"ERNIE 4.5 VL 424B A47B ","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":123000,"maxOutputTokens":16000,"knowledgeCutoff":"2025-03-31","structuredOutput":false,"lastUpdated":"2025-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["image","text"],"output":["text"]}},"entry":{"id":"baidu/ernie-4.5-vl-424b-a47b","displayName":"ERNIE 4.5 VL 424B A47B ","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":123000,"defaultContextWindow":123000,"knowledgeCutoff":"2025-03-31"}},"bytedance-seed/seed-1.6":{"metadata":{"displayName":"Seed 1.6","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2025-12-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["image","text","video"],"output":["text"]}},"entry":{"id":"bytedance-seed/seed-1.6","displayName":"Seed 1.6","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"bytedance-seed/seed-1.6-flash":{"metadata":{"displayName":"Seed 1.6 Flash","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2025-12-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["image","text","video"],"output":["text"]}},"entry":{"id":"bytedance-seed/seed-1.6-flash","displayName":"Seed 1.6 Flash","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"bytedance-seed/seed-2-1-turbo":{"metadata":{"displayName":"Seed 2.1 Turbo","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"bytedance-seed/seed-2-1-turbo","displayName":"Seed 2.1 Turbo","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"bytedance-seed/seed-2.0-code":{"metadata":{"displayName":"Seed 2.0 Code","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-02-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"bytedance-seed/seed-2.0-code","displayName":"Seed 2.0 Code","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":262144,"defaultContextWindow":262144}},"bytedance-seed/seed-2.0-lite":{"metadata":{"displayName":"Seed 2.0 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-02-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"bytedance-seed/seed-2.0-lite","displayName":"Seed 2.0 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":262144,"defaultContextWindow":262144}},"bytedance-seed/seed-2.0-mini":{"metadata":{"displayName":"Seed 2.0 Mini","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-02-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"bytedance-seed/seed-2.0-mini","displayName":"Seed 2.0 Mini","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":262144,"defaultContextWindow":262144}},"bytedance/ui-tars-1.5-7b":{"metadata":{"displayName":"UI-TARS 7B ","description":"Multimodal model for analyzing text, images, documents, and rich media","lifecycle":"active","contextWindow":128000,"maxOutputTokens":2048,"knowledgeCutoff":"2025-01-31","structuredOutput":true,"lastUpdated":"2025-07-22","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["image","text"],"output":["text"]}},"entry":{"id":"bytedance/ui-tars-1.5-7b","displayName":"UI-TARS 7B ","description":"Multimodal model for analyzing text, images, documents, and rich media","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-01-31"}},"cognitivecomputations/dolphin-mistral-24b-venice-edition":{"metadata":{"displayName":"Uncensored","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04-30","structuredOutput":false,"lastUpdated":"2025-07-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","displayName":"Uncensored","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-04-30"}},"cohere/command-a":{"metadata":{"displayName":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","lifecycle":"active","contextWindow":256000,"maxOutputTokens":8192,"knowledgeCutoff":"2024-08-31","structuredOutput":true,"lastUpdated":"2025-03-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"cohere/command-a","displayName":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-08-31"}},"cohere/command-r-08-2024":{"metadata":{"displayName":"Command R","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4000,"knowledgeCutoff":"2024-06-01","structuredOutput":true,"lastUpdated":"2024-08-30","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"cohere/command-r-08-2024","displayName":"Command R","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-06-01"}},"cohere/command-r-plus-08-2024":{"metadata":{"displayName":"Command R+","description":"Cohere's RAG workhorse for long-context enterprise search and tool use","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4000,"knowledgeCutoff":"2024-06-01","structuredOutput":true,"lastUpdated":"2024-08-30","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"cohere/command-r-plus-08-2024","displayName":"Command R+","description":"Cohere's RAG workhorse for long-context enterprise search and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-06-01"}},"cohere/command-r7b-12-2024":{"metadata":{"displayName":"Command R7B","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4000,"knowledgeCutoff":"2024-06-01","structuredOutput":true,"lastUpdated":"2024-12-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"cohere/command-r7b-12-2024","displayName":"Command R7B","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-06-01"}},"cohere/north-mini-code:free":{"metadata":{"displayName":"North Mini Code (free)","description":"Cohere coding model for practical software engineering and agentic edits","lifecycle":"active","contextWindow":256000,"maxOutputTokens":64000,"structuredOutput":false,"lastUpdated":"2026-06-17","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"cohere/north-mini-code:free","displayName":"North Mini Code (free)","description":"Cohere coding model for practical software engineering and agentic edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"deepseek/deepseek-chat":{"metadata":{"displayName":"DeepSeek Chat","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":16000,"knowledgeCutoff":"2025-09","structuredOutput":true,"lastUpdated":"2026-02-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-chat","displayName":"DeepSeek Chat","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2025-09"}},"deepseek/deepseek-chat-v3-0324":{"metadata":{"displayName":"DeepSeek V3 0324","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":147456,"knowledgeCutoff":"2024-07-31","structuredOutput":true,"lastUpdated":"2025-03-24","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-chat-v3-0324","displayName":"DeepSeek V3 0324","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2024-07-31"}},"deepseek/deepseek-chat-v3.1":{"metadata":{"displayName":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":32768,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-08-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-chat-v3.1","displayName":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2025-03-31"}},"deepseek/deepseek-r1":{"metadata":{"displayName":"DeepSeek-R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","lifecycle":"active","contextWindow":64000,"maxOutputTokens":16000,"knowledgeCutoff":"2024-07","structuredOutput":false,"lastUpdated":"2025-05-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-r1","displayName":"DeepSeek-R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":64000,"defaultContextWindow":64000,"knowledgeCutoff":"2024-07"}},"deepseek/deepseek-r1-0528":{"metadata":{"displayName":"R1 0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","lifecycle":"active","contextWindow":163840,"maxOutputTokens":32768,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-05-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-r1-0528","displayName":"R1 0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2025-03-31"}},"deepseek/deepseek-r1-distill-llama-70b":{"metadata":{"displayName":"R1 Distill Llama 70B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","lifecycle":"active","contextWindow":8192,"maxOutputTokens":7372,"knowledgeCutoff":"2024-07-31","structuredOutput":false,"lastUpdated":"2025-01-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-r1-distill-llama-70b","displayName":"R1 Distill Llama 70B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2024-07-31"}},"deepseek/deepseek-v3.1-terminus":{"metadata":{"displayName":"DeepSeek V3.1 Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":32768,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-09-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v3.1-terminus","displayName":"DeepSeek V3.1 Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2025-03-31"}},"deepseek/deepseek-v3.2":{"metadata":{"displayName":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":65536,"knowledgeCutoff":"2024-07","structuredOutput":true,"lastUpdated":"2025-12-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v3.2","displayName":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2024-07"}},"deepseek/deepseek-v3.2-exp":{"metadata":{"displayName":"DeepSeek V3.2 Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":65536,"knowledgeCutoff":"2025-07-31","structuredOutput":true,"lastUpdated":"2025-09-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v3.2-exp","displayName":"DeepSeek V3.2 Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2025-07-31"}},"deepseek/deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-flash","displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"deepseek/deepseek-v4-flash-0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1310720,"maxOutputTokens":943718,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-flash-0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1310720,"defaultContextWindow":1310720,"knowledgeCutoff":"2025-05"}},"deepseek/deepseek-v4-flash-vision-exp":{"metadata":{"displayName":"DeepSeek V4 Flash Vision Exp","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":943718,"structuredOutput":true,"lastUpdated":"2026-08-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-flash-vision-exp","displayName":"DeepSeek V4 Flash Vision Exp","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"deepseek/deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":393216,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-pro","displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"deepseek/deepseek-v4-pro-0813":{"metadata":{"displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-pro-0813","displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"deepseek/deepseek-v4.1-flash":{"metadata":{"displayName":"DeepSeek V4.1 Flash","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4.1-flash","displayName":"DeepSeek V4.1 Flash","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"dots-studio/dots-3-note-preview:free":{"metadata":{"displayName":"Dots3-Note Preview (free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":512000,"maxOutputTokens":460800,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"dots-studio/dots-3-note-preview:free","displayName":"Dots3-Note Preview (free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":512000,"defaultContextWindow":512000}},"google/gemini-2.5-flash":{"metadata":{"displayName":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65535,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-06-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-2.5-flash","displayName":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-2.5-flash-image":{"metadata":{"displayName":"Nano Banana","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","lifecycle":"active","contextWindow":32768,"maxOutputTokens":8192,"knowledgeCutoff":"2024-06","structuredOutput":true,"lastUpdated":"2025-08-26","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"google/gemini-2.5-flash-image","displayName":"Nano Banana","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-06"}},"google/gemini-2.5-flash-lite":{"metadata":{"displayName":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65535,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-06-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-2.5-flash-lite","displayName":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-2.5-pro":{"metadata":{"displayName":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-06-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-2.5-pro","displayName":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-2.5-pro-preview":{"metadata":{"displayName":"Gemini 2.5 Pro Preview 06-05","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01-31","structuredOutput":true,"lastUpdated":"2025-06-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["pdf","image","text","audio"],"output":["text"]}},"entry":{"id":"google/gemini-2.5-pro-preview","displayName":"Gemini 2.5 Pro Preview 06-05","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01-31"}},"google/gemini-3-flash-preview":{"metadata":{"displayName":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-12-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"],"toggle":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3-flash-preview","displayName":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-3-pro-image":{"metadata":{"displayName":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"google/gemini-3-pro-image","displayName":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"google/gemini-3-pro-image-preview":{"metadata":{"displayName":"Nano Banana Pro Preview","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","lifecycle":"active","contextWindow":65536,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-11-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"google/gemini-3-pro-image-preview","displayName":"Nano Banana Pro Preview","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-flash-image":{"metadata":{"displayName":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["minimal","high"],"toggle":true},"modalities":{"input":["image","text"],"output":["text","image"]}},"entry":{"id":"google/gemini-3.1-flash-image","displayName":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","high"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-flash-image-preview":{"metadata":{"displayName":"Nano Banana 2 Preview","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":65536,"maxOutputTokens":58982,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-02-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["minimal","high"],"toggle":true},"modalities":{"input":["image","text"],"output":["text","image"]}},"entry":{"id":"google/gemini-3.1-flash-image-preview","displayName":"Nano Banana 2 Preview","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","high"],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-flash-lite":{"metadata":{"displayName":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"],"toggle":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.1-flash-lite","displayName":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-flash-lite-image":{"metadata":{"displayName":"Nano Banana 2 Lite","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":65536,"maxOutputTokens":58982,"knowledgeCutoff":"2025-01","structuredOutput":false,"lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["minimal","high"],"toggle":true},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"google/gemini-3.1-flash-lite-image","displayName":"Nano Banana 2 Lite","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","high"],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-flash-lite-preview":{"metadata":{"displayName":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-03-03","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"],"toggle":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.1-flash-lite-preview","displayName":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-pro-preview":{"metadata":{"displayName":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-02-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.1-pro-preview","displayName":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-pro-preview-customtools":{"metadata":{"displayName":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-02-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.1-pro-preview-customtools","displayName":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-3.5-flash":{"metadata":{"displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.5-flash","displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-3.5-flash-lite":{"metadata":{"displayName":"Gemini 3.5 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-07-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.5-flash-lite","displayName":"Gemini 3.5 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2026-03"}},"google/gemini-3.6-flash":{"metadata":{"displayName":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-07-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.6-flash","displayName":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2026-03"}},"google/gemini-3.7-flash":{"metadata":{"displayName":"Gemini 3.7 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-08-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.7-flash","displayName":"Gemini 3.7 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2026-03"}},"google/gemini-3.8-flash":{"metadata":{"displayName":"Gemini 3.8 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.8-flash","displayName":"Gemini 3.8 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576}},"google/gemma-2-27b-it":{"metadata":{"displayName":"Gemma 2 27B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":8192,"maxOutputTokens":2048,"knowledgeCutoff":"2024-06-30","structuredOutput":true,"lastUpdated":"2024-07-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"google/gemma-2-27b-it","displayName":"Gemma 2 27B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2024-06-30"}},"google/gemma-3-12b-it":{"metadata":{"displayName":"Gemma 3 12B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2024-08","structuredOutput":true,"lastUpdated":"2025-03-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3-12b-it","displayName":"Gemma 3 12B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-08"}},"google/gemma-3-27b-it":{"metadata":{"displayName":"Gemma 3 27B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"knowledgeCutoff":"2024-08","structuredOutput":true,"lastUpdated":"2025-03-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3-27b-it","displayName":"Gemma 3 27B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-08"}},"google/gemma-3-4b-it":{"metadata":{"displayName":"Gemma 3 4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2024-08","structuredOutput":true,"lastUpdated":"2025-03-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3-4b-it","displayName":"Gemma 3 4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-08"}},"google/gemma-4-26b-a4b-it":{"metadata":{"displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["image","text","video"],"output":["text"]}},"entry":{"id":"google/gemma-4-26b-a4b-it","displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"google/gemma-4-26b-a4b-it:free":{"metadata":{"displayName":"Gemma 4 26B A4B (free)","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["image","text","video"],"output":["text"]}},"entry":{"id":"google/gemma-4-26b-a4b-it:free","displayName":"Gemma 4 26B A4B (free)","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"google/gemma-4-31b-it":{"metadata":{"displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["image","text","video"],"output":["text"]}},"entry":{"id":"google/gemma-4-31b-it","displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"google/gemma-4-31b-it:free":{"metadata":{"displayName":"Gemma 4 31B (free)","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["image","text","video"],"output":["text"]}},"entry":{"id":"google/gemma-4-31b-it:free","displayName":"Gemma 4 31B (free)","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"google/lyria-3-clip-preview":{"metadata":{"displayName":"Lyria 3 Clip Preview","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"structuredOutput":false,"lastUpdated":"2026-03-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","audio"]}},"entry":{"id":"google/lyria-3-clip-preview","displayName":"Lyria 3 Clip Preview","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}},"google/lyria-3-pro-preview":{"metadata":{"displayName":"Lyria 3 Pro Preview","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"structuredOutput":false,"lastUpdated":"2026-03-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","audio"]}},"entry":{"id":"google/lyria-3-pro-preview","displayName":"Lyria 3 Pro Preview","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}},"gryphe/mythomax-l2-13b":{"metadata":{"displayName":"MythoMax 13B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","lifecycle":"active","contextWindow":8192,"maxOutputTokens":3686,"knowledgeCutoff":"2023-06-30","structuredOutput":true,"lastUpdated":"2023-07-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"gryphe/mythomax-l2-13b","displayName":"MythoMax 13B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2023-06-30"}},"ibm-granite/granite-4.0-h-micro":{"metadata":{"displayName":"Granite 4.0 Micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":131000,"maxOutputTokens":117900,"structuredOutput":false,"lastUpdated":"2025-10-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"ibm-granite/granite-4.0-h-micro","displayName":"Granite 4.0 Micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000}},"ibm-granite/granite-4.2-8b":{"metadata":{"displayName":"Granite 4.2 8B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"structuredOutput":true,"lastUpdated":"2026-08-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"ibm-granite/granite-4.2-8b","displayName":"Granite 4.2 8B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","high"],"contextWindow":131072,"defaultContextWindow":131072}},"inception/mercury-2":{"metadata":{"displayName":"Mercury 2","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":128000,"maxOutputTokens":50000,"structuredOutput":true,"lastUpdated":"2026-03-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inception/mercury-2","displayName":"Mercury 2","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high"],"contextWindow":128000,"defaultContextWindow":128000}},"inception/mercury-2.5":{"metadata":{"displayName":"Mercury 2.5","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":260000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-09-08","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inception/mercury-2.5","displayName":"Mercury 2.5","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high"],"contextWindow":260000,"defaultContextWindow":260000}},"inclusionai/ling-3.0-flash":{"metadata":{"displayName":"Ling 3.0 Flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-07-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash","displayName":"Ling 3.0 Flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"inclusionai/ling-3.0-flash-fin":{"metadata":{"displayName":"Ling 3.0 Flash Fin","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2026-08-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash-fin","displayName":"Ling 3.0 Flash Fin","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"inclusionai/ling-3.0-flash-fin:free":{"metadata":{"displayName":"Ling 3.0 Flash Fin (free)","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-08-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash-fin:free","displayName":"Ling 3.0 Flash Fin (free)","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"inclusionai/ling-3.0-flash-sante:free":{"metadata":{"displayName":"Ling 3.0 Flash Sante (free)","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-09-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash-sante:free","displayName":"Ling 3.0 Flash Sante (free)","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"inclusionai/ling-3.0-flash-vl":{"metadata":{"displayName":"Ling 3.0 Flash VL","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash-vl","displayName":"Ling 3.0 Flash VL","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"inclusionai/ling-3.0-flash-vl:free":{"metadata":{"displayName":"Ling 3.0 Flash VL (free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash-vl:free","displayName":"Ling 3.0 Flash VL (free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"inference-net/schematron-v2-small":{"metadata":{"displayName":"Schematron V2 Small","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"structuredOutput":true,"lastUpdated":"2026-09-12","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inference-net/schematron-v2-small","displayName":"Schematron V2 Small","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"inference-net/schematron-v2-turbo":{"metadata":{"displayName":"Schematron V2 Turbo","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"structuredOutput":true,"lastUpdated":"2026-09-12","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inference-net/schematron-v2-turbo","displayName":"Schematron V2 Turbo","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"kwaipilot/kat-coder-pro-v2":{"metadata":{"displayName":"KAT-Coder-Pro V2","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":144000,"structuredOutput":true,"lastUpdated":"2026-03-27","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"kwaipilot/kat-coder-pro-v2","displayName":"KAT-Coder-Pro V2","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"kwaipilot/kat-coder-pro-v2.5":{"metadata":{"displayName":"KAT-Coder-Pro V2.5","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2026-07-10","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"kwaipilot/kat-coder-pro-v2.5","displayName":"KAT-Coder-Pro V2.5","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"liquid/lfm-2.5-2.6b:free":{"metadata":{"displayName":"LFM2.5-2.6B (free)","description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","lifecycle":"active","contextWindow":65536,"maxOutputTokens":8192,"structuredOutput":true,"lastUpdated":"2026-08-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"liquid/lfm-2.5-2.6b:free","displayName":"LFM2.5-2.6B (free)","description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536}},"mancer/weaver":{"metadata":{"displayName":"Weaver (alpha)","description":"General-purpose chat model for instruction following, writing, and analysis","lifecycle":"active","contextWindow":8000,"maxOutputTokens":6000,"knowledgeCutoff":"2023-06-30","structuredOutput":false,"lastUpdated":"2023-08-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mancer/weaver","displayName":"Weaver (alpha)","description":"General-purpose chat model for instruction following, writing, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8000,"defaultContextWindow":8000,"knowledgeCutoff":"2023-06-30"}},"meituan/longcat-2.0":{"metadata":{"displayName":"LongCat 2.0","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":1048756,"maxOutputTokens":262144,"structuredOutput":false,"lastUpdated":"2026-07-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meituan/longcat-2.0","displayName":"LongCat 2.0","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048756,"defaultContextWindow":1048756}},"meta-llama/llama-3.1-70b-instruct":{"metadata":{"displayName":"Llama-3.1-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2023-12","structuredOutput":true,"lastUpdated":"2024-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/llama-3.1-70b-instruct","displayName":"Llama-3.1-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12"}},"meta-llama/llama-3.1-8b-instruct":{"metadata":{"displayName":"Llama-3.1-8B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"knowledgeCutoff":"2023-12","structuredOutput":true,"lastUpdated":"2024-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/llama-3.1-8b-instruct","displayName":"Llama-3.1-8B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12"}},"meta-llama/llama-3.2-1b-instruct":{"metadata":{"displayName":"Llama 3.2 1B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":60000,"maxOutputTokens":54000,"knowledgeCutoff":"2023-12-31","structuredOutput":false,"lastUpdated":"2024-09-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/llama-3.2-1b-instruct","displayName":"Llama 3.2 1B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":60000,"defaultContextWindow":60000,"knowledgeCutoff":"2023-12-31"}},"meta-llama/llama-3.2-3b-instruct":{"metadata":{"displayName":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"knowledgeCutoff":"2023-12-31","structuredOutput":true,"lastUpdated":"2024-09-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/llama-3.2-3b-instruct","displayName":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12-31"}},"meta-llama/llama-3.3-70b-instruct":{"metadata":{"displayName":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2023-12","structuredOutput":true,"lastUpdated":"2024-12-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/llama-3.3-70b-instruct","displayName":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12"}},"meta-llama/llama-4-maverick":{"metadata":{"displayName":"Llama 4 Maverick","description":"Open multimodal Llama model for strong reasoning and fast responses","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":16384,"knowledgeCutoff":"2024-08-31","structuredOutput":true,"lastUpdated":"2025-04-05","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta-llama/llama-4-maverick","displayName":"Llama 4 Maverick","description":"Open multimodal Llama model for strong reasoning and fast responses","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-08-31"}},"meta-llama/llama-4-scout":{"metadata":{"displayName":"Llama 4 Scout","description":"Open multimodal Llama model for long-context analysis and efficient agents","lifecycle":"active","contextWindow":1310720,"maxOutputTokens":16384,"knowledgeCutoff":"2024-08-31","structuredOutput":true,"lastUpdated":"2025-04-05","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta-llama/llama-4-scout","displayName":"Llama 4 Scout","description":"Open multimodal Llama model for long-context analysis and efficient agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1310720,"defaultContextWindow":1310720,"knowledgeCutoff":"2024-08-31"}},"meta-llama/llama-guard-4-12b":{"metadata":{"displayName":"Llama Guard 4 12B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"active","contextWindow":163840,"maxOutputTokens":16384,"knowledgeCutoff":"2024-08-31","structuredOutput":false,"lastUpdated":"2025-04-30","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["image","text"],"output":["text"]}},"entry":{"id":"meta-llama/llama-guard-4-12b","displayName":"Llama Guard 4 12B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2024-08-31"}},"meta/muse-glimmer-30b":{"metadata":{"displayName":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"knowledgeCutoff":"2026-01-04","structuredOutput":true,"lastUpdated":"2026-08-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta/muse-glimmer-30b","displayName":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2026-01-04"}},"meta/muse-spark-1.1":{"metadata":{"displayName":"Muse Spark 1.1","description":"Open Llama multimodal model for image understanding and text reasoning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":943718,"structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"entry":{"id":"meta/muse-spark-1.1","displayName":"Muse Spark 1.1","description":"Open Llama multimodal model for image understanding and text reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"meta/muse-spark-1.2":{"metadata":{"displayName":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":943718,"structuredOutput":true,"lastUpdated":"2026-08-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"entry":{"id":"meta/muse-spark-1.2","displayName":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"meta/muse-spark-1.2-contributor":{"metadata":{"displayName":"Muse Spark 1.2 Contributor","description":"Open Llama multimodal model for image understanding and text reasoning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":943718,"structuredOutput":true,"lastUpdated":"2026-08-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"entry":{"id":"meta/muse-spark-1.2-contributor","displayName":"Muse Spark 1.2 Contributor","description":"Open Llama multimodal model for image understanding and text reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"meta/muse-spark-1.3":{"metadata":{"displayName":"Muse Spark 1.3","description":"Open Llama multimodal model for image understanding and text reasoning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":943718,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"entry":{"id":"meta/muse-spark-1.3","displayName":"Muse Spark 1.3","description":"Open Llama multimodal model for image understanding and text reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"meta/muse-spark-1.3-contributor":{"metadata":{"displayName":"Muse Spark 1.3 Contributor","description":"Open Llama multimodal model for image understanding and text reasoning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":943718,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"entry":{"id":"meta/muse-spark-1.3-contributor","displayName":"Muse Spark 1.3 Contributor","description":"Open Llama multimodal model for image understanding and text reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"microsoft/phi-4":{"metadata":{"displayName":"Phi 4","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","lifecycle":"active","contextWindow":16384,"maxOutputTokens":14745,"knowledgeCutoff":"2024-06-30","structuredOutput":true,"lastUpdated":"2025-01-10","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"microsoft/phi-4","displayName":"Phi 4","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16384,"defaultContextWindow":16384,"knowledgeCutoff":"2024-06-30"}},"microsoft/wizardlm-2-8x22b":{"metadata":{"displayName":"WizardLM-2 8x22B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","lifecycle":"active","contextWindow":65535,"maxOutputTokens":8000,"knowledgeCutoff":"2024-04-30","structuredOutput":false,"lastUpdated":"2024-04-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"microsoft/wizardlm-2-8x22b","displayName":"WizardLM-2 8x22B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":65535,"defaultContextWindow":65535,"knowledgeCutoff":"2024-04-30"}},"minimax/minimax-01":{"metadata":{"displayName":"MiniMax-01","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","lifecycle":"active","contextWindow":1000192,"maxOutputTokens":900172,"knowledgeCutoff":"2024-03-31","structuredOutput":false,"lastUpdated":"2025-01-15","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"minimax/minimax-01","displayName":"MiniMax-01","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000192,"defaultContextWindow":1000192,"knowledgeCutoff":"2024-03-31"}},"minimax/minimax-m1":{"metadata":{"displayName":"MiniMax M1","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":40000,"knowledgeCutoff":"2024-06-30","structuredOutput":false,"lastUpdated":"2025-06-17","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m1","displayName":"MiniMax M1","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-06-30"}},"minimax/minimax-m2":{"metadata":{"displayName":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2025-10-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2","displayName":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"minimax/minimax-m2-her":{"metadata":{"displayName":"MiniMax-M2 Her","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":65536,"maxOutputTokens":2048,"structuredOutput":false,"lastUpdated":"2026-01-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2-her","displayName":"MiniMax-M2 Her","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536}},"minimax/minimax-m2.1":{"metadata":{"displayName":"MiniMax-M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"structuredOutput":false,"lastUpdated":"2025-12-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2.1","displayName":"MiniMax-M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"minimax/minimax-m2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","lifecycle":"active","contextWindow":204800,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2.5","displayName":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"minimax/minimax-m2.7":{"metadata":{"displayName":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2.7","displayName":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"minimax/minimax-m3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":512000,"structuredOutput":true,"lastUpdated":"2026-06-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"minimax/minimax-m3","displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}},"mistralai/codestral-2508":{"metadata":{"displayName":"Codestral 2508","description":"Mistral coding model for code completion, generation, and developer workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":204800,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-08-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","pdf"],"output":["text"]}},"entry":{"id":"mistralai/codestral-2508","displayName":"Codestral 2508","description":"Mistral coding model for code completion, generation, and developer workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-03-31"}},"mistralai/devstral-2512":{"metadata":{"displayName":"Devstral 2","description":"Mistral coding agent model for repository tasks and software engineering workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":209715,"knowledgeCutoff":"2025-12","structuredOutput":true,"lastUpdated":"2025-12-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","pdf"],"output":["text"]}},"entry":{"id":"mistralai/devstral-2512","displayName":"Devstral 2","description":"Mistral coding agent model for repository tasks and software engineering workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-12"}},"mistralai/ministral-14b-2512":{"metadata":{"displayName":"Ministral 3 14B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":209715,"structuredOutput":true,"lastUpdated":"2025-12-02","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistralai/ministral-14b-2512","displayName":"Ministral 3 14B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"mistralai/ministral-3b-2512":{"metadata":{"displayName":"Ministral 3 3B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":104857,"structuredOutput":true,"lastUpdated":"2025-12-02","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistralai/ministral-3b-2512","displayName":"Ministral 3 3B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"mistralai/ministral-8b-2512":{"metadata":{"displayName":"Ministral 3 8B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":209715,"structuredOutput":true,"lastUpdated":"2025-12-02","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistralai/ministral-8b-2512","displayName":"Ministral 3 8B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"mistralai/mistral-large":{"metadata":{"displayName":"Mistral Large","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","lifecycle":"active","contextWindow":128000,"maxOutputTokens":102400,"knowledgeCutoff":"2024-11-30","structuredOutput":true,"lastUpdated":"2024-02-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","pdf"],"output":["text"]}},"entry":{"id":"mistralai/mistral-large","displayName":"Mistral Large","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-11-30"}},"mistralai/mistral-large-2407":{"metadata":{"displayName":"Mistral Large 2407","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","lifecycle":"active","contextWindow":131072,"maxOutputTokens":104857,"knowledgeCutoff":"2024-03-31","structuredOutput":true,"lastUpdated":"2024-11-19","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","pdf"],"output":["text"]}},"entry":{"id":"mistralai/mistral-large-2407","displayName":"Mistral Large 2407","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-03-31"}},"mistralai/mistral-large-2512":{"metadata":{"displayName":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":209715,"knowledgeCutoff":"2024-11","structuredOutput":true,"lastUpdated":"2025-12-02","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"mistralai/mistral-large-2512","displayName":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-11"}},"mistralai/mistral-medium-3":{"metadata":{"displayName":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":104857,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-05-07","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"mistralai/mistral-medium-3","displayName":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-03-31"}},"mistralai/mistral-medium-3-5":{"metadata":{"displayName":"Mistral Medium 3.5","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":209715,"structuredOutput":true,"lastUpdated":"2026-04-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"mistralai/mistral-medium-3-5","displayName":"Mistral Medium 3.5","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","high"],"contextWindow":262144,"defaultContextWindow":262144}},"mistralai/mistral-medium-3.1":{"metadata":{"displayName":"Mistral Medium 3.1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":104857,"knowledgeCutoff":"2025-06-30","structuredOutput":true,"lastUpdated":"2025-08-13","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"mistralai/mistral-medium-3.1","displayName":"Mistral Medium 3.1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-06-30"}},"mistralai/mistral-nemo":{"metadata":{"displayName":"Mistral Nemo","description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2024-07","structuredOutput":true,"lastUpdated":"2024-07-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistralai/mistral-nemo","displayName":"Mistral Nemo","description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-07"}},"mistralai/mistral-saba":{"metadata":{"displayName":"Saba","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":32768,"maxOutputTokens":26214,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-02-17","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","pdf"],"output":["text"]}},"entry":{"id":"mistralai/mistral-saba","displayName":"Saba","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-09-30"}},"mistralai/mistral-small-24b-instruct-2501":{"metadata":{"displayName":"Mistral Small 3","description":"Efficient Mistral model for fast chat, extraction, and production assistants","lifecycle":"active","contextWindow":32768,"maxOutputTokens":16384,"knowledgeCutoff":"2023-10-31","structuredOutput":true,"lastUpdated":"2025-01-30","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistralai/mistral-small-24b-instruct-2501","displayName":"Mistral Small 3","description":"Efficient Mistral model for fast chat, extraction, and production assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2023-10-31"}},"mistralai/mistral-small-2603":{"metadata":{"displayName":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","lifecycle":"active","contextWindow":262144,"maxOutputTokens":209715,"knowledgeCutoff":"2025-06","structuredOutput":true,"lastUpdated":"2026-03-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistralai/mistral-small-2603","displayName":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","high"],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-06"}},"mistralai/mistral-small-3.1-24b-instruct":{"metadata":{"displayName":"Mistral Small 3.1 24B","description":"Efficient Mistral model for fast chat, extraction, and production assistants","lifecycle":"active","contextWindow":128000,"maxOutputTokens":102400,"knowledgeCutoff":"2023-10-31","structuredOutput":false,"lastUpdated":"2025-03-17","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistralai/mistral-small-3.1-24b-instruct","displayName":"Mistral Small 3.1 24B","description":"Efficient Mistral model for fast chat, extraction, and production assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-10-31"}},"mistralai/mistral-small-3.2-24b-instruct":{"metadata":{"displayName":"Mistral Small 3.2 24B","description":"Efficient Mistral model for fast chat, extraction, and production assistants","lifecycle":"active","contextWindow":256000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-10-31","structuredOutput":true,"lastUpdated":"2025-06-20","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["image","text"],"output":["text"]}},"entry":{"id":"mistralai/mistral-small-3.2-24b-instruct","displayName":"Mistral Small 3.2 24B","description":"Efficient Mistral model for fast chat, extraction, and production assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2023-10-31"}},"mistralai/mixtral-8x22b-instruct":{"metadata":{"displayName":"Mixtral 8x22B Instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":65536,"maxOutputTokens":52428,"knowledgeCutoff":"2024-01-31","structuredOutput":true,"lastUpdated":"2024-04-17","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","pdf"],"output":["text"]}},"entry":{"id":"mistralai/mixtral-8x22b-instruct","displayName":"Mixtral 8x22B Instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2024-01-31"}},"mistralai/voxtral-small-24b-2507":{"metadata":{"displayName":"Voxtral Small 24B 2507","description":"Efficient Mistral model for fast chat, extraction, and production assistants","lifecycle":"active","contextWindow":32768,"maxOutputTokens":26214,"structuredOutput":true,"lastUpdated":"2025-07-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","audio","pdf"],"output":["text"]}},"entry":{"id":"mistralai/voxtral-small-24b-2507","displayName":"Voxtral Small 24B 2507","description":"Efficient Mistral model for fast chat, extraction, and production assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"moonshotai/kimi-k2":{"metadata":{"displayName":"Kimi K2 0711","description":"Kimi model for long-context chat, coding, and agentic reasoning","lifecycle":"active","contextWindow":131072,"maxOutputTokens":98304,"knowledgeCutoff":"2024-12-31","structuredOutput":false,"lastUpdated":"2025-07-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2","displayName":"Kimi K2 0711","description":"Kimi model for long-context chat, coding, and agentic reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-12-31"}},"moonshotai/kimi-k2-0905":{"metadata":{"displayName":"Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":98304,"knowledgeCutoff":"2024-12-31","structuredOutput":true,"lastUpdated":"2025-09-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2-0905","displayName":"Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-12-31"}},"moonshotai/kimi-k2-thinking":{"metadata":{"displayName":"Kimi K2 Thinking","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","lifecycle":"active","contextWindow":262144,"maxOutputTokens":98304,"knowledgeCutoff":"2024-08","structuredOutput":true,"lastUpdated":"2025-11-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2-thinking","displayName":"Kimi K2 Thinking","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-08"}},"moonshotai/kimi-k2.5":{"metadata":{"displayName":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.5","displayName":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/kimi-k2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.6","displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/kimi-k2.7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.7-code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/kimi-k3":{"metadata":{"displayName":"Kimi K3","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":943718,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k3","displayName":"Kimi K3","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"morph/morph-v3-fast":{"metadata":{"displayName":"Morph V3 Fast","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":81920,"maxOutputTokens":38000,"structuredOutput":false,"lastUpdated":"2025-07-07","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"morph/morph-v3-fast","displayName":"Morph V3 Fast","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":81920,"defaultContextWindow":81920}},"morph/morph-v3-large":{"metadata":{"displayName":"Morph V3 Large","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2025-07-07","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"morph/morph-v3-large","displayName":"Morph V3 Large","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"nex-agi/nex-n2.5-mini:free":{"metadata":{"displayName":"Nex-N2.5-Mini (free)","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2026-09-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"nex-agi/nex-n2.5-mini:free","displayName":"Nex-N2.5-Mini (free)","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","medium","high"],"contextWindow":262144,"defaultContextWindow":262144}},"nex-agi/nex-n2.5-pro:free":{"metadata":{"displayName":"Nex-N2.5-Pro (free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2026-09-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"nex-agi/nex-n2.5-pro:free","displayName":"Nex-N2.5-Pro (free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","medium","high"],"contextWindow":262144,"defaultContextWindow":262144}},"nousresearch/hermes-3-llama-3.1-405b":{"metadata":{"displayName":"Hermes 3 405B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2023-12-31","structuredOutput":true,"lastUpdated":"2024-08-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nousresearch/hermes-3-llama-3.1-405b","displayName":"Hermes 3 405B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12-31"}},"nousresearch/hermes-3-llama-3.1-70b":{"metadata":{"displayName":"Hermes 3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2023-12-31","structuredOutput":true,"lastUpdated":"2024-08-18","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nousresearch/hermes-3-llama-3.1-70b","displayName":"Hermes 3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12-31"}},"nousresearch/hermes-4-405b":{"metadata":{"displayName":"Hermes 4 405B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"knowledgeCutoff":"2024-08-31","structuredOutput":false,"lastUpdated":"2025-08-26","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nousresearch/hermes-4-405b","displayName":"Hermes 4 405B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-08-31"}},"nvidia/nemotron-3-nano-30b-a3b":{"metadata":{"displayName":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2025-12-15","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-nano-30b-a3b","displayName":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free":{"metadata":{"displayName":"Nemotron 3 Nano Omni (free)","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","lifecycle":"active","contextWindow":256000,"maxOutputTokens":65536,"structuredOutput":false,"lastUpdated":"2026-04-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","displayName":"Nemotron 3 Nano Omni (free)","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"nvidia/nemotron-3-super-120b-a12b":{"metadata":{"displayName":"Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2026-03-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-super-120b-a12b","displayName":"Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium"],"contextWindow":262144,"defaultContextWindow":262144}},"nvidia/nemotron-3-super-120b-a12b:free":{"metadata":{"displayName":"Nemotron 3 Super (free)","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2026-03-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-super-120b-a12b:free","displayName":"Nemotron 3 Super (free)","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium"],"contextWindow":262144,"defaultContextWindow":262144}},"nvidia/nemotron-3-ultra-550b-a55b":{"metadata":{"displayName":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","lifecycle":"active","contextWindow":262144,"maxOutputTokens":182520,"structuredOutput":true,"lastUpdated":"2026-06-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-ultra-550b-a55b","displayName":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["medium","high"],"contextWindow":262144,"defaultContextWindow":262144}},"nvidia/nemotron-3-ultra-550b-a55b:free":{"metadata":{"displayName":"Nemotron 3 Ultra (free)","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":false,"lastUpdated":"2026-06-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-ultra-550b-a55b:free","displayName":"Nemotron 3 Ultra (free)","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000}},"nvidia/nemotron-3.5-content-safety":{"metadata":{"displayName":"Nemotron 3.5 Content Safety","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"structuredOutput":false,"lastUpdated":"2026-06-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3.5-content-safety","displayName":"Nemotron 3.5 Content Safety","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"nvidia/nemotron-3.5-content-safety:free":{"metadata":{"displayName":"Nemotron 3.5 Content Safety (free)","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"structuredOutput":false,"lastUpdated":"2026-06-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3.5-content-safety:free","displayName":"Nemotron 3.5 Content Safety (free)","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/nemotron-3.5-lightning":{"metadata":{"displayName":"Nemotron 3.5 Lightning 30B A3B","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3.5-lightning","displayName":"Nemotron 3.5 Lightning 30B A3B","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"nvidia/nemotron-3.5-lightning:free":{"metadata":{"displayName":"Nemotron 3.5 Lightning (free)","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":false,"lastUpdated":"2026-08-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3.5-lightning:free","displayName":"Nemotron 3.5 Lightning (free)","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"openai/gpt-3.5-turbo":{"metadata":{"displayName":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":16385,"maxOutputTokens":4096,"knowledgeCutoff":"2021-09-01","structuredOutput":true,"lastUpdated":"2023-11-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-3.5-turbo","displayName":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16385,"defaultContextWindow":16385,"knowledgeCutoff":"2021-09-01"}},"openai/gpt-3.5-turbo-0613":{"metadata":{"displayName":"GPT-3.5 Turbo (older v0613)","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":4095,"maxOutputTokens":3685,"knowledgeCutoff":"2021-09-30","structuredOutput":true,"lastUpdated":"2024-01-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-3.5-turbo-0613","displayName":"GPT-3.5 Turbo (older v0613)","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":4095,"defaultContextWindow":4095,"knowledgeCutoff":"2021-09-30"}},"openai/gpt-3.5-turbo-16k":{"metadata":{"displayName":"GPT-3.5 Turbo 16k","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":16385,"maxOutputTokens":4096,"knowledgeCutoff":"2021-09-30","structuredOutput":true,"lastUpdated":"2023-08-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-3.5-turbo-16k","displayName":"GPT-3.5 Turbo 16k","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16385,"defaultContextWindow":16385,"knowledgeCutoff":"2021-09-30"}},"openai/gpt-3.5-turbo-instruct":{"metadata":{"displayName":"GPT-3.5 Turbo Instruct","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":4095,"maxOutputTokens":3685,"knowledgeCutoff":"2021-09-30","structuredOutput":true,"lastUpdated":"2023-09-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-3.5-turbo-instruct","displayName":"GPT-3.5 Turbo Instruct","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":4095,"defaultContextWindow":4095,"knowledgeCutoff":"2021-09-30"}},"openai/gpt-4":{"metadata":{"displayName":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":8191,"maxOutputTokens":4096,"knowledgeCutoff":"2023-11","structuredOutput":true,"lastUpdated":"2024-04-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-4","displayName":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8191,"defaultContextWindow":8191,"knowledgeCutoff":"2023-11"}},"openai/gpt-4-turbo":{"metadata":{"displayName":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-12","structuredOutput":true,"lastUpdated":"2024-04-09","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openai/gpt-4-turbo","displayName":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-12"}},"openai/gpt-4.1":{"metadata":{"displayName":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","lifecycle":"active","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4.1","displayName":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"openai/gpt-4.1-mini":{"metadata":{"displayName":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","lifecycle":"active","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4.1-mini","displayName":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"openai/gpt-4.1-nano":{"metadata":{"displayName":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","lifecycle":"active","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4.1-nano","displayName":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"openai/gpt-4o":{"metadata":{"displayName":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-08-06","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4o","displayName":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"openai/gpt-4o-2024-05-13":{"metadata":{"displayName":"GPT-4o (2024-05-13)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-05-13","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4o-2024-05-13","displayName":"GPT-4o (2024-05-13)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"openai/gpt-4o-2024-08-06":{"metadata":{"displayName":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-08-06","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4o-2024-08-06","displayName":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"openai/gpt-4o-2024-11-20":{"metadata":{"displayName":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-11-20","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4o-2024-11-20","displayName":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"openai/gpt-4o-mini":{"metadata":{"displayName":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-07-18","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4o-mini","displayName":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"openai/gpt-4o-mini-2024-07-18":{"metadata":{"displayName":"GPT-4o-mini (2024-07-18)","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-10-31","structuredOutput":true,"lastUpdated":"2024-07-18","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4o-mini-2024-07-18","displayName":"GPT-4o-mini (2024-07-18)","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-10-31"}},"openai/gpt-5":{"metadata":{"displayName":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5","displayName":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5-image":{"metadata":{"displayName":"GPT-5 Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-10-01","structuredOutput":true,"lastUpdated":"2025-10-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"modalities":{"input":["image","text","pdf"],"output":["image","text"]}},"entry":{"id":"openai/gpt-5-image","displayName":"GPT-5 Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2024-10-01"}},"openai/gpt-5-image-mini":{"metadata":{"displayName":"GPT-5 Image Mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2025-10-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"modalities":{"input":["pdf","image","text"],"output":["image","text"]}},"entry":{"id":"openai/gpt-5-image-mini","displayName":"GPT-5 Image Mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":400000,"defaultContextWindow":400000}},"openai/gpt-5-mini":{"metadata":{"displayName":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-05-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5-mini","displayName":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-05-30"}},"openai/gpt-5-nano":{"metadata":{"displayName":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-05-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5-nano","displayName":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-05-30"}},"openai/gpt-5-pro":{"metadata":{"displayName":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-10-06","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high"]},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5-pro","displayName":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5.1":{"metadata":{"displayName":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.1","displayName":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5.1-codex":{"metadata":{"displayName":"GPT-5.1 Codex","description":"Codex GPT for repository edits, code review, and practical software agents","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openai/gpt-5.1-codex","displayName":"GPT-5.1 Codex","description":"Codex GPT for repository edits, code review, and practical software agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5.1-codex-max":{"metadata":{"displayName":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openai/gpt-5.1-codex-max","displayName":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5.1-codex-mini":{"metadata":{"displayName":"GPT-5.1 Codex mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openai/gpt-5.1-codex-mini","displayName":"GPT-5.1 Codex mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5.2":{"metadata":{"displayName":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"entry":{"id":"openai/gpt-5.2","displayName":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.2-chat":{"metadata":{"displayName":"GPT-5.2 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2025-12-10","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"entry":{"id":"openai/gpt-5.2-chat","displayName":"GPT-5.2 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.2-codex":{"metadata":{"displayName":"GPT-5.2 Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openai/gpt-5.2-codex","displayName":"GPT-5.2 Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.2-pro":{"metadata":{"displayName":"GPT-5.2 Pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.2-pro","displayName":"GPT-5.2 Pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.3-codex":{"metadata":{"displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-02-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.3-codex","displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4":{"metadata":{"displayName":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.4","displayName":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4-image-2":{"metadata":{"displayName":"GPT-5.4 Image 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":272000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["image","text","pdf"],"output":["image","text"]}},"entry":{"id":"openai/gpt-5.4-image-2","displayName":"GPT-5.4 Image 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":272000,"defaultContextWindow":272000}},"openai/gpt-5.4-mini":{"metadata":{"displayName":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"entry":{"id":"openai/gpt-5.4-mini","displayName":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4-nano":{"metadata":{"displayName":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"entry":{"id":"openai/gpt-5.4-nano","displayName":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4-pro":{"metadata":{"displayName":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.4-pro","displayName":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.5":{"metadata":{"displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.5","displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-12-01"}},"openai/gpt-5.5-pro":{"metadata":{"displayName":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.5-pro","displayName":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-12-01"}},"openai/gpt-5.6-luna":{"metadata":{"displayName":"GPT-5.6 Luna","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-luna","displayName":"GPT-5.6 Luna","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-luna-pro":{"metadata":{"displayName":"GPT-5.6 Luna Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-luna-pro","displayName":"GPT-5.6 Luna Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-sol":{"metadata":{"displayName":"GPT-5.6 Sol","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-sol","displayName":"GPT-5.6 Sol","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-sol-pro":{"metadata":{"displayName":"GPT-5.6 Sol Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-sol-pro","displayName":"GPT-5.6 Sol Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-terra":{"metadata":{"displayName":"GPT-5.6 Terra","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-terra","displayName":"GPT-5.6 Terra","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-terra-pro":{"metadata":{"displayName":"GPT-5.6 Terra Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-terra-pro","displayName":"GPT-5.6 Terra Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-6-astra":{"metadata":{"displayName":"GPT-6 Astra","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-04-30","structuredOutput":true,"lastUpdated":"2026-09-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-6-astra","displayName":"GPT-6 Astra","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-04-30"}},"openai/gpt-6-astra-pro":{"metadata":{"displayName":"GPT-6 Astra Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-09-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"entry":{"id":"openai/gpt-6-astra-pro","displayName":"GPT-6 Astra Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1050000,"defaultContextWindow":1050000}},"openai/gpt-audio":{"metadata":{"displayName":"GPT Audio","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","audio"],"output":["text","audio"]}},"entry":{"id":"openai/gpt-audio","displayName":"GPT Audio","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"openai/gpt-audio-mini":{"metadata":{"displayName":"GPT Audio Mini","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","audio"],"output":["text","audio"]}},"entry":{"id":"openai/gpt-audio-mini","displayName":"GPT Audio Mini","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"openai/gpt-chat-latest":{"metadata":{"displayName":"GPT Chat Latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-05-05","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-chat-latest","displayName":"GPT Chat Latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":400000,"defaultContextWindow":400000}},"openai/gpt-oss-120b":{"metadata":{"displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-120b","displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"openai/gpt-oss-20b":{"metadata":{"displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-20b","displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"openai/gpt-oss-safeguard-20b":{"metadata":{"displayName":"GPT OSS Safeguard 20B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2025-10-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-safeguard-20b","displayName":"GPT OSS Safeguard 20B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"openai/o1":{"metadata":{"displayName":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-12-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/o1","displayName":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2023-09"}},"openai/o1-pro":{"metadata":{"displayName":"o1-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2025-03-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/o1-pro","displayName":"o1-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2023-09"}},"openai/o3":{"metadata":{"displayName":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/o3","displayName":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"openai/o3-mini":{"metadata":{"displayName":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-01-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","pdf"],"output":["text"]}},"entry":{"id":"openai/o3-mini","displayName":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"openai/o3-mini-high":{"metadata":{"displayName":"o3 Mini High","description":"O-series reasoning model for hard analysis, math, coding, and planning","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2023-10-31","structuredOutput":true,"lastUpdated":"2025-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high"]},"modalities":{"input":["text","pdf"],"output":["text"]}},"entry":{"id":"openai/o3-mini-high","displayName":"o3 Mini High","description":"O-series reasoning model for hard analysis, math, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2023-10-31"}},"openai/o3-pro":{"metadata":{"displayName":"o3-pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-06-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","pdf","image"],"output":["text"]}},"entry":{"id":"openai/o3-pro","displayName":"o3-pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"openai/o4-mini":{"metadata":{"displayName":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"entry":{"id":"openai/o4-mini","displayName":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"openai/o4-mini-high":{"metadata":{"displayName":"o4 Mini High","description":"O-series reasoning model for hard analysis, math, coding, and planning","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-06-30","structuredOutput":true,"lastUpdated":"2025-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high"]},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"entry":{"id":"openai/o4-mini-high","displayName":"o4 Mini High","description":"O-series reasoning model for hard analysis, math, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-06-30"}},"openrouter/auto":{"metadata":{"displayName":"Auto Router","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":2000000,"structuredOutput":true,"lastUpdated":"2023-11-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio","pdf","video"],"output":["text","image"]}},"entry":{"id":"openrouter/auto","displayName":"Auto Router","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000}},"openrouter/bodybuilder":{"metadata":{"displayName":"Body Builder (beta)","description":"Preview model for early access evaluation, prototyping, and compatibility testing","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"structuredOutput":false,"lastUpdated":"2025-12-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openrouter/bodybuilder","displayName":"Body Builder (beta)","description":"Preview model for early access evaluation, prototyping, and compatibility testing","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"openrouter/free":{"metadata":{"displayName":"Free Models Router","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":200000,"inputLimit":200000,"maxOutputTokens":8000,"structuredOutput":true,"lastUpdated":"2026-02-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openrouter/free","displayName":"Free Models Router","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"inputLimit":200000,"defaultContextWindow":200000,"defaultInputLimit":200000}},"openrouter/fusion":{"metadata":{"displayName":"Fusion","description":"General-purpose chat model for instruction following, writing, and analysis","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"structuredOutput":false,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openrouter/fusion","displayName":"Fusion","description":"General-purpose chat model for instruction following, writing, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"openrouter/pareto-code":{"metadata":{"displayName":"Pareto Code Router","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":200000,"structuredOutput":false,"lastUpdated":"2026-04-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openrouter/pareto-code","displayName":"Pareto Code Router","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000}},"perceptron/perceptron-mk1":{"metadata":{"displayName":"Perceptron Mk1","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":32768,"maxOutputTokens":8192,"structuredOutput":true,"lastUpdated":"2026-05-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"perceptron/perceptron-mk1","displayName":"Perceptron Mk1","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"perplexity/sonar":{"metadata":{"displayName":"Sonar","description":"Sonar search model for current answers, retrieval, and citation-backed chat","lifecycle":"active","contextWindow":127072,"maxOutputTokens":114364,"structuredOutput":false,"lastUpdated":"2025-01-27","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"perplexity/sonar","displayName":"Sonar","description":"Sonar search model for current answers, retrieval, and citation-backed chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":127072,"defaultContextWindow":127072}},"perplexity/sonar-deep-research":{"metadata":{"displayName":"Sonar Deep Research","description":"Sonar search model for current answers, retrieval, and citation-backed chat","lifecycle":"active","contextWindow":128000,"maxOutputTokens":115200,"structuredOutput":false,"lastUpdated":"2025-03-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"perplexity/sonar-deep-research","displayName":"Sonar Deep Research","description":"Sonar search model for current answers, retrieval, and citation-backed chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"perplexity/sonar-pro":{"metadata":{"displayName":"Sonar Pro","description":"Advanced Sonar search model for deeper research and cited synthesis","lifecycle":"active","contextWindow":200000,"maxOutputTokens":8000,"structuredOutput":false,"lastUpdated":"2025-03-07","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"perplexity/sonar-pro","displayName":"Sonar Pro","description":"Advanced Sonar search model for deeper research and cited synthesis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}},"perplexity/sonar-pro-search":{"metadata":{"displayName":"Sonar Pro Search","description":"Advanced Sonar search model for deeper research and cited synthesis","lifecycle":"active","contextWindow":200000,"maxOutputTokens":8000,"structuredOutput":true,"lastUpdated":"2025-10-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"perplexity/sonar-pro-search","displayName":"Sonar Pro Search","description":"Advanced Sonar search model for deeper research and cited synthesis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}},"perplexity/sonar-reasoning-pro":{"metadata":{"displayName":"Sonar Reasoning Pro","description":"Web-grounded reasoning model for multi-step research and cited answers","lifecycle":"active","contextWindow":128000,"maxOutputTokens":115200,"structuredOutput":false,"lastUpdated":"2025-03-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"perplexity/sonar-reasoning-pro","displayName":"Sonar Reasoning Pro","description":"Web-grounded reasoning model for multi-step research and cited answers","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"poolside/laguna-s-2.1":{"metadata":{"displayName":"Laguna S 2.1","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":false,"lastUpdated":"2026-07-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"poolside/laguna-s-2.1","displayName":"Laguna S 2.1","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}},"poolside/laguna-s-2.1:free":{"metadata":{"displayName":"Laguna S 2.1 (free)","description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-07-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"poolside/laguna-s-2.1:free","displayName":"Laguna S 2.1 (free)","description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"poolside/laguna-xs-2.1":{"metadata":{"displayName":"Laguna XS 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"poolside/laguna-xs-2.1","displayName":"Laguna XS 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"poolside/laguna-xs-2.1:free":{"metadata":{"displayName":"Laguna XS 2.1 (free)","description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"poolside/laguna-xs-2.1:free","displayName":"Laguna XS 2.1 (free)","description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen-2.5-72b-instruct":{"metadata":{"displayName":"Qwen2.5 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":32768,"maxOutputTokens":16384,"knowledgeCutoff":"2024-06-30","structuredOutput":true,"lastUpdated":"2024-09-19","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen-2.5-72b-instruct","displayName":"Qwen2.5 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-06-30"}},"qwen/qwen-2.5-7b-instruct":{"metadata":{"displayName":"Qwen2.5 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":32768,"maxOutputTokens":29491,"knowledgeCutoff":"2024-06-30","structuredOutput":true,"lastUpdated":"2024-10-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen-2.5-7b-instruct","displayName":"Qwen2.5 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-06-30"}},"qwen/qwen-2.5-coder-32b-instruct":{"metadata":{"displayName":"Qwen2.5 Coder 32B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":32768,"maxOutputTokens":29491,"knowledgeCutoff":"2024-06-30","structuredOutput":false,"lastUpdated":"2024-11-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen-2.5-coder-32b-instruct","displayName":"Qwen2.5 Coder 32B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-06-30"}},"qwen/qwen-plus":{"metadata":{"displayName":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-09-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen-plus","displayName":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-04"}},"qwen/qwen-plus-2025-07-28":{"metadata":{"displayName":"Qwen Plus 0728","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":32768,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-09-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen-plus-2025-07-28","displayName":"Qwen Plus 0728","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-03-31"}},"qwen/qwen2.5-vl-72b-instruct":{"metadata":{"displayName":"Qwen2.5 VL 72B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":128000,"maxOutputTokens":115200,"knowledgeCutoff":"2024-06-30","structuredOutput":true,"lastUpdated":"2025-02-01","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen2.5-vl-72b-instruct","displayName":"Qwen2.5 VL 72B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-06-30"}},"qwen/qwen3-14b":{"metadata":{"displayName":"Qwen3 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-04-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-14b","displayName":"Qwen3 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-03-31"}},"qwen/qwen3-235b-a22b":{"metadata":{"displayName":"Qwen3 235B-A22B","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2025-04","structuredOutput":false,"lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-235b-a22b","displayName":"Qwen3 235B-A22B","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen/qwen3-235b-a22b-2507":{"metadata":{"displayName":"Qwen3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"knowledgeCutoff":"2025-06-30","structuredOutput":true,"lastUpdated":"2025-07-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-235b-a22b-2507","displayName":"Qwen3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-06-30"}},"qwen/qwen3-235b-a22b-thinking-2507":{"metadata":{"displayName":"Qwen3 235B A22B Thinking 2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"knowledgeCutoff":"2025-06-30","structuredOutput":false,"lastUpdated":"2025-07-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-235b-a22b-thinking-2507","displayName":"Qwen3 235B A22B Thinking 2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-06-30"}},"qwen/qwen3-30b-a3b":{"metadata":{"displayName":"Qwen3 30B A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-04-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-30b-a3b","displayName":"Qwen3 30B A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"qwen/qwen3-30b-a3b-instruct-2507":{"metadata":{"displayName":"Qwen3 30B A3B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32000,"knowledgeCutoff":"2025-06-30","structuredOutput":true,"lastUpdated":"2025-07-29","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-30b-a3b-instruct-2507","displayName":"Qwen3 30B A3B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-06-30"}},"qwen/qwen3-30b-a3b-thinking-2507":{"metadata":{"displayName":"Qwen3 30B A3B Thinking 2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":81920,"maxOutputTokens":32768,"knowledgeCutoff":"2025-06-30","structuredOutput":false,"lastUpdated":"2025-08-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-30b-a3b-thinking-2507","displayName":"Qwen3 30B A3B Thinking 2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":81920,"defaultContextWindow":81920,"knowledgeCutoff":"2025-06-30"}},"qwen/qwen3-32b":{"metadata":{"displayName":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-32b","displayName":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen/qwen3-8b":{"metadata":{"displayName":"Qwen3 8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2025-03-31","structuredOutput":false,"lastUpdated":"2025-04-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-8b","displayName":"Qwen3 8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-03-31"}},"qwen/qwen3-coder":{"metadata":{"displayName":"Qwen3 Coder 480B A35B","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-06-30","structuredOutput":true,"lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-coder","displayName":"Qwen3 Coder 480B A35B","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-06-30"}},"qwen/qwen3-coder-30b-a3b-instruct":{"metadata":{"displayName":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-coder-30b-a3b-instruct","displayName":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen/qwen3-coder-flash":{"metadata":{"displayName":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":false,"lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-coder-flash","displayName":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen/qwen3-coder-next":{"metadata":{"displayName":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"knowledgeCutoff":"2025-09","structuredOutput":true,"lastUpdated":"2026-02-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-coder-next","displayName":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-09"}},"qwen/qwen3-coder-plus":{"metadata":{"displayName":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-coder-plus","displayName":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen/qwen3-max":{"metadata":{"displayName":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-09-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-max","displayName":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen/qwen3-max-thinking":{"metadata":{"displayName":"Qwen3 Max Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-09","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-max-thinking","displayName":"Qwen3 Max Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen3-next-80b-a3b-instruct":{"metadata":{"displayName":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-next-80b-a3b-instruct","displayName":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen/qwen3-next-80b-a3b-thinking":{"metadata":{"displayName":"Qwen3-Next 80B-A3B (Thinking)","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-09","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-next-80b-a3b-thinking","displayName":"Qwen3-Next 80B-A3B (Thinking)","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen/qwen3-vl-235b-a22b-instruct":{"metadata":{"displayName":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-09-23","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen3-vl-235b-a22b-instruct","displayName":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-03-31"}},"qwen/qwen3-vl-235b-a22b-thinking":{"metadata":{"displayName":"Qwen3 VL 235B A22B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-09-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen3-vl-235b-a22b-thinking","displayName":"Qwen3 VL 235B A22B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-03-31"}},"qwen/qwen3-vl-30b-a3b-instruct":{"metadata":{"displayName":"Qwen3 VL 30B A3B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-10-06","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen3-vl-30b-a3b-instruct","displayName":"Qwen3 VL 30B A3B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-03-31"}},"qwen/qwen3-vl-30b-a3b-thinking":{"metadata":{"displayName":"Qwen3 VL 30B A3B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-10-06","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen3-vl-30b-a3b-thinking","displayName":"Qwen3 VL 30B A3B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-03-31"}},"qwen/qwen3-vl-32b-instruct":{"metadata":{"displayName":"Qwen3 VL 32B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2025-10-23","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen3-vl-32b-instruct","displayName":"Qwen3 VL 32B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"qwen/qwen3-vl-8b-instruct":{"metadata":{"displayName":"Qwen3 VL 8B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2025-10-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["image","text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-vl-8b-instruct","displayName":"Qwen3 VL 8B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen3-vl-8b-thinking":{"metadata":{"displayName":"Qwen3 VL 8B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2025-10-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["image","text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-vl-8b-thinking","displayName":"Qwen3 VL 8B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"qwen/qwen3.5-122b-a10b":{"metadata":{"displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-122b-a10b","displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen3.5-27b":{"metadata":{"displayName":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-27b","displayName":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen3.5-35b-a3b":{"metadata":{"displayName":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-35b-a3b","displayName":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen3.5-397b-a17b":{"metadata":{"displayName":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2026-02-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-397b-a17b","displayName":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen3.5-9b":{"metadata":{"displayName":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-9b","displayName":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen3.5-flash-02-23":{"metadata":{"displayName":"Qwen3.5-Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-25","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-flash-02-23","displayName":"Qwen3.5-Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen/qwen3.5-plus-02-15":{"metadata":{"displayName":"Qwen3.5 Plus 2026-02-15","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-02-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-plus-02-15","displayName":"Qwen3.5 Plus 2026-02-15","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen/qwen3.5-plus-20260420":{"metadata":{"displayName":"Qwen3.5 Plus 2026-04-20","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-plus-20260420","displayName":"Qwen3.5 Plus 2026-04-20","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen/qwen3.6-27b":{"metadata":{"displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.6-27b","displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen3.6-35b-a3b":{"metadata":{"displayName":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2026-04-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.6-35b-a3b","displayName":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen3.6-flash":{"metadata":{"displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.6-flash","displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen/qwen3.6-max-preview":{"metadata":{"displayName":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-04-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3.6-max-preview","displayName":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen/qwen3.6-plus":{"metadata":{"displayName":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.6-plus","displayName":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen/qwen3.7-flash":{"metadata":{"displayName":"Qwen3.7 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"inputLimit":991000,"maxOutputTokens":65536,"structuredOutput":false,"lastUpdated":"2026-07-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.7-flash","displayName":"Qwen3.7 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"inputLimit":991000,"defaultContextWindow":1000000,"defaultInputLimit":991000}},"qwen/qwen3.7-max":{"metadata":{"displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3.7-max","displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen/qwen3.7-plus":{"metadata":{"displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-06-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen3.7-plus","displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen/qwen3.8-2.4t-a95b":{"metadata":{"displayName":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3.8-2.4t-a95b","displayName":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"qwen/qwen3.8-27b":{"metadata":{"displayName":"Qwen3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.8-27b","displayName":"Qwen3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen/qwen3.8-flash":{"metadata":{"displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.8-flash","displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen/qwen3.8-max-0902":{"metadata":{"displayName":"Qwen3.8 Max 0902","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.8-max-0902","displayName":"Qwen3.8 Max 0902","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"rekaai/reka-edge":{"metadata":{"displayName":"Reka Edge","description":"Multimodal model for analyzing text, images, documents, and rich media","lifecycle":"active","contextWindow":16384,"maxOutputTokens":14745,"structuredOutput":true,"lastUpdated":"2026-03-20","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["image","text","video"],"output":["text"]}},"entry":{"id":"rekaai/reka-edge","displayName":"Reka Edge","description":"Multimodal model for analyzing text, images, documents, and rich media","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":16384,"defaultContextWindow":16384}},"rekaai/reka-flash-3":{"metadata":{"displayName":"Reka Flash 3","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":65536,"maxOutputTokens":58982,"knowledgeCutoff":"2025-01-31","structuredOutput":true,"lastUpdated":"2025-03-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"rekaai/reka-flash-3","displayName":"Reka Flash 3","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-01-31"}},"relace/relace-apply-3":{"metadata":{"displayName":"Relace Apply 3","description":"General-purpose chat model for instruction following, writing, and analysis","lifecycle":"active","contextWindow":256000,"maxOutputTokens":128000,"structuredOutput":false,"lastUpdated":"2025-09-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"relace/relace-apply-3","displayName":"Relace Apply 3","description":"General-purpose chat model for instruction following, writing, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"relace/relace-search":{"metadata":{"displayName":"Relace Search","description":"Tool-capable chat model for instruction following and agentic application workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":128000,"structuredOutput":false,"lastUpdated":"2025-12-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"relace/relace-search","displayName":"Relace Search","description":"Tool-capable chat model for instruction following and agentic application workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"sakana/fugu-max":{"metadata":{"displayName":"Fugu Max","description":"Multi-agent model for routing expert agents across complex analytical tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-09-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"sakana/fugu-max","displayName":"Fugu Max","description":"Multi-agent model for routing expert agents across complex analytical tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"sakana/fugu-ultra":{"metadata":{"displayName":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-06-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"sakana/fugu-ultra","displayName":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"sakana/fugu-ultra-v2":{"metadata":{"displayName":"Fugu Ultra v2","description":"Quality-first multi-agent model for hard research, analysis, and competitions","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-08-28","structuredOutput":true,"lastUpdated":"2026-09-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"sakana/fugu-ultra-v2","displayName":"Fugu Ultra v2","description":"Quality-first multi-agent model for hard research, analysis, and competitions","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-08-28"}},"sakana/sakana-namazu":{"metadata":{"displayName":"Sakana Namazu","description":"Multi-agent model for routing expert agents across complex analytical tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-08-03","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"sakana/sakana-namazu","displayName":"Sakana Namazu","description":"Multi-agent model for routing expert agents across complex analytical tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","high"],"contextWindow":262144,"defaultContextWindow":262144}},"sao10k/l3-lunaris-8b":{"metadata":{"displayName":"Llama 3 8B Lunaris","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":8192,"maxOutputTokens":7372,"knowledgeCutoff":"2023-12-31","structuredOutput":true,"lastUpdated":"2024-08-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"sao10k/l3-lunaris-8b","displayName":"Llama 3 8B Lunaris","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2023-12-31"}},"sao10k/l3.1-euryale-70b":{"metadata":{"displayName":"Llama 3.1 Euryale 70B v2.2","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2023-12-31","structuredOutput":true,"lastUpdated":"2024-08-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"sao10k/l3.1-euryale-70b","displayName":"Llama 3.1 Euryale 70B v2.2","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12-31"}},"sao10k/l3.3-euryale-70b":{"metadata":{"displayName":"Llama 3.3 Euryale 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2023-12-31","structuredOutput":true,"lastUpdated":"2024-12-18","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"sao10k/l3.3-euryale-70b","displayName":"Llama 3.3 Euryale 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12-31"}},"stepfun/step-3.5-flash":{"metadata":{"displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":false,"lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"stepfun/step-3.5-flash","displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"stepfun/step-3.7-flash":{"metadata":{"displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","lifecycle":"active","contextWindow":262144,"inputLimit":256000,"maxOutputTokens":230400,"knowledgeCutoff":"2026-03-01","structuredOutput":true,"lastUpdated":"2026-05-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"stepfun/step-3.7-flash","displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":262144,"inputLimit":256000,"defaultContextWindow":262144,"defaultInputLimit":256000,"knowledgeCutoff":"2026-03-01"}},"tencent/hunyuan-a13b-instruct":{"metadata":{"displayName":"Hunyuan A13B Instruct","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-07-08","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hunyuan-a13b-instruct","displayName":"Hunyuan A13B Instruct","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-03-31"}},"tencent/hy-mt2-1.8b":{"metadata":{"displayName":"Hy-MT2-1.8B","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":8192,"maxOutputTokens":4096,"structuredOutput":false,"lastUpdated":"2026-08-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy-mt2-1.8b","displayName":"Hy-MT2-1.8B","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"tencent/hy-mt2-30b-a3b":{"metadata":{"displayName":"Hy-MT2-30B-A3B","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":8192,"maxOutputTokens":4096,"structuredOutput":true,"lastUpdated":"2026-08-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy-mt2-30b-a3b","displayName":"Hy-MT2-30B-A3B","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"tencent/hy-mt2-7b":{"metadata":{"displayName":"Hy-MT2-7B","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":8192,"maxOutputTokens":4096,"structuredOutput":true,"lastUpdated":"2026-08-19","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy-mt2-7b","displayName":"Hy-MT2-7B","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"tencent/hy3":{"metadata":{"displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":262144,"inputLimit":192000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-07-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy3","displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","high"],"contextWindow":262144,"inputLimit":192000,"defaultContextWindow":262144,"defaultInputLimit":192000}},"tencent/hy3-preview":{"metadata":{"displayName":"Hy3 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":false,"lastUpdated":"2026-04-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy3-preview","displayName":"Hy3 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","high"],"contextWindow":262144,"defaultContextWindow":262144}},"tencent/hy4-preview":{"metadata":{"displayName":"Hy4 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":64000,"structuredOutput":true,"lastUpdated":"2026-08-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy4-preview","displayName":"Hy4 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","high"],"contextWindow":1048576,"defaultContextWindow":1048576}},"thedrummer/cydonia-24b-v4.1":{"metadata":{"displayName":"Cydonia 24B V4.1","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"knowledgeCutoff":"2024-04-30","structuredOutput":true,"lastUpdated":"2025-09-27","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"thedrummer/cydonia-24b-v4.1","displayName":"Cydonia 24B V4.1","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04-30"}},"thedrummer/skyfall-36b-v2":{"metadata":{"displayName":"Skyfall 36B V2","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","lifecycle":"active","contextWindow":32768,"maxOutputTokens":29491,"knowledgeCutoff":"2024-06-30","structuredOutput":true,"lastUpdated":"2025-03-10","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"thedrummer/skyfall-36b-v2","displayName":"Skyfall 36B V2","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-06-30"}},"thedrummer/unslopnemo-12b":{"metadata":{"displayName":"UnslopNemo 12B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":819200,"knowledgeCutoff":"2024-04-30","structuredOutput":true,"lastUpdated":"2024-11-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"thedrummer/unslopnemo-12b","displayName":"UnslopNemo 12B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000,"knowledgeCutoff":"2024-04-30"}},"thinkingmachines/inkling":{"metadata":{"displayName":"Inkling","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":471859,"structuredOutput":false,"lastUpdated":"2026-07-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","minimal","low","medium","high","max"]},"modalities":{"input":["text","image","audio"],"output":["text"]}},"entry":{"id":"thinkingmachines/inkling","displayName":"Inkling","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","minimal","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"thinkingmachines/inkling-small":{"metadata":{"displayName":"Inkling Small","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":262144,"structuredOutput":false,"lastUpdated":"2026-07-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","minimal","low","medium","high","max"]},"modalities":{"input":["text","image","audio"],"output":["text"]}},"entry":{"id":"thinkingmachines/inkling-small","displayName":"Inkling Small","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","minimal","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"thinkingmachines/inkling-small:free":{"metadata":{"displayName":"Inkling Small (free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":262144,"structuredOutput":false,"lastUpdated":"2026-07-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","minimal","low","medium","high","max"]},"modalities":{"input":["text","image","audio"],"output":["text"]}},"entry":{"id":"thinkingmachines/inkling-small:free","displayName":"Inkling Small (free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","minimal","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"thinkingmachines/inkling:free":{"metadata":{"displayName":"Inkling (free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":262144,"structuredOutput":false,"lastUpdated":"2026-07-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","minimal","low","medium","high","max"]},"modalities":{"input":["text","image","audio"],"output":["text"]}},"entry":{"id":"thinkingmachines/inkling:free","displayName":"Inkling (free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","minimal","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"undi95/remm-slerp-l2-13b":{"metadata":{"displayName":"ReMM SLERP 13B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","lifecycle":"active","contextWindow":6144,"maxOutputTokens":5529,"knowledgeCutoff":"2023-06-30","structuredOutput":true,"lastUpdated":"2023-07-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"undi95/remm-slerp-l2-13b","displayName":"ReMM SLERP 13B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":6144,"defaultContextWindow":6144,"knowledgeCutoff":"2023-06-30"}},"upstage/solar-pro-3":{"metadata":{"displayName":"Solar Pro 3","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"structuredOutput":true,"lastUpdated":"2026-01-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"upstage/solar-pro-3","displayName":"Solar Pro 3","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"upstage/solar-pro4":{"metadata":{"displayName":"Solar Pro 4","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":524288,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-10","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"upstage/solar-pro4","displayName":"Solar Pro 4","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":524288,"defaultContextWindow":524288}},"writer/palmyra-x5":{"metadata":{"displayName":"Palmyra X5","description":"General-purpose chat model for instruction following, writing, and analysis","lifecycle":"active","contextWindow":1040000,"maxOutputTokens":8192,"structuredOutput":false,"lastUpdated":"2026-01-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"writer/palmyra-x5","displayName":"Palmyra X5","description":"General-purpose chat model for instruction following, writing, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1040000,"defaultContextWindow":1040000}},"x-ai/grok-4.20":{"metadata":{"displayName":"Grok 4.20","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":1800000,"knowledgeCutoff":"2025-09-01","structuredOutput":true,"lastUpdated":"2026-03-31","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"x-ai/grok-4.20","displayName":"Grok 4.20","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000,"knowledgeCutoff":"2025-09-01"}},"x-ai/grok-4.20-multi-agent":{"metadata":{"displayName":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":1800000,"knowledgeCutoff":"2025-09-01","structuredOutput":true,"lastUpdated":"2026-03-31","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"x-ai/grok-4.20-multi-agent","displayName":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":2000000,"defaultContextWindow":2000000,"knowledgeCutoff":"2025-09-01"}},"x-ai/grok-4.3":{"metadata":{"displayName":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":900000,"structuredOutput":true,"lastUpdated":"2026-04-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"x-ai/grok-4.3","displayName":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000}},"x-ai/grok-4.5":{"metadata":{"displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","lifecycle":"active","contextWindow":500000,"maxOutputTokens":450000,"structuredOutput":true,"lastUpdated":"2026-07-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"x-ai/grok-4.5","displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":500000,"defaultContextWindow":500000}},"x-ai/grok-4.6":{"metadata":{"displayName":"Grok 4.6","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":500000,"maxOutputTokens":450000,"knowledgeCutoff":"2026-02-01","structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"x-ai/grok-4.6","displayName":"Grok 4.6","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":500000,"defaultContextWindow":500000,"knowledgeCutoff":"2026-02-01"}},"x-ai/grok-build-0.1":{"metadata":{"displayName":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","lifecycle":"active","contextWindow":256000,"maxOutputTokens":230400,"structuredOutput":true,"lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"x-ai/grok-build-0.1","displayName":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"xiaomi/mimo-v2.5":{"metadata":{"displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]}},"entry":{"id":"xiaomi/mimo-v2.5","displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2024-12"}},"xiaomi/mimo-v2.5-pro":{"metadata":{"displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"xiaomi/mimo-v2.5-pro","displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2024-12"}},"z-ai/glm-4.5":{"metadata":{"displayName":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","lifecycle":"active","contextWindow":131072,"maxOutputTokens":98304,"knowledgeCutoff":"2025-04","structuredOutput":false,"lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.5","displayName":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"z-ai/glm-4.5-air":{"metadata":{"displayName":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":98304,"knowledgeCutoff":"2025-04","structuredOutput":false,"lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.5-air","displayName":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"z-ai/glm-4.5v":{"metadata":{"displayName":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":65536,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","structuredOutput":false,"lastUpdated":"2025-08-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.5v","displayName":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-04"}},"z-ai/glm-4.6":{"metadata":{"displayName":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-09-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.6","displayName":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"z-ai/glm-4.6v":{"metadata":{"displayName":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","structuredOutput":false,"lastUpdated":"2025-12-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.6v","displayName":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"z-ai/glm-4.7":{"metadata":{"displayName":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-12-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.7","displayName":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"z-ai/glm-4.7-flash":{"metadata":{"displayName":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","lifecycle":"active","contextWindow":200000,"maxOutputTokens":117964,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.7-flash","displayName":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-04"}},"z-ai/glm-5":{"metadata":{"displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-5","displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"z-ai/glm-5-turbo":{"metadata":{"displayName":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","lifecycle":"active","contextWindow":202752,"maxOutputTokens":131072,"structuredOutput":false,"lastUpdated":"2026-03-16","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-5-turbo","displayName":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"z-ai/glm-5.1":{"metadata":{"displayName":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","lifecycle":"active","contextWindow":204800,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-5.1","displayName":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"z-ai/glm-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"z-ai/glm-5.3":{"metadata":{"displayName":"GLM-5.3","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":1310720,"maxOutputTokens":943717,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-5.3","displayName":"GLM-5.3","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1310720,"defaultContextWindow":1310720}},"z-ai/glm-5.3-flash":{"metadata":{"displayName":"GLM-5.3-Flash","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":1310720,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"z-ai/glm-5.3-flash","displayName":"GLM-5.3-Flash","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1310720,"defaultContextWindow":1310720}},"z-ai/glm-5v-turbo":{"metadata":{"displayName":"GLM-5V-Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","lifecycle":"active","contextWindow":202752,"maxOutputTokens":131072,"structuredOutput":false,"lastUpdated":"2026-04-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["image","text","video"],"output":["text"]}},"entry":{"id":"z-ai/glm-5v-turbo","displayName":"GLM-5V-Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}}}},"alibaba":{"baseUrl":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","label":"Alibaba","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["qwen3.7-plus","deepseek-v4-flash-0731","glm-5.2","qvq-max","qwen-flash","qwen-max","qwen-omni-turbo","qwen-omni-turbo-realtime","qwen-plus","qwen-plus-character-ja","qwen-turbo","qwen-vl-max","qwen-vl-plus","qwen2-5-14b-instruct","qwen2-5-32b-instruct","qwen2-5-72b-instruct","qwen2-5-7b-instruct","qwen2-5-omni-7b","qwen2-5-vl-72b-instruct","qwen2-5-vl-7b-instruct","qwen3-14b","qwen3-235b-a22b","qwen3-32b","qwen3-8b","qwen3-coder-30b-a3b-instruct","qwen3-coder-480b-a35b-instruct","qwen3-coder-flash","qwen3-coder-plus","qwen3-max","qwen3-next-80b-a3b-instruct","qwen3-next-80b-a3b-thinking","qwen3-omni-flash","qwen3-omni-flash-realtime","qwen3-vl-235b-a22b","qwen3-vl-30b-a3b","qwen3-vl-plus","qwen3.5-122b-a10b","qwen3.5-27b","qwen3.5-35b-a3b","qwen3.5-397b-a17b","qwen3.5-plus","qwen3.6-27b","qwen3.6-35b-a3b","qwen3.6-flash","qwen3.6-max-preview","qwen3.6-plus","qwen3.7-max","qwen3.8-flash","qwen3.8-max","qwq-plus"],"models":{"deepseek-v4-flash-0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash-0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"glm-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","minimal","low","medium","high","xhigh","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","minimal","low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qvq-max":{"metadata":{"displayName":"QVQ Max","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-03-25","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qvq-max","displayName":"QVQ Max","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen-flash":{"metadata":{"displayName":"Qwen Flash","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-flash","displayName":"Qwen Flash","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-04"}},"qwen-max":{"metadata":{"displayName":"Qwen Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","lifecycle":"active","contextWindow":32768,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-01-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-max","displayName":"Qwen Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-04"}},"qwen-mt-plus":{"metadata":{"displayName":"Qwen-MT Plus","description":"Translation model for multilingual conversion, localization, and cross-language workflows","lifecycle":"active","contextWindow":16384,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-mt-plus","displayName":"Qwen-MT Plus","description":"Translation model for multilingual conversion, localization, and cross-language workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16384,"defaultContextWindow":16384,"knowledgeCutoff":"2024-04"}},"qwen-mt-turbo":{"metadata":{"displayName":"Qwen-MT Turbo","description":"Translation model for multilingual conversion, localization, and cross-language workflows","lifecycle":"active","contextWindow":16384,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-mt-turbo","displayName":"Qwen-MT Turbo","description":"Translation model for multilingual conversion, localization, and cross-language workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16384,"defaultContextWindow":16384,"knowledgeCutoff":"2024-04"}},"qwen-omni-turbo":{"metadata":{"displayName":"Qwen-Omni Turbo","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","lifecycle":"active","contextWindow":32768,"maxOutputTokens":2048,"knowledgeCutoff":"2024-04","lastUpdated":"2025-03-26","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","audio","video"],"output":["text","audio"]}},"entry":{"id":"qwen-omni-turbo","displayName":"Qwen-Omni Turbo","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-04"}},"qwen-omni-turbo-realtime":{"metadata":{"displayName":"Qwen-Omni Turbo Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","lifecycle":"active","contextWindow":32768,"maxOutputTokens":2048,"knowledgeCutoff":"2024-04","lastUpdated":"2025-05-08","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","audio"],"output":["text","audio"]}},"entry":{"id":"qwen-omni-turbo-realtime","displayName":"Qwen-Omni Turbo Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-04"}},"qwen-plus":{"metadata":{"displayName":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","lastUpdated":"2025-09-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-plus","displayName":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-04"}},"qwen-plus-character-ja":{"metadata":{"displayName":"Qwen Plus Character (Japanese)","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":8192,"maxOutputTokens":512,"knowledgeCutoff":"2024-04","lastUpdated":"2024-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-plus-character-ja","displayName":"Qwen Plus Character (Japanese)","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2024-04"}},"qwen-turbo":{"metadata":{"displayName":"Qwen Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":16384,"knowledgeCutoff":"2024-04","lastUpdated":"2025-04-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-turbo","displayName":"Qwen Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-04"}},"qwen-vl-max":{"metadata":{"displayName":"Qwen-VL Max","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-08-13","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen-vl-max","displayName":"Qwen-VL Max","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen-vl-ocr":{"metadata":{"displayName":"Qwen-VL OCR","description":"OCR model for extracting structured text from documents and screenshots","lifecycle":"active","contextWindow":34096,"maxOutputTokens":4096,"knowledgeCutoff":"2024-04","lastUpdated":"2025-04-13","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen-vl-ocr","displayName":"Qwen-VL OCR","description":"OCR model for extracting structured text from documents and screenshots","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":34096,"defaultContextWindow":34096,"knowledgeCutoff":"2024-04"}},"qwen-vl-plus":{"metadata":{"displayName":"Qwen-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-08-15","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen-vl-plus","displayName":"Qwen-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-14b-instruct":{"metadata":{"displayName":"Qwen2.5 14B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-14b-instruct","displayName":"Qwen2.5 14B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-32b-instruct":{"metadata":{"displayName":"Qwen2.5 32B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-32b-instruct","displayName":"Qwen2.5 32B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-72b-instruct":{"metadata":{"displayName":"Qwen2.5 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-72b-instruct","displayName":"Qwen2.5 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-7b-instruct":{"metadata":{"displayName":"Qwen2.5 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-7b-instruct","displayName":"Qwen2.5 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-omni-7b":{"metadata":{"displayName":"Qwen2.5-Omni 7B","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","lifecycle":"active","contextWindow":32768,"maxOutputTokens":2048,"knowledgeCutoff":"2024-04","lastUpdated":"2024-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","audio","video"],"output":["text","audio"]}},"entry":{"id":"qwen2-5-omni-7b","displayName":"Qwen2.5-Omni 7B","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-04"}},"qwen2-5-vl-72b-instruct":{"metadata":{"displayName":"Qwen2.5-VL 72B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen2-5-vl-72b-instruct","displayName":"Qwen2.5-VL 72B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-vl-7b-instruct":{"metadata":{"displayName":"Qwen2.5-VL 7B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen2-5-vl-7b-instruct","displayName":"Qwen2.5-VL 7B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen3-14b":{"metadata":{"displayName":"Qwen3 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-14b","displayName":"Qwen3 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-235b-a22b":{"metadata":{"displayName":"Qwen3 235B-A22B","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-235b-a22b","displayName":"Qwen3 235B-A22B","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-32b":{"metadata":{"displayName":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-32b","displayName":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-8b":{"metadata":{"displayName":"Qwen3 8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-8b","displayName":"Qwen3 8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-asr-flash":{"metadata":{"displayName":"Qwen3-ASR Flash","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","contextWindow":53248,"maxOutputTokens":4096,"knowledgeCutoff":"2024-04","lastUpdated":"2025-09-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"qwen3-asr-flash","displayName":"Qwen3-ASR Flash","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":53248,"defaultContextWindow":53248,"knowledgeCutoff":"2024-04"}},"qwen3-coder-30b-a3b-instruct":{"metadata":{"displayName":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-30b-a3b-instruct","displayName":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3-coder-480b-a35b-instruct":{"metadata":{"displayName":"Qwen3-Coder 480B-A35B Instruct","description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-480b-a35b-instruct","displayName":"Qwen3-Coder 480B-A35B Instruct","description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3-coder-flash":{"metadata":{"displayName":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-flash","displayName":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3-coder-plus":{"metadata":{"displayName":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-plus","displayName":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-04"}},"qwen3-livetranslate-flash-realtime":{"metadata":{"displayName":"Qwen3-LiveTranslate Flash Realtime","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":53248,"maxOutputTokens":4096,"knowledgeCutoff":"2024-04","lastUpdated":"2025-09-22","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","audio","video"],"output":["text","audio"]}},"entry":{"id":"qwen3-livetranslate-flash-realtime","displayName":"Qwen3-LiveTranslate Flash Realtime","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":53248,"defaultContextWindow":53248,"knowledgeCutoff":"2024-04"}},"qwen3-max":{"metadata":{"displayName":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-max","displayName":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3-next-80b-a3b-instruct":{"metadata":{"displayName":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-next-80b-a3b-instruct","displayName":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-next-80b-a3b-thinking":{"metadata":{"displayName":"Qwen3-Next 80B-A3B (Thinking)","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-next-80b-a3b-thinking","displayName":"Qwen3-Next 80B-A3B (Thinking)","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-omni-flash":{"metadata":{"displayName":"Qwen3-Omni Flash","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","lifecycle":"active","contextWindow":65536,"maxOutputTokens":16384,"knowledgeCutoff":"2024-04","lastUpdated":"2025-09-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video"],"output":["text","audio"]}},"entry":{"id":"qwen3-omni-flash","displayName":"Qwen3-Omni Flash","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2024-04"}},"qwen3-omni-flash-realtime":{"metadata":{"displayName":"Qwen3-Omni Flash Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","lifecycle":"active","contextWindow":65536,"maxOutputTokens":16384,"knowledgeCutoff":"2024-04","lastUpdated":"2025-09-15","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","audio","video"],"output":["text","audio"]}},"entry":{"id":"qwen3-omni-flash-realtime","displayName":"Qwen3-Omni Flash Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2024-04"}},"qwen3-vl-235b-a22b":{"metadata":{"displayName":"Qwen3-VL 235B-A22B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen3-vl-235b-a22b","displayName":"Qwen3-VL 235B-A22B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-vl-30b-a3b":{"metadata":{"displayName":"Qwen3-VL 30B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen3-vl-30b-a3b","displayName":"Qwen3-VL 30B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-vl-plus":{"metadata":{"displayName":"Qwen3-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen3-vl-plus","displayName":"Qwen3-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3.5-122b-a10b":{"metadata":{"displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"qwen3.5-122b-a10b","displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen3.5-27b":{"metadata":{"displayName":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"qwen3.5-27b","displayName":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen3.5-35b-a3b":{"metadata":{"displayName":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"qwen3.5-35b-a3b","displayName":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen3.5-397b-a17b":{"metadata":{"displayName":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"qwen3.5-397b-a17b","displayName":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen3.5-plus":{"metadata":{"displayName":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.5-plus","displayName":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.6-27b":{"metadata":{"displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"qwen3.6-27b","displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen3.6-35b-a3b":{"metadata":{"displayName":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"qwen3.6-35b-a3b","displayName":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen3.6-flash":{"metadata":{"displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-flash","displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.6-max-preview":{"metadata":{"displayName":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-04-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3.6-max-preview","displayName":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3.6-plus":{"metadata":{"displayName":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-plus","displayName":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.7-max":{"metadata":{"displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3.7-max","displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.7-plus":{"metadata":{"displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-06-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.7-plus","displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.8-flash":{"metadata":{"displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.8-flash","displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.8-max":{"metadata":{"displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-03","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"qwen3.8-max","displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwq-plus":{"metadata":{"displayName":"QwQ Plus","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-03-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwq-plus","displayName":"QwQ Plus","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}}}},"alibaba-cn":{"baseUrl":"https://dashscope.aliyuncs.com/compatible-mode/v1","label":"Alibaba (China)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["qwen3.8-max","deepseek-r1","deepseek-r1-0528","deepseek-r1-distill-llama-70b","deepseek-r1-distill-llama-8b","deepseek-r1-distill-qwen-1-5b","deepseek-r1-distill-qwen-14b","deepseek-r1-distill-qwen-32b","deepseek-r1-distill-qwen-7b","deepseek-v3","deepseek-v3-1","deepseek-v3-2-exp","deepseek-v4-flash","deepseek-v4-pro","glm-5","glm-5.1","glm-5.2","kimi-k2-thinking","kimi-k2.5","kimi-k2.6","kimi/kimi-k2.5","MiniMax-M2.5","MiniMax/MiniMax-M2.7","moonshot-kimi-k2-instruct","qvq-max","qwen-deep-research","qwen-doc-turbo","qwen-flash","qwen-long","qwen-math-plus","qwen-math-turbo","qwen-max","qwen-omni-turbo","qwen-omni-turbo-realtime","qwen-plus","qwen-plus-character","qwen-turbo","qwen-vl-max","qwen-vl-plus","qwen2-5-14b-instruct","qwen2-5-32b-instruct","qwen2-5-72b-instruct","qwen2-5-7b-instruct","qwen2-5-coder-32b-instruct","qwen2-5-coder-7b-instruct","qwen2-5-math-72b-instruct","qwen2-5-math-7b-instruct","qwen2-5-omni-7b","qwen2-5-vl-72b-instruct","qwen2-5-vl-7b-instruct","qwen3-14b","qwen3-235b-a22b","qwen3-32b","qwen3-8b","qwen3-coder-30b-a3b-instruct","qwen3-coder-480b-a35b-instruct","qwen3-coder-flash","qwen3-coder-plus","qwen3-max","qwen3-next-80b-a3b-instruct","qwen3-next-80b-a3b-thinking","qwen3-omni-flash","qwen3-omni-flash-realtime","qwen3-vl-235b-a22b","qwen3-vl-30b-a3b","qwen3-vl-plus","qwen3.5-397b-a17b","qwen3.5-flash","qwen3.5-plus","qwen3.6-flash","qwen3.6-max-preview","qwen3.6-plus","qwen3.7-flash","qwen3.7-max","qwen3.7-plus","qwen3.8-flash","qwq-32b","qwq-plus","siliconflow/deepseek-r1-0528","siliconflow/deepseek-v3-0324","siliconflow/deepseek-v3.1-terminus","siliconflow/deepseek-v3.2"],"models":{"deepseek-r1":{"metadata":{"displayName":"DeepSeek R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-r1","displayName":"DeepSeek R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"deepseek-r1-0528":{"metadata":{"displayName":"DeepSeek R1 0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"lastUpdated":"2025-05-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-r1-0528","displayName":"DeepSeek R1 0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"deepseek-r1-distill-llama-70b":{"metadata":{"displayName":"DeepSeek R1 Distill Llama 70B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","lifecycle":"active","contextWindow":32768,"maxOutputTokens":16384,"lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-r1-distill-llama-70b","displayName":"DeepSeek R1 Distill Llama 70B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"deepseek-r1-distill-llama-8b":{"metadata":{"displayName":"DeepSeek R1 Distill Llama 8B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","lifecycle":"active","contextWindow":32768,"maxOutputTokens":16384,"lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-r1-distill-llama-8b","displayName":"DeepSeek R1 Distill Llama 8B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"deepseek-r1-distill-qwen-1-5b":{"metadata":{"displayName":"DeepSeek R1 Distill Qwen 1.5B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":32768,"maxOutputTokens":16384,"lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-r1-distill-qwen-1-5b","displayName":"DeepSeek R1 Distill Qwen 1.5B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"deepseek-r1-distill-qwen-14b":{"metadata":{"displayName":"DeepSeek R1 Distill Qwen 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":32768,"maxOutputTokens":16384,"lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-r1-distill-qwen-14b","displayName":"DeepSeek R1 Distill Qwen 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"deepseek-r1-distill-qwen-32b":{"metadata":{"displayName":"DeepSeek R1 Distill Qwen 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":32768,"maxOutputTokens":16384,"lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-r1-distill-qwen-32b","displayName":"DeepSeek R1 Distill Qwen 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"deepseek-r1-distill-qwen-7b":{"metadata":{"displayName":"DeepSeek R1 Distill Qwen 7B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":32768,"maxOutputTokens":16384,"lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-r1-distill-qwen-7b","displayName":"DeepSeek R1 Distill Qwen 7B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"deepseek-v3":{"metadata":{"displayName":"DeepSeek V3","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":65536,"maxOutputTokens":8192,"lastUpdated":"2024-12-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v3","displayName":"DeepSeek V3","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536}},"deepseek-v3-1":{"metadata":{"displayName":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v3-1","displayName":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"deepseek-v3-2-exp":{"metadata":{"displayName":"DeepSeek V3.2 Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v3-2-exp","displayName":"DeepSeek V3.2 Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash","displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-pro","displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"glm-5":{"metadata":{"displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":16384,"lastUpdated":"2026-02-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5","displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"glm-5.1":{"metadata":{"displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-04-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.1","displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"glm-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"kimi-k2-thinking":{"metadata":{"displayName":"Moonshot Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-11-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"kimi-k2-thinking","displayName":"Moonshot Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"kimi-k2.5":{"metadata":{"displayName":"Moonshot Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","structuredOutput":false,"lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.5","displayName":"Moonshot Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k2.6":{"metadata":{"displayName":"Moonshot Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"knowledgeCutoff":"2025-01","structuredOutput":false,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.6","displayName":"Moonshot Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi/kimi-k2.5":{"metadata":{"displayName":"kimi/kimi-k2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi/kimi-k2.5","displayName":"kimi/kimi-k2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"MiniMax-M2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.5","displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax/MiniMax-M2.7":{"metadata":{"displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax/MiniMax-M2.7","displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"moonshot-kimi-k2-instruct":{"metadata":{"displayName":"Moonshot Kimi K2 Instruct","description":"Kimi model for long-context chat, coding, and agentic reasoning","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"structuredOutput":false,"lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshot-kimi-k2-instruct","displayName":"Moonshot Kimi K2 Instruct","description":"Kimi model for long-context chat, coding, and agentic reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"qvq-max":{"metadata":{"displayName":"QVQ Max","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-03-25","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qvq-max","displayName":"QVQ Max","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen-deep-research":{"metadata":{"displayName":"Qwen Deep Research","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","lastUpdated":"2024-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-deep-research","displayName":"Qwen Deep Research","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-04"}},"qwen-doc-turbo":{"metadata":{"displayName":"Qwen Doc Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-doc-turbo","displayName":"Qwen Doc Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen-flash":{"metadata":{"displayName":"Qwen Flash","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-flash","displayName":"Qwen Flash","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-04"}},"qwen-long":{"metadata":{"displayName":"Qwen Long","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":10000000,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-01-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-long","displayName":"Qwen Long","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":10000000,"defaultContextWindow":10000000,"knowledgeCutoff":"2024-04"}},"qwen-math-plus":{"metadata":{"displayName":"Qwen Math Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":4096,"maxOutputTokens":3072,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09-19","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-math-plus","displayName":"Qwen Math Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":4096,"defaultContextWindow":4096,"knowledgeCutoff":"2024-04"}},"qwen-math-turbo":{"metadata":{"displayName":"Qwen Math Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","lifecycle":"active","contextWindow":4096,"maxOutputTokens":3072,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09-19","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-math-turbo","displayName":"Qwen Math Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":4096,"defaultContextWindow":4096,"knowledgeCutoff":"2024-04"}},"qwen-max":{"metadata":{"displayName":"Qwen Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-01-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-max","displayName":"Qwen Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen-mt-plus":{"metadata":{"displayName":"Qwen-MT Plus","description":"Translation model for multilingual conversion, localization, and cross-language workflows","lifecycle":"active","contextWindow":16384,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-mt-plus","displayName":"Qwen-MT Plus","description":"Translation model for multilingual conversion, localization, and cross-language workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16384,"defaultContextWindow":16384,"knowledgeCutoff":"2024-04"}},"qwen-mt-turbo":{"metadata":{"displayName":"Qwen-MT Turbo","description":"Translation model for multilingual conversion, localization, and cross-language workflows","lifecycle":"active","contextWindow":16384,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-mt-turbo","displayName":"Qwen-MT Turbo","description":"Translation model for multilingual conversion, localization, and cross-language workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16384,"defaultContextWindow":16384,"knowledgeCutoff":"2024-04"}},"qwen-omni-turbo":{"metadata":{"displayName":"Qwen-Omni Turbo","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","lifecycle":"active","contextWindow":32768,"maxOutputTokens":2048,"knowledgeCutoff":"2024-04","lastUpdated":"2025-03-26","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","audio","video"],"output":["text","audio"]}},"entry":{"id":"qwen-omni-turbo","displayName":"Qwen-Omni Turbo","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-04"}},"qwen-omni-turbo-realtime":{"metadata":{"displayName":"Qwen-Omni Turbo Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","lifecycle":"active","contextWindow":32768,"maxOutputTokens":2048,"knowledgeCutoff":"2024-04","lastUpdated":"2025-05-08","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","audio"],"output":["text","audio"]}},"entry":{"id":"qwen-omni-turbo-realtime","displayName":"Qwen-Omni Turbo Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-04"}},"qwen-plus":{"metadata":{"displayName":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","lastUpdated":"2025-09-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-plus","displayName":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-04"}},"qwen-plus-character":{"metadata":{"displayName":"Qwen Plus Character","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":32768,"maxOutputTokens":4096,"knowledgeCutoff":"2024-04","lastUpdated":"2024-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-plus-character","displayName":"Qwen Plus Character","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-04"}},"qwen-turbo":{"metadata":{"displayName":"Qwen Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":16384,"knowledgeCutoff":"2024-04","lastUpdated":"2025-07-15","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-turbo","displayName":"Qwen Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-04"}},"qwen-vl-max":{"metadata":{"displayName":"Qwen-VL Max","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-08-13","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen-vl-max","displayName":"Qwen-VL Max","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen-vl-ocr":{"metadata":{"displayName":"Qwen-VL OCR","description":"OCR model for extracting structured text from documents and screenshots","lifecycle":"active","contextWindow":34096,"maxOutputTokens":4096,"knowledgeCutoff":"2024-04","lastUpdated":"2025-04-13","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen-vl-ocr","displayName":"Qwen-VL OCR","description":"OCR model for extracting structured text from documents and screenshots","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":34096,"defaultContextWindow":34096,"knowledgeCutoff":"2024-04"}},"qwen-vl-plus":{"metadata":{"displayName":"Qwen-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-08-15","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen-vl-plus","displayName":"Qwen-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-14b-instruct":{"metadata":{"displayName":"Qwen2.5 14B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-14b-instruct","displayName":"Qwen2.5 14B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-32b-instruct":{"metadata":{"displayName":"Qwen2.5 32B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-32b-instruct","displayName":"Qwen2.5 32B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-72b-instruct":{"metadata":{"displayName":"Qwen2.5 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-72b-instruct","displayName":"Qwen2.5 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-7b-instruct":{"metadata":{"displayName":"Qwen2.5 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-7b-instruct","displayName":"Qwen2.5 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-coder-32b-instruct":{"metadata":{"displayName":"Qwen2.5-Coder 32B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-coder-32b-instruct","displayName":"Qwen2.5-Coder 32B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-coder-7b-instruct":{"metadata":{"displayName":"Qwen2.5-Coder 7B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-coder-7b-instruct","displayName":"Qwen2.5-Coder 7B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-math-72b-instruct":{"metadata":{"displayName":"Qwen2.5-Math 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":4096,"maxOutputTokens":3072,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-math-72b-instruct","displayName":"Qwen2.5-Math 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":4096,"defaultContextWindow":4096,"knowledgeCutoff":"2024-04"}},"qwen2-5-math-7b-instruct":{"metadata":{"displayName":"Qwen2.5-Math 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":4096,"maxOutputTokens":3072,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-math-7b-instruct","displayName":"Qwen2.5-Math 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":4096,"defaultContextWindow":4096,"knowledgeCutoff":"2024-04"}},"qwen2-5-omni-7b":{"metadata":{"displayName":"Qwen2.5-Omni 7B","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","lifecycle":"active","contextWindow":32768,"maxOutputTokens":2048,"knowledgeCutoff":"2024-04","lastUpdated":"2024-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","audio","video"],"output":["text","audio"]}},"entry":{"id":"qwen2-5-omni-7b","displayName":"Qwen2.5-Omni 7B","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-04"}},"qwen2-5-vl-72b-instruct":{"metadata":{"displayName":"Qwen2.5-VL 72B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen2-5-vl-72b-instruct","displayName":"Qwen2.5-VL 72B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-vl-7b-instruct":{"metadata":{"displayName":"Qwen2.5-VL 7B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen2-5-vl-7b-instruct","displayName":"Qwen2.5-VL 7B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen3-14b":{"metadata":{"displayName":"Qwen3 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-14b","displayName":"Qwen3 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-235b-a22b":{"metadata":{"displayName":"Qwen3 235B-A22B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-235b-a22b","displayName":"Qwen3 235B-A22B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-32b":{"metadata":{"displayName":"Qwen3 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-32b","displayName":"Qwen3 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-8b":{"metadata":{"displayName":"Qwen3 8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-8b","displayName":"Qwen3 8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-asr-flash":{"metadata":{"displayName":"Qwen3-ASR Flash","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","contextWindow":53248,"maxOutputTokens":4096,"knowledgeCutoff":"2024-04","lastUpdated":"2025-09-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"qwen3-asr-flash","displayName":"Qwen3-ASR Flash","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":53248,"defaultContextWindow":53248,"knowledgeCutoff":"2024-04"}},"qwen3-coder-30b-a3b-instruct":{"metadata":{"displayName":"Qwen3-Coder 30B-A3B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-30b-a3b-instruct","displayName":"Qwen3-Coder 30B-A3B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3-coder-480b-a35b-instruct":{"metadata":{"displayName":"Qwen3-Coder 480B-A35B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-480b-a35b-instruct","displayName":"Qwen3-Coder 480B-A35B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3-coder-flash":{"metadata":{"displayName":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-flash","displayName":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3-coder-plus":{"metadata":{"displayName":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-plus","displayName":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-04"}},"qwen3-max":{"metadata":{"displayName":"Qwen3 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-max","displayName":"Qwen3 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3-next-80b-a3b-instruct":{"metadata":{"displayName":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-next-80b-a3b-instruct","displayName":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-next-80b-a3b-thinking":{"metadata":{"displayName":"Qwen3-Next 80B-A3B (Thinking)","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-next-80b-a3b-thinking","displayName":"Qwen3-Next 80B-A3B (Thinking)","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-omni-flash":{"metadata":{"displayName":"Qwen3-Omni Flash","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","lifecycle":"active","contextWindow":65536,"maxOutputTokens":16384,"knowledgeCutoff":"2024-04","lastUpdated":"2025-09-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video"],"output":["text","audio"]}},"entry":{"id":"qwen3-omni-flash","displayName":"Qwen3-Omni Flash","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2024-04"}},"qwen3-omni-flash-realtime":{"metadata":{"displayName":"Qwen3-Omni Flash Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","lifecycle":"active","contextWindow":65536,"maxOutputTokens":16384,"knowledgeCutoff":"2024-04","lastUpdated":"2025-09-15","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","audio"],"output":["text","audio"]}},"entry":{"id":"qwen3-omni-flash-realtime","displayName":"Qwen3-Omni Flash Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2024-04"}},"qwen3-vl-235b-a22b":{"metadata":{"displayName":"Qwen3-VL 235B-A22B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen3-vl-235b-a22b","displayName":"Qwen3-VL 235B-A22B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-vl-30b-a3b":{"metadata":{"displayName":"Qwen3-VL 30B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen3-vl-30b-a3b","displayName":"Qwen3-VL 30B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-vl-plus":{"metadata":{"displayName":"Qwen3-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen3-vl-plus","displayName":"Qwen3-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3.5-397b-a17b":{"metadata":{"displayName":"Qwen3.5 397B-A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.5-397b-a17b","displayName":"Qwen3.5 397B-A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3.5-flash":{"metadata":{"displayName":"Qwen3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.5-flash","displayName":"Qwen3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.5-plus":{"metadata":{"displayName":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.5-plus","displayName":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.6-flash":{"metadata":{"displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-flash","displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.6-max-preview":{"metadata":{"displayName":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","lifecycle":"active","contextWindow":245800,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3.6-max-preview","displayName":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":245800,"defaultContextWindow":245800}},"qwen3.6-plus":{"metadata":{"displayName":"Qwen3.6 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-plus","displayName":"Qwen3.6 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.7-flash":{"metadata":{"displayName":"Qwen3.7 Flash","description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","lifecycle":"active","contextWindow":1000000,"inputLimit":991000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-07-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.7-flash","displayName":"Qwen3.7 Flash","description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"inputLimit":991000,"defaultContextWindow":1000000,"defaultInputLimit":991000}},"qwen3.7-max":{"metadata":{"displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3.7-max","displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.7-plus":{"metadata":{"displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-04","lastUpdated":"2026-06-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.7-plus","displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.8-flash":{"metadata":{"displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.8-flash","displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.8-max":{"metadata":{"displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-03","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"qwen3.8-max","displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwq-32b":{"metadata":{"displayName":"QwQ 32B","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwq-32b","displayName":"QwQ 32B","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwq-plus":{"metadata":{"displayName":"QwQ Plus","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-03-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwq-plus","displayName":"QwQ Plus","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"siliconflow/deepseek-r1-0528":{"metadata":{"displayName":"siliconflow/deepseek-r1-0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","lifecycle":"active","contextWindow":163840,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"siliconflow/deepseek-r1-0528","displayName":"siliconflow/deepseek-r1-0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840}},"siliconflow/deepseek-v3-0324":{"metadata":{"displayName":"siliconflow/deepseek-v3-0324","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":163840,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"siliconflow/deepseek-v3-0324","displayName":"siliconflow/deepseek-v3-0324","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840}},"siliconflow/deepseek-v3.1-terminus":{"metadata":{"displayName":"siliconflow/deepseek-v3.1-terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"siliconflow/deepseek-v3.1-terminus","displayName":"siliconflow/deepseek-v3.1-terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840}},"siliconflow/deepseek-v3.2":{"metadata":{"displayName":"siliconflow/deepseek-v3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2025-12-03","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"siliconflow/deepseek-v3.2","displayName":"siliconflow/deepseek-v3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840}},"tongyi-intent-detect-v3":{"metadata":{"displayName":"Tongyi Intent Detect V3","description":"General-purpose chat model for instruction following, writing, and analysis","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1024,"knowledgeCutoff":"2024-04","lastUpdated":"2024-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tongyi-intent-detect-v3","displayName":"Tongyi Intent Detect V3","description":"General-purpose chat model for instruction following, writing, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2024-04"}}}},"alibaba-coding-plan-cn":{"baseUrl":"https://coding.dashscope.aliyuncs.com/v1","label":"Alibaba Coding Plan (China)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["qwen3.7-plus","qwen3.7-max","qwen3.6-plus","qwen3.6-flash","qwen3.5-plus","qwen3-max-2026-01-23","qwen3-coder-next","qwen3-coder-plus","glm-5","glm-4.7","kimi-k2.5","MiniMax-M2.5"],"models":{"glm-4.7":{"metadata":{"displayName":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","lastUpdated":"2025-12-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.7","displayName":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752,"knowledgeCutoff":"2025-04"}},"glm-5":{"metadata":{"displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":16384,"lastUpdated":"2026-02-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5","displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"kimi-k2.5":{"metadata":{"displayName":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"kimi-k2.5","displayName":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"MiniMax-M2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":196608,"maxOutputTokens":24576,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.5","displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":196608,"defaultContextWindow":196608}},"qwen3-coder-next":{"metadata":{"displayName":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-next","displayName":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen3-coder-plus":{"metadata":{"displayName":"Qwen3 Coder Plus","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-plus","displayName":"Qwen3 Coder Plus","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3-max-2026-01-23":{"metadata":{"displayName":"Qwen3 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2026-01-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-max-2026-01-23","displayName":"Qwen3 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3.5-plus":{"metadata":{"displayName":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen3.5-plus","displayName":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.6-flash":{"metadata":{"displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-flash","displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.6-plus":{"metadata":{"displayName":"Qwen3.6 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-plus","displayName":"Qwen3.6 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.7-max":{"metadata":{"displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3.7-max","displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.7-plus":{"metadata":{"displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-04","lastUpdated":"2026-06-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.7-plus","displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}}}},"alibaba-coding-plan":{"baseUrl":"https://coding-intl.dashscope.aliyuncs.com/v1","label":"Alibaba Coding Plan","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["qwen3.7-plus","qwen3.7-max","qwen3.6-plus","qwen3.6-flash","qwen3.5-plus","qwen3-max-2026-01-23","qwen3-coder-next","qwen3-coder-plus","glm-5","glm-4.7","kimi-k2.5","MiniMax-M2.5"],"models":{"glm-4.7":{"metadata":{"displayName":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","lastUpdated":"2025-12-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.7","displayName":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752,"knowledgeCutoff":"2025-04"}},"glm-5":{"metadata":{"displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":16384,"lastUpdated":"2026-02-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5","displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"kimi-k2.5":{"metadata":{"displayName":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.5","displayName":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"MiniMax-M2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":196608,"inputLimit":196601,"maxOutputTokens":24576,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.5","displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":196608,"inputLimit":196601,"defaultContextWindow":196608,"defaultInputLimit":196601}},"qwen3-coder-next":{"metadata":{"displayName":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-next","displayName":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen3-coder-plus":{"metadata":{"displayName":"Qwen3 Coder Plus","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-plus","displayName":"Qwen3 Coder Plus","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3-max-2026-01-23":{"metadata":{"displayName":"Qwen3 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2026-01-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-max-2026-01-23","displayName":"Qwen3 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3.5-plus":{"metadata":{"displayName":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.5-plus","displayName":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.6-flash":{"metadata":{"displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-flash","displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.6-plus":{"metadata":{"displayName":"Qwen3.6 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-plus","displayName":"Qwen3.6 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.7-max":{"metadata":{"displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3.7-max","displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.7-plus":{"metadata":{"displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-04","lastUpdated":"2026-06-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.7-plus","displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}}}},"alibaba-token-plan-cn":{"baseUrl":"https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1","label":"Alibaba Token Plan (China)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider","responses":{"adapter":"open-responses","reasoningReplay":"plaintext-summary","compatibility":"alibaba-token-plan"}},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["qwen3.8-max","qwen3.7-max","qwen3.7-plus","qwen3.6-plus","qwen3.6-flash","deepseek-v4-pro","deepseek-v4-flash","deepseek-v3.2","kimi-k2.7-code","kimi-k2.6","kimi-k2.5","glm-5.2","glm-5.1","glm-5","MiniMax-M2.5"],"models":{"deepseek-v3.2":{"metadata":{"displayName":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-12-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v3.2","displayName":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash","displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-flash-0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash-0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-pro","displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-pro-0813":{"metadata":{"displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-pro-0813","displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"deepseek-v4.1-flash":{"metadata":{"displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-v4.1-flash","displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"glm-5":{"metadata":{"displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","lifecycle":"active","contextWindow":202752,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5","displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"glm-5.1":{"metadata":{"displayName":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","lifecycle":"active","contextWindow":202752,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.1","displayName":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"glm-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"happyhorse-1.1-i2v":{"metadata":{"displayName":"HappyHorse 1.1 Image-to-Video","description":"Video model for image-to-video generation","lifecycle":"active","lastUpdated":"2026-07-17","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["image","text"],"output":["video"]}},"entry":{"id":"happyhorse-1.1-i2v","displayName":"HappyHorse 1.1 Image-to-Video","description":"Video model for image-to-video generation","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"happyhorse-1.1-r2v":{"metadata":{"displayName":"HappyHorse 1.1 Reference-to-Video","description":"Video model for reference-guided video generation","lifecycle":"active","lastUpdated":"2026-07-17","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["image","text"],"output":["video"]}},"entry":{"id":"happyhorse-1.1-r2v","displayName":"HappyHorse 1.1 Reference-to-Video","description":"Video model for reference-guided video generation","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"happyhorse-1.1-t2v":{"metadata":{"displayName":"HappyHorse 1.1 Text-to-Video","description":"Video model for prompt-driven text-to-video generation","lifecycle":"active","lastUpdated":"2026-07-17","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"happyhorse-1.1-t2v","displayName":"HappyHorse 1.1 Text-to-Video","description":"Video model for prompt-driven text-to-video generation","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"kimi-k2.5":{"metadata":{"displayName":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","lifecycle":"active","contextWindow":262144,"maxOutputTokens":98304,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.5","displayName":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.6","displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k2.7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.7-code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"MiniMax-M2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","lifecycle":"active","contextWindow":196608,"inputLimit":196601,"maxOutputTokens":32768,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.5","displayName":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":196608,"inputLimit":196601,"defaultContextWindow":196608,"defaultInputLimit":196601}},"qwen-image-2.0":{"metadata":{"displayName":"Qwen Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":8192,"lastUpdated":"2026-03-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"qwen-image-2.0","displayName":"Qwen Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"qwen-image-2.0-pro":{"metadata":{"displayName":"Qwen Image 2.0 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":8192,"lastUpdated":"2026-03-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"qwen-image-2.0-pro","displayName":"Qwen Image 2.0 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"qwen3.6-flash":{"metadata":{"displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-flash","displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.6-plus":{"metadata":{"displayName":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-plus","displayName":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.7-max":{"metadata":{"displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3.7-max","displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.7-plus":{"metadata":{"displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-06-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.7-plus","displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.8-flash":{"metadata":{"displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.8-flash","displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.8-max":{"metadata":{"displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-03","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"qwen3.8-max","displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.8-max-preview":{"metadata":{"displayName":"Qwen3.8 Max Preview","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","lifecycle":"deprecated","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.8-max-preview","displayName":"Qwen3.8 Max Preview","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"wan2.7-image":{"metadata":{"displayName":"Wan2.7 Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":8192,"lastUpdated":"2026-05-29","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"wan2.7-image","displayName":"Wan2.7 Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"wan2.7-image-pro":{"metadata":{"displayName":"Wan2.7 Image Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":8192,"lastUpdated":"2026-05-29","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"wan2.7-image-pro","displayName":"Wan2.7 Image Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}}}},"alibaba-token-plan":{"baseUrl":"https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","label":"Alibaba Token Plan","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider","responses":{"adapter":"open-responses","reasoningReplay":"plaintext-summary","compatibility":"alibaba-token-plan"}},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["qwen3.8-max","qwen3.7-max","qwen3.7-plus","qwen3.6-plus","qwen3.6-flash","deepseek-v4-pro","deepseek-v4-flash","deepseek-v3.2","kimi-k2.7-code","kimi-k2.6","kimi-k2.5","glm-5.2","glm-5.1","glm-5","MiniMax-M2.5"],"models":{"deepseek-v3.2":{"metadata":{"displayName":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-12-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v3.2","displayName":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash","displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-flash-0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash-0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-pro","displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-pro-0813":{"metadata":{"displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-pro-0813","displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5":{"metadata":{"displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","lifecycle":"active","contextWindow":202752,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5","displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"glm-5.1":{"metadata":{"displayName":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","lifecycle":"active","contextWindow":202752,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.1","displayName":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"glm-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"happyhorse-1.1-i2v":{"metadata":{"displayName":"HappyHorse 1.1 Image-to-Video","description":"Video model for image-to-video generation","lifecycle":"active","lastUpdated":"2026-07-17","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["image","text"],"output":["video"]}},"entry":{"id":"happyhorse-1.1-i2v","displayName":"HappyHorse 1.1 Image-to-Video","description":"Video model for image-to-video generation","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"happyhorse-1.1-r2v":{"metadata":{"displayName":"HappyHorse 1.1 Reference-to-Video","description":"Video model for reference-guided video generation","lifecycle":"active","lastUpdated":"2026-07-17","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["image","text"],"output":["video"]}},"entry":{"id":"happyhorse-1.1-r2v","displayName":"HappyHorse 1.1 Reference-to-Video","description":"Video model for reference-guided video generation","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"happyhorse-1.1-t2v":{"metadata":{"displayName":"HappyHorse 1.1 Text-to-Video","description":"Video model for prompt-driven text-to-video generation","lifecycle":"active","lastUpdated":"2026-07-17","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"happyhorse-1.1-t2v","displayName":"HappyHorse 1.1 Text-to-Video","description":"Video model for prompt-driven text-to-video generation","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"kimi-k2.5":{"metadata":{"displayName":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","lifecycle":"active","contextWindow":262144,"maxOutputTokens":98304,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.5","displayName":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.6","displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k2.7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.7-code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"MiniMax-M2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","lifecycle":"active","contextWindow":196608,"inputLimit":196601,"maxOutputTokens":32768,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.5","displayName":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":196608,"inputLimit":196601,"defaultContextWindow":196608,"defaultInputLimit":196601}},"qwen-image-2.0":{"metadata":{"displayName":"Qwen Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":8192,"lastUpdated":"2026-03-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"qwen-image-2.0","displayName":"Qwen Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"qwen-image-2.0-pro":{"metadata":{"displayName":"Qwen Image 2.0 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":8192,"lastUpdated":"2026-03-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"qwen-image-2.0-pro","displayName":"Qwen Image 2.0 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"qwen3.6-flash":{"metadata":{"displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-flash","displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.6-plus":{"metadata":{"displayName":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-plus","displayName":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.7-max":{"metadata":{"displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3.7-max","displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.7-plus":{"metadata":{"displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-06-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.7-plus","displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.8-flash":{"metadata":{"displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.8-flash","displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.8-max":{"metadata":{"displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-03","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"qwen3.8-max","displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.8-max-preview":{"metadata":{"displayName":"Qwen3.8 Max Preview","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","lifecycle":"deprecated","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.8-max-preview","displayName":"Qwen3.8 Max Preview","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"wan2.7-image":{"metadata":{"displayName":"Wan2.7 Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":8192,"lastUpdated":"2026-05-29","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"wan2.7-image","displayName":"Wan2.7 Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"wan2.7-image-pro":{"metadata":{"displayName":"Wan2.7 Image Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":8192,"lastUpdated":"2026-05-29","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"wan2.7-image-pro","displayName":"Wan2.7 Image Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}}}},"commandcode":{"baseUrl":"https://api.commandcode.ai/provider/v1","label":"Command Code","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{"anthropic-messages":{"kind":"anthropic","auth":"bearer","normalizeBaseUrl":true}},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol","modelProtocols":"commandcode"},"fallbackModels":[],"models":{}},"cloudflare-workers-ai":{"baseUrl":"","label":"Cloudflare Workers AI","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider","requireBaseUrl":true,"replayAssistantReasoningAs":"reasoning"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"cloudflare"},"fallbackModels":["@cf/moonshotai/kimi-k2.6","@cf/moonshotai/kimi-k2.7-code","@cf/deepseek-ai/deepseek-v4-flash-0731","@cf/deepseek-ai/deepseek-v4-pro-0813","@cf/google/gemma-4-26b-a4b-it","@cf/ibm-granite/granite-4.0-h-micro","@cf/meta/llama-3.3-70b-instruct-fp8-fast","@cf/meta/llama-4-scout-17b-16e-instruct","@cf/mistralai/mistral-small-3.1-24b-instruct","@cf/nvidia/nemotron-3-120b-a12b","@cf/openai/gpt-oss-120b","@cf/openai/gpt-oss-20b","@cf/qwen/qwen3-30b-a3b-fp8","@cf/qwen/qwen3.8-27b","@cf/zai-org/glm-4.7-flash","@cf/zai-org/glm-5.2","@cf/zai-org/glm-5.3","@cf/zai-org/glm-5.3-flash"],"models":{"@cf/aisingapore/gemma-sea-lion-v4-27b-it":{"metadata":{"displayName":"Gemma Sea Lion V4 27B It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"structuredOutput":false,"lastUpdated":"2025-09-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/aisingapore/gemma-sea-lion-v4-27b-it","displayName":"Gemma Sea Lion V4 27B It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"@cf/deepseek-ai/deepseek-r1-distill-qwen-32b":{"metadata":{"displayName":"Deepseek R1 Distill Qwen 32B","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","lifecycle":"active","contextWindow":80000,"maxOutputTokens":80000,"knowledgeCutoff":"2024-07","structuredOutput":false,"lastUpdated":"2025-05-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","displayName":"Deepseek R1 Distill Qwen 32B","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":80000,"defaultContextWindow":80000,"knowledgeCutoff":"2024-07"}},"@cf/deepseek-ai/deepseek-v4-flash-0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1310720,"maxOutputTokens":1048576,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/deepseek-ai/deepseek-v4-flash-0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1310720,"defaultContextWindow":1310720,"knowledgeCutoff":"2025-05"}},"@cf/deepseek-ai/deepseek-v4-pro-0813":{"metadata":{"displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"structuredOutput":true,"lastUpdated":"2026-08-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/deepseek-ai/deepseek-v4-pro-0813","displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"@cf/google/gemma-4-26b-a4b-it":{"metadata":{"displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":256000,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"@cf/google/gemma-4-26b-a4b-it","displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000}},"@cf/ibm-granite/granite-4.0-h-micro":{"metadata":{"displayName":"Granite 4.0 H Micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":131000,"maxOutputTokens":131000,"structuredOutput":false,"lastUpdated":"2025-10-07","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/ibm-granite/granite-4.0-h-micro","displayName":"Granite 4.0 H Micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000}},"@cf/meta/llama-3.1-8b-instruct-fp8":{"metadata":{"displayName":"Llama 3.1 8B Instruct fp8","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":32000,"maxOutputTokens":32000,"knowledgeCutoff":"2023-12","structuredOutput":false,"lastUpdated":"2024-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/meta/llama-3.1-8b-instruct-fp8","displayName":"Llama 3.1 8B Instruct fp8","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000,"knowledgeCutoff":"2023-12"}},"@cf/meta/llama-3.2-11b-vision-instruct":{"metadata":{"displayName":"Llama 3.2 11B Vision Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2023-12","structuredOutput":false,"lastUpdated":"2024-09-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"@cf/meta/llama-3.2-11b-vision-instruct","displayName":"Llama 3.2 11B Vision Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-12"}},"@cf/meta/llama-3.2-1b-instruct":{"metadata":{"displayName":"Llama 3.2 1B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":60000,"maxOutputTokens":60000,"knowledgeCutoff":"2023-12","structuredOutput":false,"lastUpdated":"2024-09-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/meta/llama-3.2-1b-instruct","displayName":"Llama 3.2 1B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":60000,"defaultContextWindow":60000,"knowledgeCutoff":"2023-12"}},"@cf/meta/llama-3.2-3b-instruct":{"metadata":{"displayName":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":80000,"maxOutputTokens":80000,"knowledgeCutoff":"2023-12","structuredOutput":false,"lastUpdated":"2024-09-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/meta/llama-3.2-3b-instruct","displayName":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":80000,"defaultContextWindow":80000,"knowledgeCutoff":"2023-12"}},"@cf/meta/llama-3.3-70b-instruct-fp8-fast":{"metadata":{"displayName":"Llama 3.3 70B Instruct fp8 Fast","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","lifecycle":"active","contextWindow":24000,"maxOutputTokens":24000,"knowledgeCutoff":"2023-12","structuredOutput":false,"lastUpdated":"2024-12-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/meta/llama-3.3-70b-instruct-fp8-fast","displayName":"Llama 3.3 70B Instruct fp8 Fast","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":24000,"defaultContextWindow":24000,"knowledgeCutoff":"2023-12"}},"@cf/meta/llama-4-scout-17b-16e-instruct":{"metadata":{"displayName":"Llama 4 Scout 17B 16E Instruct","description":"Open Llama with long-context vision for efficient multimodal agents","lifecycle":"active","contextWindow":131000,"maxOutputTokens":16384,"knowledgeCutoff":"2024-08","structuredOutput":false,"lastUpdated":"2025-04-05","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"@cf/meta/llama-4-scout-17b-16e-instruct","displayName":"Llama 4 Scout 17B 16E Instruct","description":"Open Llama with long-context vision for efficient multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000,"knowledgeCutoff":"2024-08"}},"@cf/meta/llama-guard-3-8b":{"metadata":{"displayName":"Llama Guard 3 8B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2023-12","structuredOutput":false,"lastUpdated":"2024-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/meta/llama-guard-3-8b","displayName":"Llama Guard 3 8B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12"}},"@cf/mistralai/mistral-small-3.1-24b-instruct":{"metadata":{"displayName":"Mistral Small 3.1 24B Instruct","description":"Efficient Mistral model for fast chat, extraction, and production assistants","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"structuredOutput":false,"lastUpdated":"2025-03-18","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/mistralai/mistral-small-3.1-24b-instruct","displayName":"Mistral Small 3.1 24B Instruct","description":"Efficient Mistral model for fast chat, extraction, and production assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"@cf/moonshotai/kimi-k2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","lifecycle":"active","contextWindow":262144,"maxOutputTokens":256000,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true,"offBehavior":"cloudflare-chat-template-thinking-false"},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"@cf/moonshotai/kimi-k2.6","displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"@cf/moonshotai/kimi-k2.7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"@cf/moonshotai/kimi-k2.7-code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"@cf/nvidia/nemotron-3-120b-a12b":{"metadata":{"displayName":"Nemotron 3 Super 120B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"structuredOutput":true,"lastUpdated":"2026-03-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/nvidia/nemotron-3-120b-a12b","displayName":"Nemotron 3 Super 120B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000}},"@cf/openai/gpt-oss-120b":{"metadata":{"displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/openai/gpt-oss-120b","displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":128000,"defaultContextWindow":128000}},"@cf/openai/gpt-oss-20b":{"metadata":{"displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/openai/gpt-oss-20b","displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"@cf/qwen/qwen2.5-coder-32b-instruct":{"metadata":{"displayName":"Qwen2.5 Coder 32B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":32768,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2024-11-12","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/qwen/qwen2.5-coder-32b-instruct","displayName":"Qwen2.5 Coder 32B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"@cf/qwen/qwen3-30b-a3b-fp8":{"metadata":{"displayName":"Qwen3 30B A3b fp8","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":32768,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2025-04-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/qwen/qwen3-30b-a3b-fp8","displayName":"Qwen3 30B A3b fp8","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"@cf/qwen/qwen3.8-27b":{"metadata":{"displayName":"Qwen3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"@cf/qwen/qwen3.8-27b","displayName":"Qwen3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":262144,"defaultContextWindow":262144}},"@cf/qwen/qwq-32b":{"metadata":{"displayName":"Qwq 32B","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":24000,"maxOutputTokens":24000,"knowledgeCutoff":"2024-04","structuredOutput":false,"lastUpdated":"2025-03-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/qwen/qwq-32b","displayName":"Qwq 32B","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":24000,"defaultContextWindow":24000,"knowledgeCutoff":"2024-04"}},"@cf/zai-org/glm-4.7-flash":{"metadata":{"displayName":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/zai-org/glm-4.7-flash","displayName":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"@cf/zai-org/glm-5.2":{"metadata":{"displayName":"Glm 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":262144,"maxOutputTokens":256000,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/zai-org/glm-5.2","displayName":"Glm 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":262144,"defaultContextWindow":262144}},"@cf/zai-org/glm-5.3":{"metadata":{"displayName":"Glm 5.3","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":1310720,"maxOutputTokens":1310720,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/zai-org/glm-5.3","displayName":"Glm 5.3","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":1310720,"defaultContextWindow":1310720}},"@cf/zai-org/glm-5.3-flash":{"metadata":{"displayName":"Glm 5.3 Flash","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":1310720,"maxOutputTokens":1048576,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"@cf/zai-org/glm-5.3-flash","displayName":"Glm 5.3 Flash","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1310720,"defaultContextWindow":1310720}}}},"ollama-cloud":{"baseUrl":"https://ollama.com/v1","label":"Ollama Cloud","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider","includeUsage":true,"replayAssistantReasoningAs":"reasoning"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["qwen3.5:397b","gpt-oss:120b","deepseek-v4-flash","deepseek-v4-flash:0731","deepseek-v4-pro","deepseek-v4-pro:0813","deepseek-v4.1-flash","gemma4:31b","glm-5.1","glm-5.2","glm-5.3","glm-5.3-flash","gpt-oss:20b","kimi-k2.5","kimi-k2.6","kimi-k2.7-code","kimi-k3","minimax-m2.5","minimax-m2.7","minimax-m3","mistral-large-3:675b","nemotron-3-nano:30b","nemotron-3-super","nemotron-3-ultra"],"models":{"deepseek-v4-flash":{"metadata":{"displayName":"deepseek-v4-flash","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash","displayName":"deepseek-v4-flash","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"deepseek-v4-flash:0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash:0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"deepseek-v4-pro":{"metadata":{"displayName":"deepseek-v4-pro","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-pro","displayName":"deepseek-v4-pro","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"deepseek-v4-pro:0813":{"metadata":{"displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"structuredOutput":true,"lastUpdated":"2026-08-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-pro:0813","displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"deepseek-v4.1-flash":{"metadata":{"displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-v4.1-flash","displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"gemma4:31b":{"metadata":{"displayName":"gemma4:31b","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","lastUpdated":"2026-04-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gemma4:31b","displayName":"gemma4:31b","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"glm-5.1":{"metadata":{"displayName":"glm-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":131072,"lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.1","displayName":"glm-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":202752,"defaultContextWindow":202752}},"glm-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":976000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":976000,"defaultContextWindow":976000}},"glm-5.3":{"metadata":{"displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.3","displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"glm-5.3-flash":{"metadata":{"displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"glm-5.3-flash","displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"gpt-oss:120b":{"metadata":{"displayName":"gpt-oss:120b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"gpt-oss:120b","displayName":"gpt-oss:120b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"gpt-oss:20b":{"metadata":{"displayName":"gpt-oss:20b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"gpt-oss:20b","displayName":"gpt-oss:20b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"kimi-k2.5":{"metadata":{"displayName":"kimi-k2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"kimi-k2.5","displayName":"kimi-k2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":262144,"defaultContextWindow":262144}},"kimi-k2.6":{"metadata":{"displayName":"kimi-k2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"lastUpdated":"2026-04-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"kimi-k2.6","displayName":"kimi-k2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":262144,"defaultContextWindow":262144}},"kimi-k2.7-code":{"metadata":{"displayName":"kimi-k2.7-code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"kimi-k2.7-code","displayName":"kimi-k2.7-code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k3":{"metadata":{"displayName":"kimi-k3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"kimi-k3","displayName":"kimi-k3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"minimax-m2.5":{"metadata":{"displayName":"minimax-m2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01","lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true}},"entry":{"id":"minimax-m2.5","displayName":"minimax-m2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01"}},"minimax-m2.7":{"metadata":{"displayName":"minimax-m2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":196608,"maxOutputTokens":196608,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax-m2.7","displayName":"minimax-m2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":196608,"defaultContextWindow":196608}},"minimax-m3":{"metadata":{"displayName":"minimax-m3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","lifecycle":"active","contextWindow":512000,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01","lastUpdated":"2026-05-31","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"minimax-m3","displayName":"minimax-m3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":512000,"defaultContextWindow":512000,"knowledgeCutoff":"2025-01"}},"mistral-large-3:675b":{"metadata":{"displayName":"mistral-large-3:675b","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"lastUpdated":"2026-01-19","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral-large-3:675b","displayName":"mistral-large-3:675b","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"nemotron-3-nano:30b":{"metadata":{"displayName":"nemotron-3-nano:30b","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nemotron-3-nano:30b","displayName":"nemotron-3-nano:30b","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"nemotron-3-super":{"metadata":{"displayName":"nemotron-3-super","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"lastUpdated":"2026-03-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nemotron-3-super","displayName":"nemotron-3-super","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":262144,"defaultContextWindow":262144}},"nemotron-3-ultra":{"metadata":{"displayName":"nemotron-3-ultra","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","lifecycle":"active","contextWindow":262144,"maxOutputTokens":128000,"lastUpdated":"2026-06-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nemotron-3-ultra","displayName":"nemotron-3-ultra","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":262144,"defaultContextWindow":262144}},"qwen3.5:397b":{"metadata":{"displayName":"qwen3.5:397b","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"lastUpdated":"2026-02-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen3.5:397b","displayName":"qwen3.5:397b","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":262144,"defaultContextWindow":262144}}}},"ollama":{"baseUrl":"http://127.0.0.1:11434/v1","label":"Ollama","authKind":"none","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"ollama"},"fallbackModels":["llama3.2","qwen2.5-coder","gemma3"],"models":{"llama3.2":{"metadata":{},"entry":{"id":"llama3.2","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"qwen2.5-coder":{"metadata":{},"entry":{"id":"qwen2.5-coder","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"gemma3":{"metadata":{},"entry":{"id":"gemma3","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}}}},"lm-studio":{"baseUrl":"http://127.0.0.1:1234/v1","label":"LM Studio","authKind":"none","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}},"localai":{"baseUrl":"http://127.0.0.1:8080/v1","label":"LocalAI","authKind":"optional_api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["qwen3-8b"],"models":{"qwen3-8b":{"metadata":{},"entry":{"id":"qwen3-8b","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}}}},"openai-compatible":{"baseUrl":"","label":"Custom relay (OpenAI Chat-compatible)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"connection","requireBaseUrl":true},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}},"openai-responses-compatible":{"baseUrl":"","label":"Custom relay (OpenAI Responses)","authKind":"api_key","runtimeAdapter":{"kind":"openai","apiProtocol":"openai-responses","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}},"anthropic-compatible":{"baseUrl":"","label":"Custom relay (Anthropic)","authKind":"api_key","runtimeAdapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}},"github-copilot":{"baseUrl":"https://api.githubcopilot.com","label":"GitHub Copilot","authKind":"oauth_token","runtimeAdapter":{"kind":"openai-compatible","name":"provider","includeUsage":false},"protocolAdapters":{"anthropic-messages":{"kind":"anthropic","auth":"bearer","normalizeBaseUrl":true,"includeBetaHeaders":false},"openai-responses":{"kind":"openai","apiProtocol":"openai-responses","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol","auth":"github-copilot"},"fallbackModels":["gpt-5.4","claude-fable-5","claude-fable-5.1","claude-haiku-4.5","claude-opus-4.7","claude-opus-4.8","claude-opus-5","claude-sonnet-4.6","claude-sonnet-5","gemini-3.5-flash","gemini-3.6-flash","gemini-3.7-flash","gemini-3.8-flash","gpt-5-mini","gpt-5.3-codex","gpt-5.4-mini","gpt-5.4-nano","gpt-5.5","gpt-5.6-luna","gpt-5.6-sol","gpt-5.6-terra","gpt-6-astra","grok-4.5","grok-4.6","kimi-k2.7-code","kimi-k3","mai-code-1-flash-picker","mai-code-1.1-flash"],"models":{"claude-fable-5":{"metadata":{"displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-06-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-fable-5","displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"claude-fable-5.1":{"metadata":{"displayName":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-06","lastUpdated":"2026-09-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-fable-5.1","displayName":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-06"}},"claude-haiku-4.5":{"metadata":{"displayName":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","lifecycle":"active","contextWindow":200000,"inputLimit":136000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-02-28","lastUpdated":"2025-10-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-haiku-4.5","displayName":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"inputLimit":136000,"defaultContextWindow":200000,"defaultInputLimit":136000,"knowledgeCutoff":"2025-02-28"}},"claude-opus-4.7":{"metadata":{"displayName":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","lifecycle":"active","contextWindow":200000,"inputLimit":168000,"maxOutputTokens":32000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-opus-4.7","displayName":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":200000,"inputLimit":168000,"defaultContextWindow":200000,"defaultInputLimit":168000,"knowledgeCutoff":"2026-01-31"}},"claude-opus-4.8":{"metadata":{"displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"inputLimit":168000,"maxOutputTokens":64000,"knowledgeCutoff":"2026-01","lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-opus-4.8","displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":200000,"inputLimit":168000,"defaultContextWindow":200000,"defaultInputLimit":168000,"knowledgeCutoff":"2026-01"}},"claude-opus-5":{"metadata":{"displayName":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","lifecycle":"active","contextWindow":1000000,"inputLimit":936000,"maxOutputTokens":64000,"knowledgeCutoff":"2026-05","structuredOutput":true,"lastUpdated":"2026-07-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-opus-5","displayName":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"inputLimit":936000,"defaultContextWindow":1000000,"defaultInputLimit":936000,"knowledgeCutoff":"2026-05"}},"claude-sonnet-4.6":{"metadata":{"displayName":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","lifecycle":"active","contextWindow":200000,"inputLimit":168000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-03-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-sonnet-4.6","displayName":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","max"],"contextWindow":200000,"inputLimit":168000,"defaultContextWindow":200000,"defaultInputLimit":168000,"knowledgeCutoff":"2025-08-31"}},"claude-sonnet-5":{"metadata":{"displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-sonnet-5","displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"gemini-3.5-flash":{"metadata":{"displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":200000,"inputLimit":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-3.5-flash","displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":200000,"inputLimit":128000,"defaultContextWindow":200000,"defaultInputLimit":128000,"knowledgeCutoff":"2025-01"}},"gemini-3.6-flash":{"metadata":{"displayName":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1000000,"inputLimit":936000,"maxOutputTokens":64000,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-07-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gemini-3.6-flash","displayName":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1000000,"inputLimit":936000,"defaultContextWindow":1000000,"defaultInputLimit":936000,"knowledgeCutoff":"2026-03"}},"gemini-3.7-flash":{"metadata":{"displayName":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","lifecycle":"active","contextWindow":1000000,"inputLimit":936000,"maxOutputTokens":64000,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-08-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gemini-3.7-flash","displayName":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"inputLimit":936000,"defaultContextWindow":1000000,"defaultInputLimit":936000,"knowledgeCutoff":"2026-03"}},"gemini-3.8-flash":{"metadata":{"displayName":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","lifecycle":"active","contextWindow":1000000,"inputLimit":936000,"maxOutputTokens":64000,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gemini-3.8-flash","displayName":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"inputLimit":936000,"defaultContextWindow":1000000,"defaultInputLimit":936000}},"gpt-5-mini":{"metadata":{"displayName":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","lifecycle":"active","contextWindow":264000,"inputLimit":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2024-05-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5-mini","displayName":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":264000,"inputLimit":128000,"defaultContextWindow":264000,"defaultInputLimit":128000,"knowledgeCutoff":"2024-05-30"}},"gpt-5.3-codex":{"metadata":{"displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-02-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.3-codex","displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4":{"metadata":{"displayName":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.4","displayName":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4-mini":{"metadata":{"displayName":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.4-mini","displayName":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4-nano":{"metadata":{"displayName":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.4-nano","displayName":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.5":{"metadata":{"displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.5","displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-12-01"}},"gpt-5.6-luna":{"metadata":{"displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.6-luna","displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"gpt-5.6-sol":{"metadata":{"displayName":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.6-sol","displayName":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"gpt-5.6-terra":{"metadata":{"displayName":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.6-terra","displayName":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"gpt-6-astra":{"metadata":{"displayName":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-04-30","structuredOutput":true,"lastUpdated":"2026-09-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-6-astra","displayName":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-04-30"}},"grok-4.5":{"metadata":{"displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","lifecycle":"active","contextWindow":500000,"inputLimit":372000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-07-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"grok-4.5","displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":500000,"inputLimit":372000,"defaultContextWindow":500000,"defaultInputLimit":372000}},"grok-4.6":{"metadata":{"displayName":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","lifecycle":"active","contextWindow":500000,"inputLimit":372000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-01","structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"grok-4.6","displayName":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":500000,"inputLimit":372000,"defaultContextWindow":500000,"defaultInputLimit":372000,"knowledgeCutoff":"2026-02-01"}},"kimi-k2.7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":256000,"inputLimit":224000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"kimi-k2.7-code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"inputLimit":224000,"defaultContextWindow":256000,"defaultInputLimit":224000,"knowledgeCutoff":"2025-01"}},"kimi-k3":{"metadata":{"displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"kimi-k3","displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"mai-code-1-flash-picker":{"metadata":{"displayName":"MAI-Code-1-Flash","description":"Microsoft coding model built for fast, efficient assistance in everyday developer workflows","lifecycle":"active","contextWindow":256000,"inputLimit":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12","structuredOutput":true,"lastUpdated":"2026-06-08","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mai-code-1-flash-picker","displayName":"MAI-Code-1-Flash","description":"Microsoft coding model built for fast, efficient assistance in everyday developer workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"inputLimit":128000,"defaultContextWindow":256000,"defaultInputLimit":128000,"knowledgeCutoff":"2025-12"}},"mai-code-1.1-flash":{"metadata":{"displayName":"MAI-Code-1.1-Flash","description":"Microsoft coding model with native vision support, optimized for fast and efficient software development","lifecycle":"active","contextWindow":256000,"inputLimit":128000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-08-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"mai-code-1.1-flash","displayName":"MAI-Code-1.1-Flash","description":"Microsoft coding model with native vision support, optimized for fast and efficient software development","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"inputLimit":128000,"defaultContextWindow":256000,"defaultInputLimit":128000}}}},"claude-subscription":{"baseUrl":"https://api.anthropic.com","label":"Claude Subscription (Pro / Max OAuth)","authKind":"oauth_token","runtimeAdapter":{"kind":"unavailable"},"protocolAdapters":{},"retired":true,"supportsModelDiscovery":false,"modelDiscovery":{"kind":"fallback","reason":"Subscription OAuth tokens are session-scoped (user:sessions:claude_code, no user:inference), so GET /v1/models rejects them with 401"},"fallbackModels":["claude-opus-5","claude-sonnet-5","claude-sonnet-4-6","claude-opus-4-8","claude-haiku-4-5","claude-sonnet-4-5-20250929"],"models":{"claude-fable-5":{"metadata":{"displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","lifecycle":"active","structuredOutput":true,"lastUpdated":"2026-06-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]}},"entry":{"id":"claude-fable-5","displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"]}},"claude-fable-5-1":{"metadata":{"displayName":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","lifecycle":"active","knowledgeCutoff":"2026-06","structuredOutput":true,"lastUpdated":"2026-09-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]}},"entry":{"id":"claude-fable-5-1","displayName":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"knowledgeCutoff":"2026-06"}},"claude-haiku-4-5":{"metadata":{"displayName":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","lifecycle":"active","knowledgeCutoff":"2025-02-28","structuredOutput":true,"lastUpdated":"2025-10-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"toggle":true,"offBehavior":"anthropic-thinking-disabled"}},"entry":{"id":"claude-haiku-4-5","displayName":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"],"knowledgeCutoff":"2025-02-28"}},"claude-haiku-4-5-20251001":{"metadata":{"displayName":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","lifecycle":"active","knowledgeCutoff":"2025-02-28","structuredOutput":true,"lastUpdated":"2025-10-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"toggle":true,"offBehavior":"anthropic-thinking-disabled"}},"entry":{"id":"claude-haiku-4-5-20251001","displayName":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"],"knowledgeCutoff":"2025-02-28"}},"claude-opus-4-5":{"metadata":{"displayName":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2025-11-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"efforts":["low","medium","high"]}},"entry":{"id":"claude-opus-4-5","displayName":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"knowledgeCutoff":"2025-05"}},"claude-opus-4-5-20251101":{"metadata":{"displayName":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2025-11-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"efforts":["low","medium","high"]}},"entry":{"id":"claude-opus-4-5-20251101","displayName":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"knowledgeCutoff":"2025-05"}},"claude-opus-4-6":{"metadata":{"displayName":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","lifecycle":"active","knowledgeCutoff":"2025-05-31","structuredOutput":true,"lastUpdated":"2026-03-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"efforts":["low","medium","high","max"]}},"entry":{"id":"claude-opus-4-6","displayName":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","max"],"knowledgeCutoff":"2025-05-31"}},"claude-opus-4-7":{"metadata":{"displayName":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","lifecycle":"active","knowledgeCutoff":"2026-01-31","structuredOutput":true,"lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]}},"entry":{"id":"claude-opus-4-7","displayName":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"knowledgeCutoff":"2026-01-31"}},"claude-opus-4-8":{"metadata":{"displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","lifecycle":"active","knowledgeCutoff":"2026-01","structuredOutput":true,"lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]}},"entry":{"id":"claude-opus-4-8","displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"knowledgeCutoff":"2026-01"}},"claude-opus-5":{"metadata":{"displayName":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","lifecycle":"active","knowledgeCutoff":"2026-05","structuredOutput":true,"lastUpdated":"2026-07-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]}},"entry":{"id":"claude-opus-5","displayName":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"knowledgeCutoff":"2026-05"}},"claude-sonnet-4-5":{"metadata":{"displayName":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","knowledgeCutoff":"2025-07-31","structuredOutput":true,"lastUpdated":"2025-09-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"toggle":true,"offBehavior":"anthropic-thinking-disabled"}},"entry":{"id":"claude-sonnet-4-5","displayName":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"],"knowledgeCutoff":"2025-07-31"}},"claude-sonnet-4-5-20250929":{"metadata":{"displayName":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","knowledgeCutoff":"2025-07-31","structuredOutput":true,"lastUpdated":"2025-09-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"toggle":true,"offBehavior":"anthropic-thinking-disabled"}},"entry":{"id":"claude-sonnet-4-5-20250929","displayName":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"],"knowledgeCutoff":"2025-07-31"}},"claude-sonnet-4-6":{"metadata":{"displayName":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","lifecycle":"active","knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"efforts":["low","medium","high","max"]}},"entry":{"id":"claude-sonnet-4-6","displayName":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","max"],"knowledgeCutoff":"2025-08-31"}},"claude-sonnet-5":{"metadata":{"displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","lifecycle":"active","knowledgeCutoff":"2026-01-31","structuredOutput":true,"lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"],"toggle":true}},"entry":{"id":"claude-sonnet-5","displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"knowledgeCutoff":"2026-01-31"}}}},"openai-codex":{"baseUrl":"https://chatgpt.com/backend-api/codex","label":"OpenAI OAuth (ChatGPT / Codex)","authKind":"oauth_token","runtimeAdapter":{"kind":"openai-codex","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol","auth":"openai-codex"},"fallbackModels":["gpt-6-astra","gpt-5.6-sol","gpt-5.6-terra","gpt-5.6-luna"],"models":{"chatgpt-image-latest":{"metadata":{"displayName":"chatgpt-image-latest","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-12-16","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"chatgpt-image-latest","displayName":"chatgpt-image-latest","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"gpt-3.5-turbo":{"metadata":{"displayName":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"deprecated","contextWindow":16385,"maxOutputTokens":4096,"knowledgeCutoff":"2021-09-01","structuredOutput":false,"lastUpdated":"2023-11-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"gpt-3.5-turbo","displayName":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16385,"defaultContextWindow":16385,"knowledgeCutoff":"2021-09-01"}},"gpt-4":{"metadata":{"displayName":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"deprecated","contextWindow":8192,"maxOutputTokens":8192,"knowledgeCutoff":"2023-11","structuredOutput":false,"lastUpdated":"2024-04-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"gpt-4","displayName":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2023-11"}},"gpt-4-turbo":{"metadata":{"displayName":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-12","structuredOutput":false,"lastUpdated":"2024-04-09","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-4-turbo","displayName":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-12"}},"gpt-4.1":{"metadata":{"displayName":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","lifecycle":"active","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-4.1","displayName":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"gpt-4.1-mini":{"metadata":{"displayName":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","lifecycle":"active","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-4.1-mini","displayName":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"gpt-4.1-nano":{"metadata":{"displayName":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","lifecycle":"deprecated","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-4.1-nano","displayName":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"gpt-4o":{"metadata":{"displayName":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-08-06","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-4o","displayName":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"gpt-4o-2024-05-13":{"metadata":{"displayName":"GPT-4o (2024-05-13)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-05-13","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-4o-2024-05-13","displayName":"GPT-4o (2024-05-13)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"gpt-4o-2024-08-06":{"metadata":{"displayName":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-08-06","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-4o-2024-08-06","displayName":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"gpt-4o-2024-11-20":{"metadata":{"displayName":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-11-20","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-4o-2024-11-20","displayName":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"gpt-4o-mini":{"metadata":{"displayName":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-07-18","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-4o-mini","displayName":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"gpt-5":{"metadata":{"displayName":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5","displayName":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2024-09-30"}},"gpt-5-mini":{"metadata":{"displayName":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-05-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5-mini","displayName":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2024-05-30"}},"gpt-5-nano":{"metadata":{"displayName":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-05-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5-nano","displayName":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2024-05-30"}},"gpt-5-pro":{"metadata":{"displayName":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","lifecycle":"active","contextWindow":400000,"maxOutputTokens":272000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-10-06","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5-pro","displayName":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2024-09-30"}},"gpt-5.1":{"metadata":{"displayName":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.1","displayName":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2024-09-30"}},"gpt-5.2":{"metadata":{"displayName":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.2","displayName":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.2-chat-latest":{"metadata":{"displayName":"GPT-5.2 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.2-chat-latest","displayName":"GPT-5.2 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium"],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.2-pro":{"metadata":{"displayName":"GPT-5.2 Pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":false,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.2-pro","displayName":"GPT-5.2 Pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.3-chat-latest":{"metadata":{"displayName":"GPT-5.3 Chat (latest)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-03","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.3-chat-latest","displayName":"GPT-5.3 Chat (latest)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.3-codex":{"metadata":{"displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-02-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.3-codex","displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.3-codex-spark":{"metadata":{"displayName":"GPT-5.3 Codex Spark","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":128000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-02-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.3-codex-spark","displayName":"GPT-5.3 Codex Spark","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4":{"metadata":{"displayName":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","lifecycle":"active","contextWindow":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.4","displayName":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":272000,"defaultContextWindow":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4-mini":{"metadata":{"displayName":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","lifecycle":"active","contextWindow":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.4-mini","displayName":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":272000,"defaultContextWindow":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4-nano":{"metadata":{"displayName":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.4-nano","displayName":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4-pro":{"metadata":{"displayName":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":false,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.4-pro","displayName":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.5":{"metadata":{"displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","lifecycle":"active","contextWindow":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.5","displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":272000,"defaultContextWindow":272000,"knowledgeCutoff":"2025-12-01"}},"gpt-5.5-pro":{"metadata":{"displayName":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.5-pro","displayName":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2025-12-01"}},"gpt-5.6":{"metadata":{"displayName":"GPT-5.6","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.6","displayName":"GPT-5.6","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2026-02-16"}},"gpt-5.6-luna":{"metadata":{"displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.6-luna","displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2026-02-16"}},"gpt-5.6-sol":{"metadata":{"displayName":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","lifecycle":"active","contextWindow":372000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.6-sol","displayName":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":372000,"defaultContextWindow":372000,"knowledgeCutoff":"2026-02-16"}},"gpt-5.6-terra":{"metadata":{"displayName":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.6-terra","displayName":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2026-02-16"}},"gpt-6-astra":{"metadata":{"displayName":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-04-30","structuredOutput":true,"lastUpdated":"2026-09-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-6-astra","displayName":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2026-04-30"}},"gpt-image-1":{"metadata":{"displayName":"gpt-image-1","description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","lifecycle":"deprecated","lastUpdated":"2025-04-24","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["image"]}},"entry":{"id":"gpt-image-1","displayName":"gpt-image-1","description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"gpt-image-1-mini":{"metadata":{"displayName":"gpt-image-1-mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-09-26","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"gpt-image-1-mini","displayName":"gpt-image-1-mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"gpt-image-1.5":{"metadata":{"displayName":"gpt-image-1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-11-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"gpt-image-1.5","displayName":"gpt-image-1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"gpt-image-2":{"metadata":{"displayName":"gpt-image-2","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["image"]}},"entry":{"id":"gpt-image-2","displayName":"gpt-image-2","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"gpt-realtime-2.1":{"metadata":{"displayName":"GPT-Realtime-2.1","description":"Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior","lifecycle":"active","contextWindow":128000,"maxOutputTokens":32000,"knowledgeCutoff":"2024-09-30","structuredOutput":false,"lastUpdated":"2026-07-06","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","audio","image"],"output":["text","audio"]}},"entry":{"id":"gpt-realtime-2.1","displayName":"GPT-Realtime-2.1","description":"Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-09-30"}},"o1":{"metadata":{"displayName":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-12-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"o1","displayName":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2023-09"}},"o1-pro":{"metadata":{"displayName":"o1-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2025-03-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"o1-pro","displayName":"o1-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2023-09"}},"o3":{"metadata":{"displayName":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"o3","displayName":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"o3-mini":{"metadata":{"displayName":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-01-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"o3-mini","displayName":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"o3-pro":{"metadata":{"displayName":"o3-pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-06-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"o3-pro","displayName":"o3-pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"o4-mini":{"metadata":{"displayName":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"o4-mini","displayName":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"text-embedding-3-large":{"metadata":{"displayName":"text-embedding-3-large","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8191,"maxOutputTokens":3072,"knowledgeCutoff":"2024-01","lastUpdated":"2024-01-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"text-embedding-3-large","displayName":"text-embedding-3-large","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8191,"defaultContextWindow":8191,"knowledgeCutoff":"2024-01"}},"text-embedding-3-small":{"metadata":{"displayName":"text-embedding-3-small","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8191,"maxOutputTokens":1536,"knowledgeCutoff":"2024-01","lastUpdated":"2024-01-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"text-embedding-3-small","displayName":"text-embedding-3-small","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8191,"defaultContextWindow":8191,"knowledgeCutoff":"2024-01"}},"text-embedding-ada-002":{"metadata":{"displayName":"text-embedding-ada-002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"knowledgeCutoff":"2022-12","lastUpdated":"2022-12-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"text-embedding-ada-002","displayName":"text-embedding-ada-002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2022-12"}},"gpt-6-sol":{"metadata":{"displayName":"GPT-6 Sol","thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"maxOutputTokens":128000},"entry":{"id":"gpt-6-sol","displayName":"GPT-6 Sol","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high","xhigh","max"]}},"gpt-6-luna":{"metadata":{"displayName":"GPT-6 Luna","thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"maxOutputTokens":128000},"entry":{"id":"gpt-6-luna","displayName":"GPT-6 Luna","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high","xhigh","max"]}}}},"zhipu":{"label":"Zhipu AI (China)","baseUrl":"https://open.bigmodel.cn/api/paas/v4","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}},"zhipu-coding-plan":{"label":"Zhipu AI Coding Plan (China)","baseUrl":"https://open.bigmodel.cn/api/coding/paas/v4","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}},"modelscope":{"label":"ModelScope","baseUrl":"https://api-inference.modelscope.cn/v1","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}},"aihubmix":{"label":"AiHubMix","baseUrl":"https://aihubmix.com/v1","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{"openai-responses":{"kind":"openai","apiProtocol":"openai-responses","responses":{"adapter":"openai","reasoningReplay":"none"}}},"retired":false,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}},"tencent-token-plan-enterprise":{"label":"Tencent Cloud Token Plan Enterprise (China)","baseUrl":"https://tokenhub.tencentmaas.com/plan/v3","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{"openai-responses":{"kind":"openai","apiProtocol":"openai-responses","responses":{"adapter":"openai","reasoningReplay":"none"}}},"retired":false,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}},"tencent-token-plan-enterprise-intl":{"label":"Tencent Cloud Token Plan Enterprise (Singapore)","baseUrl":"https://tokenhub-intl.tencentmaas.com/plan/v3","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{"openai-responses":{"kind":"openai","apiProtocol":"openai-responses","responses":{"adapter":"openai","reasoningReplay":"none"}}},"retired":false,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}},"sub2api":{"label":"Sub2API","baseUrl":"","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"connection","requireBaseUrl":true},"protocolAdapters":{},"retired":false,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}},"new-api":{"label":"New API","baseUrl":"","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"connection","requireBaseUrl":true},"protocolAdapters":{},"retired":false,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}}} +{"anthropic":{"baseUrl":"https://api.anthropic.com","label":"Anthropic","authKind":"api_key","runtimeAdapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["claude-sonnet-4-6","claude-opus-4-8","claude-haiku-4-5","claude-sonnet-4-5","claude-sonnet-4-5-20250929","claude-opus-4-1-20250805"],"models":{"claude-fable-5":{"metadata":{"displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-06-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-fable-5","displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000},"anthropicAdaptiveThinking":true},"claude-fable-5-1":{"metadata":{"displayName":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-06","structuredOutput":true,"lastUpdated":"2026-09-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-fable-5-1","displayName":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-06"},"anthropicAdaptiveThinking":true},"claude-haiku-4-5":{"metadata":{"displayName":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-02-28","structuredOutput":true,"lastUpdated":"2025-10-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"toggle":true,"offBehavior":"anthropic-thinking-disabled"}},"entry":{"id":"claude-haiku-4-5","displayName":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-02-28"},"anthropicAdaptiveThinking":false},"claude-haiku-4-5-20251001":{"metadata":{"displayName":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-02-28","structuredOutput":true,"lastUpdated":"2025-10-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"toggle":true,"offBehavior":"anthropic-thinking-disabled"}},"entry":{"id":"claude-haiku-4-5-20251001","displayName":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-02-28"},"anthropicAdaptiveThinking":false},"claude-opus-4-5":{"metadata":{"displayName":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2025-11-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-opus-4-5","displayName":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-05"},"anthropicAdaptiveThinking":false},"claude-opus-4-5-20251101":{"metadata":{"displayName":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2025-11-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-opus-4-5-20251101","displayName":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-05"},"anthropicAdaptiveThinking":false},"claude-opus-4-6":{"metadata":{"displayName":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-05-31","structuredOutput":true,"lastUpdated":"2026-03-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-opus-4-6","displayName":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05-31"},"anthropicAdaptiveThinking":true},"claude-opus-4-7":{"metadata":{"displayName":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","structuredOutput":true,"lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-opus-4-7","displayName":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"},"anthropicAdaptiveThinking":true},"claude-opus-4-8":{"metadata":{"displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01","structuredOutput":true,"lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-opus-4-8","displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01"},"anthropicAdaptiveThinking":true},"claude-opus-5":{"metadata":{"displayName":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-05","structuredOutput":true,"lastUpdated":"2026-07-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-opus-5","displayName":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-05"},"anthropicAdaptiveThinking":true},"claude-sonnet-4-5":{"metadata":{"displayName":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-07-31","structuredOutput":true,"lastUpdated":"2025-09-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"toggle":true,"offBehavior":"anthropic-thinking-disabled"}},"entry":{"id":"claude-sonnet-4-5","displayName":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-07-31"},"anthropicAdaptiveThinking":false},"claude-sonnet-4-5-20250929":{"metadata":{"displayName":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-07-31","structuredOutput":true,"lastUpdated":"2025-09-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"toggle":true,"offBehavior":"anthropic-thinking-disabled"}},"entry":{"id":"claude-sonnet-4-5-20250929","displayName":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-07-31"},"anthropicAdaptiveThinking":false},"claude-sonnet-4-6":{"metadata":{"displayName":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-sonnet-4-6","displayName":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-08-31"},"anthropicAdaptiveThinking":true},"claude-sonnet-5":{"metadata":{"displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","structuredOutput":true,"lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-sonnet-5","displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"},"anthropicAdaptiveThinking":true},"claude-opus-4-1-20250805":{"metadata":{"thinkingOptions":{"toggle":true,"offBehavior":"anthropic-thinking-disabled"}},"entry":{"id":"claude-opus-4-1-20250805","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"]},"anthropicAdaptiveThinking":false}}},"kimi-coding-plan":{"baseUrl":"https://api.kimi.com/coding/v1","label":"Kimi Coding Plan","authKind":"api_key","runtimeAdapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"protocolAdapters":{"openai-chat-completions":{"kind":"openai-compatible","name":"provider","normalizeUsage":true,"normalizeBaseUrl":true}},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["k3","kimi-for-coding"],"models":{"k3":{"metadata":{"displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"k3","displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"k3-256k":{"metadata":{"displayName":"Kimi K3-256K","description":"256K-context version of Kimi K3, reducing token consumption for shorter coding sessions","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"k3-256k","displayName":"Kimi K3-256K","description":"256K-context version of Kimi K3, reducing token consumption for shorter coding sessions","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":262144,"defaultContextWindow":262144}},"kimi-for-coding":{"metadata":{"displayName":"kimi-for-coding","description":"Kimi coding model with more efficient thinking and up to 1M context, available through Kimi Code","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":32768,"lastUpdated":"2026-09-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-for-coding","displayName":"kimi-for-coding","description":"Kimi coding model with more efficient thinking and up to 1M context, available through Kimi Code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"kimi-for-coding-highspeed":{"metadata":{"displayName":"Kimi For Coding HighSpeed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-for-coding-highspeed","displayName":"Kimi For Coding HighSpeed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}}}},"minimax-coding-plan":{"baseUrl":"https://api.minimax.io/anthropic","label":"MiniMax Coding Plan","authKind":"api_key","runtimeAdapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["MiniMax-M3","MiniMax-M2","MiniMax-M2.1","MiniMax-M2.5","MiniMax-M2.5-highspeed","MiniMax-M2.7","MiniMax-M2.7-highspeed"],"models":{"MiniMax-M2":{"metadata":{"displayName":"MiniMax-M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2025-10-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2","displayName":"MiniMax-M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.1":{"metadata":{"displayName":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2025-12-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.1","displayName":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.5","displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.5-highspeed":{"metadata":{"displayName":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.5-highspeed","displayName":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.7":{"metadata":{"displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.7","displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.7-highspeed":{"metadata":{"displayName":"MiniMax-M2.7-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.7-highspeed","displayName":"MiniMax-M2.7-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":512000,"lastUpdated":"2026-06-25","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"MiniMax-M3","displayName":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}}}},"tencent-coding-plan":{"baseUrl":"https://api.lkeap.cloud.tencent.com/coding/v3","label":"Tencent Coding Plan (China)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["tc-code-latest","glm-5","minimax-m2.5","kimi-k2.5"],"models":{"glm-5":{"metadata":{"displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":16384,"lastUpdated":"2026-02-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5","displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"hunyuan-2.0-instruct":{"metadata":{"displayName":"Tencent HY 2.0 Instruct","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"lastUpdated":"2026-03-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hunyuan-2.0-instruct","displayName":"Tencent HY 2.0 Instruct","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"hunyuan-2.0-thinking":{"metadata":{"displayName":"Tencent HY 2.0 Think","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"lastUpdated":"2026-03-08","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hunyuan-2.0-thinking","displayName":"Tencent HY 2.0 Think","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"hunyuan-t1":{"metadata":{"displayName":"Hunyuan-T1","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"lastUpdated":"2026-03-08","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hunyuan-t1","displayName":"Hunyuan-T1","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"hunyuan-turbos":{"metadata":{"displayName":"Hunyuan-TurboS","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"lastUpdated":"2026-03-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hunyuan-turbos","displayName":"Hunyuan-TurboS","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"kimi-k2.5":{"metadata":{"displayName":"Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","lastUpdated":"2026-01-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.5","displayName":"Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"minimax-m2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":32768,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax-m2.5","displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"tc-code-latest":{"metadata":{"displayName":"Auto","description":"Automatic model router for matching prompts to suitable backends and budgets","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"lastUpdated":"2026-03-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tc-code-latest","displayName":"Auto","description":"Automatic model router for matching prompts to suitable backends and budgets","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}}}},"volcengine-coding-plan":{"baseUrl":"https://ark.cn-beijing.volces.com/api/coding/v3","label":"Volcengine Ark Coding Plan (China)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["ark-code-latest","doubao-seed-2.0-code","doubao-seed-2.0-pro","doubao-seed-2.0-lite","doubao-seed-code","minimax-m2.7","minimax-m3","glm-5.2","deepseek-v4-flash","deepseek-v4-pro","kimi-k2.6","kimi-k2.7-code"],"models":{"ark-code-latest":{"metadata":{"displayName":"Ark Code Latest","lifecycle":"active","capabilities":{"reasoning":true,"functionCalling":true,"vision":false}},"entry":{"id":"ark-code-latest","displayName":"Ark Code Latest","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"doubao-seed-2.0-code":{"metadata":{"displayName":"Doubao Seed 2.0 Code","lifecycle":"active","capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"doubao-seed-2.0-code","displayName":"Doubao Seed 2.0 Code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"doubao-seed-2.0-pro":{"metadata":{"displayName":"Doubao Seed 2.0 Pro","lifecycle":"active","capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"doubao-seed-2.0-pro","displayName":"Doubao Seed 2.0 Pro","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"doubao-seed-2.0-lite":{"metadata":{"displayName":"Doubao Seed 2.0 Lite","lifecycle":"active","capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"doubao-seed-2.0-lite","displayName":"Doubao Seed 2.0 Lite","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"doubao-seed-code":{"metadata":{"displayName":"Doubao Seed Code","lifecycle":"active","capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"doubao-seed-code","displayName":"Doubao Seed Code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"minimax-m2.7":{"metadata":{"displayName":"MiniMax-M2.7","lifecycle":"active","contextWindow":200000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":false}},"entry":{"id":"minimax-m2.7","displayName":"MiniMax-M2.7","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}},"minimax-m3":{"metadata":{"displayName":"MiniMax-M3","lifecycle":"active","contextWindow":512000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"minimax-m3","displayName":"MiniMax-M3","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":512000,"defaultContextWindow":512000}},"glm-5.2":{"metadata":{"displayName":"GLM-5.2","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":false}},"entry":{"id":"glm-5.2","displayName":"GLM-5.2","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}},"deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek-V4-Flash","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":384000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":false}},"entry":{"id":"deepseek-v4-flash","displayName":"DeepSeek-V4-Flash","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}},"deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek-V4-Pro","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":384000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":false}},"entry":{"id":"deepseek-v4-pro","displayName":"DeepSeek-V4-Pro","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}},"kimi-k2.6":{"metadata":{"displayName":"Kimi-K2.6","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"kimi-k2.6","displayName":"Kimi-K2.6","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"kimi-k2.7-code":{"metadata":{"displayName":"Kimi-K2.7-Code","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"kimi-k2.7-code","displayName":"Kimi-K2.7-Code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}}}},"volcengine-agent-plan":{"baseUrl":"https://ark.cn-beijing.volces.com/api/plan/v3","label":"Volcengine Ark Agent Plan (China)","authKind":"api_key","runtimeAdapter":{"kind":"openai","apiProtocol":"openai-responses","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":false,"modelDiscovery":{"kind":"fallback","reason":"Agent Plan model discovery is a control-plane API that requires AK/SK signing; the plan API key reaches only the inference data plane"},"fallbackModels":["ark-code-latest","glm-5.3","glm-5.3-flash","doubao-seed-2.0-mini","doubao-seed-2.0-lite","deepseek-v4-flash","doubao-seed-2.1-turbo","doubao-seed-evolving","doubao-seed-2.0-code","doubao-seed-2.0-pro","minimax-m2.7","minimax-m3","glm-5.2","glm-latest","kimi-k2.6","kimi-k2.7-code","deepseek-v4-pro","kimi-k3"],"models":{"ark-code-latest":{"metadata":{"displayName":"Ark Code Latest","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"ark-code-latest","displayName":"Ark Code Latest","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"glm-5.3":{"metadata":{"displayName":"GLM-5.3","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true}},"entry":{"id":"glm-5.3","displayName":"GLM-5.3","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}},"doubao-seed-2.0-mini":{"metadata":{"displayName":"Doubao Seed 2.0 Mini","lifecycle":"active","contextWindow":256000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"doubao-seed-2.0-mini","displayName":"Doubao Seed 2.0 Mini","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"doubao-seed-2.0-lite":{"metadata":{"displayName":"Doubao Seed 2.0 Lite","lifecycle":"active","contextWindow":256000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"doubao-seed-2.0-lite","displayName":"Doubao Seed 2.0 Lite","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek-V4-Flash","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":384000,"capabilities":{"reasoning":true,"functionCalling":true}},"entry":{"id":"deepseek-v4-flash","displayName":"DeepSeek-V4-Flash","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}},"doubao-seed-2.1-turbo":{"metadata":{"displayName":"Doubao Seed 2.1 Turbo","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"doubao-seed-2.1-turbo","displayName":"Doubao Seed 2.1 Turbo","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"doubao-seed-evolving":{"metadata":{"displayName":"Doubao Seed Evolving","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":256000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"doubao-seed-evolving","displayName":"Doubao Seed Evolving","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}},"doubao-seed-2.0-code":{"metadata":{"displayName":"Doubao Seed 2.0 Code","lifecycle":"deprecated","contextWindow":256000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true}},"entry":{"id":"doubao-seed-2.0-code","displayName":"Doubao Seed 2.0 Code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"doubao-seed-2.0-pro":{"metadata":{"displayName":"Doubao Seed 2.0 Pro","lifecycle":"deprecated","contextWindow":256000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true}},"entry":{"id":"doubao-seed-2.0-pro","displayName":"Doubao Seed 2.0 Pro","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"minimax-m2.7":{"metadata":{"displayName":"MiniMax-M2.7","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true}},"entry":{"id":"minimax-m2.7","displayName":"MiniMax-M2.7","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}},"minimax-m3":{"metadata":{"displayName":"MiniMax-M3","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"minimax-m3","displayName":"MiniMax-M3","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}},"glm-5.2":{"metadata":{"displayName":"GLM-5.2","lifecycle":"deprecated","contextWindow":1024000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true}},"entry":{"id":"glm-5.2","displayName":"GLM-5.2","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}},"glm-latest":{"metadata":{"displayName":"GLM Latest","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true}},"entry":{"id":"glm-latest","displayName":"GLM Latest","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}},"glm-5.3-flash":{"metadata":{"displayName":"GLM-5.3-Flash","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"glm-5.3-flash","displayName":"GLM-5.3-Flash","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}},"kimi-k2.6":{"metadata":{"displayName":"Kimi-K2.6","lifecycle":"deprecated","contextWindow":256000,"maxOutputTokens":32000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"kimi-k2.6","displayName":"Kimi-K2.6","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"kimi-k2.7-code":{"metadata":{"displayName":"Kimi-K2.7-Code","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"kimi-k2.7-code","displayName":"Kimi-K2.7-Code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek-V4-Pro","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":384000,"capabilities":{"reasoning":true,"functionCalling":true}},"entry":{"id":"deepseek-v4-pro","displayName":"DeepSeek-V4-Pro","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}},"kimi-k3":{"metadata":{"displayName":"Kimi-K3","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":128000,"capabilities":{"reasoning":true,"functionCalling":true,"vision":true}},"entry":{"id":"kimi-k3","displayName":"Kimi-K3","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000}}}},"tencent-token-plan":{"baseUrl":"https://api.lkeap.cloud.tencent.com/plan/v3","label":"Tencent Token Plan","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["tc-code-latest","deepseek-v4-flash-202605","deepseek-v4-pro-202606","minimax-m2.5","minimax-m2.7","glm-5","glm-5.1","kimi-k2.5","hy3","hy3-preview"],"models":{"hy3":{"metadata":{"displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":256000,"inputLimit":192000,"maxOutputTokens":128000,"lastUpdated":"2026-07-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hy3","displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high"],"contextWindow":256000,"inputLimit":192000,"defaultContextWindow":256000,"defaultInputLimit":192000}},"hy4-preview":{"metadata":{"displayName":"Hy4 preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":64000,"lastUpdated":"2026-08-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hy4-preview","displayName":"Hy4 preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high"],"contextWindow":1024000,"defaultContextWindow":1024000}},"hy3-preview":{"metadata":{"thinkingOptions":{"efforts":["low","medium","high"]}},"entry":{"id":"hy3-preview","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"]}},"tc-code-latest":{"metadata":{},"entry":{"id":"tc-code-latest","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"deepseek-v4-flash-202605":{"metadata":{},"entry":{"id":"deepseek-v4-flash-202605","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"deepseek-v4-pro-202606":{"metadata":{},"entry":{"id":"deepseek-v4-pro-202606","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"minimax-m2.5":{"metadata":{},"entry":{"id":"minimax-m2.5","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"minimax-m2.7":{"metadata":{},"entry":{"id":"minimax-m2.7","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"glm-5":{"metadata":{},"entry":{"id":"glm-5","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"glm-5.1":{"metadata":{},"entry":{"id":"glm-5.1","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"kimi-k2.5":{"metadata":{},"entry":{"id":"kimi-k2.5","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}}}},"openai":{"baseUrl":"https://api.openai.com/v1","label":"OpenAI","authKind":"api_key","runtimeAdapter":{"kind":"openai","applyPatchProtocol":"openai-structured","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["gpt-5.5","gpt-5.5-pro","gpt-5.4","gpt-5.4-mini","gpt-5"],"models":{"chatgpt-image-latest":{"metadata":{"displayName":"chatgpt-image-latest","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-12-16","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"chatgpt-image-latest","displayName":"chatgpt-image-latest","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"gpt-3.5-turbo":{"metadata":{"displayName":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"deprecated","contextWindow":16385,"maxOutputTokens":4096,"knowledgeCutoff":"2021-09-01","structuredOutput":false,"lastUpdated":"2023-11-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"gpt-3.5-turbo","displayName":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16385,"defaultContextWindow":16385,"knowledgeCutoff":"2021-09-01"}},"gpt-4":{"metadata":{"displayName":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"deprecated","contextWindow":8192,"maxOutputTokens":8192,"knowledgeCutoff":"2023-11","structuredOutput":false,"lastUpdated":"2024-04-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"gpt-4","displayName":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2023-11"}},"gpt-4-turbo":{"metadata":{"displayName":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-12","structuredOutput":false,"lastUpdated":"2024-04-09","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-4-turbo","displayName":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-12"}},"gpt-4.1":{"metadata":{"displayName":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","lifecycle":"active","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-4.1","displayName":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"gpt-4.1-mini":{"metadata":{"displayName":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","lifecycle":"active","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-4.1-mini","displayName":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"gpt-4.1-nano":{"metadata":{"displayName":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","lifecycle":"deprecated","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-4.1-nano","displayName":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"gpt-4o":{"metadata":{"displayName":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-08-06","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-4o","displayName":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"gpt-4o-2024-05-13":{"metadata":{"displayName":"GPT-4o (2024-05-13)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-05-13","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-4o-2024-05-13","displayName":"GPT-4o (2024-05-13)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"gpt-4o-2024-08-06":{"metadata":{"displayName":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-08-06","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-4o-2024-08-06","displayName":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"gpt-4o-2024-11-20":{"metadata":{"displayName":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-11-20","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-4o-2024-11-20","displayName":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"gpt-4o-mini":{"metadata":{"displayName":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-07-18","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-4o-mini","displayName":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"gpt-5":{"metadata":{"displayName":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5","displayName":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"gpt-5-mini":{"metadata":{"displayName":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-05-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5-mini","displayName":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-05-30"}},"gpt-5-nano":{"metadata":{"displayName":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-05-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5-nano","displayName":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-05-30"}},"gpt-5-pro":{"metadata":{"displayName":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":272000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-10-06","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5-pro","displayName":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"gpt-5.1":{"metadata":{"displayName":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.1","displayName":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"gpt-5.2":{"metadata":{"displayName":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.2","displayName":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.2-chat-latest":{"metadata":{"displayName":"GPT-5.2 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.2-chat-latest","displayName":"GPT-5.2 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium"],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.2-pro":{"metadata":{"displayName":"GPT-5.2 Pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":false,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.2-pro","displayName":"GPT-5.2 Pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.3-chat-latest":{"metadata":{"displayName":"GPT-5.3 Chat (latest)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-03","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.3-chat-latest","displayName":"GPT-5.3 Chat (latest)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.3-codex":{"metadata":{"displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-02-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.3-codex","displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.3-codex-spark":{"metadata":{"displayName":"GPT-5.3 Codex Spark","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":128000,"inputLimit":100000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-02-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.3-codex-spark","displayName":"GPT-5.3 Codex Spark","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":128000,"inputLimit":100000,"defaultContextWindow":128000,"defaultInputLimit":100000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4":{"metadata":{"displayName":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.4","displayName":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4-mini":{"metadata":{"displayName":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.4-mini","displayName":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4-nano":{"metadata":{"displayName":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.4-nano","displayName":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4-pro":{"metadata":{"displayName":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":false,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.4-pro","displayName":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.5":{"metadata":{"displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.5","displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-12-01"}},"gpt-5.5-pro":{"metadata":{"displayName":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.5-pro","displayName":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-12-01"}},"gpt-5.6":{"metadata":{"displayName":"GPT-5.6","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.6","displayName":"GPT-5.6","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"gpt-5.6-luna":{"metadata":{"displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.6-luna","displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"gpt-5.6-sol":{"metadata":{"displayName":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.6-sol","displayName":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"gpt-5.6-terra":{"metadata":{"displayName":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.6-terra","displayName":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"gpt-6-astra":{"metadata":{"displayName":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-04-30","structuredOutput":true,"lastUpdated":"2026-09-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-6-astra","displayName":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-04-30"}},"gpt-image-1":{"metadata":{"displayName":"gpt-image-1","description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","lifecycle":"deprecated","lastUpdated":"2025-04-24","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["image"]}},"entry":{"id":"gpt-image-1","displayName":"gpt-image-1","description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"gpt-image-1-mini":{"metadata":{"displayName":"gpt-image-1-mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-09-26","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"gpt-image-1-mini","displayName":"gpt-image-1-mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"gpt-image-1.5":{"metadata":{"displayName":"gpt-image-1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-11-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"gpt-image-1.5","displayName":"gpt-image-1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"gpt-image-2":{"metadata":{"displayName":"gpt-image-2","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["image"]}},"entry":{"id":"gpt-image-2","displayName":"gpt-image-2","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"gpt-realtime-2.1":{"metadata":{"displayName":"GPT-Realtime-2.1","description":"Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior","lifecycle":"active","contextWindow":128000,"inputLimit":96000,"maxOutputTokens":32000,"knowledgeCutoff":"2024-09-30","structuredOutput":false,"lastUpdated":"2026-07-06","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","audio","image"],"output":["text","audio"]}},"entry":{"id":"gpt-realtime-2.1","displayName":"GPT-Realtime-2.1","description":"Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":128000,"inputLimit":96000,"defaultContextWindow":128000,"defaultInputLimit":96000,"knowledgeCutoff":"2024-09-30"}},"o1":{"metadata":{"displayName":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-12-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"o1","displayName":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2023-09"}},"o1-pro":{"metadata":{"displayName":"o1-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2025-03-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"o1-pro","displayName":"o1-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2023-09"}},"o3":{"metadata":{"displayName":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"o3","displayName":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"o3-mini":{"metadata":{"displayName":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-01-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"o3-mini","displayName":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"o3-pro":{"metadata":{"displayName":"o3-pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-06-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"o3-pro","displayName":"o3-pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"o4-mini":{"metadata":{"displayName":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"o4-mini","displayName":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"text-embedding-3-large":{"metadata":{"displayName":"text-embedding-3-large","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8191,"maxOutputTokens":3072,"knowledgeCutoff":"2024-01","lastUpdated":"2024-01-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"text-embedding-3-large","displayName":"text-embedding-3-large","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8191,"defaultContextWindow":8191,"knowledgeCutoff":"2024-01"}},"text-embedding-3-small":{"metadata":{"displayName":"text-embedding-3-small","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8191,"maxOutputTokens":1536,"knowledgeCutoff":"2024-01","lastUpdated":"2024-01-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"text-embedding-3-small","displayName":"text-embedding-3-small","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8191,"defaultContextWindow":8191,"knowledgeCutoff":"2024-01"}},"text-embedding-ada-002":{"metadata":{"displayName":"text-embedding-ada-002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"knowledgeCutoff":"2022-12","lastUpdated":"2022-12-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"text-embedding-ada-002","displayName":"text-embedding-ada-002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2022-12"}},"gpt-6-sol":{"metadata":{"displayName":"GPT-6 Sol","thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]}},"entry":{"id":"gpt-6-sol","displayName":"GPT-6 Sol","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high","xhigh","max"]}},"gpt-6-luna":{"metadata":{"displayName":"GPT-6 Luna","thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]}},"entry":{"id":"gpt-6-luna","displayName":"GPT-6 Luna","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high","xhigh","max"]}}}},"google":{"baseUrl":"https://generativelanguage.googleapis.com/v1beta","label":"Google Gemini","authKind":"api_key","runtimeAdapter":{"kind":"google"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["gemini-3.5-flash","gemini-3.1-pro-preview","gemini-2.5-pro","gemini-2.5-flash"],"models":{"deep-research-max-preview-04-2026":{"metadata":{"displayName":"Deep Research Max Preview (Apr-21-2026)","description":"Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text","image"]}},"entry":{"id":"deep-research-max-preview-04-2026","displayName":"Deep Research Max Preview (Apr-21-2026)","description":"Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"deep-research-preview-04-2026":{"metadata":{"displayName":"Deep Research Preview (Apr-21-2026)","description":"Agentic model for autonomous multi-step research, synthesis, and cited reports","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text","image"]}},"entry":{"id":"deep-research-preview-04-2026","displayName":"Deep Research Preview (Apr-21-2026)","description":"Agentic model for autonomous multi-step research, synthesis, and cited reports","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"gemini-2.5-computer-use-preview-10-2025":{"metadata":{"displayName":"Gemini 2.5 Computer Use Preview 10-2025","description":"Specialized Gemini 2.5 model for browser-control agents that automate UI tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","lastUpdated":"2025-10-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gemini-2.5-computer-use-preview-10-2025","displayName":"Gemini 2.5 Computer Use Preview 10-2025","description":"Specialized Gemini 2.5 model for browser-control agents that automate UI tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"gemini-2.5-flash":{"metadata":{"displayName":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-06-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true,"offBehavior":"google-thinking-budget-zero"},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]}},"entry":{"id":"gemini-2.5-flash","displayName":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-2.5-flash-image":{"metadata":{"displayName":"Nano Banana","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","lifecycle":"active","contextWindow":32768,"maxOutputTokens":32768,"knowledgeCutoff":"2024-06","lastUpdated":"2025-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"gemini-2.5-flash-image","displayName":"Nano Banana","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-06"}},"gemini-2.5-flash-lite":{"metadata":{"displayName":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-06-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]}},"entry":{"id":"gemini-2.5-flash-lite","displayName":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-2.5-flash-preview-tts":{"metadata":{"displayName":"Gemini 2.5 Flash Preview TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":16384,"knowledgeCutoff":"2025-01","lastUpdated":"2025-05-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"gemini-2.5-flash-preview-tts","displayName":"Gemini 2.5 Flash Preview TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2025-01"}},"gemini-2.5-pro":{"metadata":{"displayName":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-06-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]}},"entry":{"id":"gemini-2.5-pro","displayName":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-2.5-pro-preview-tts":{"metadata":{"displayName":"Gemini 2.5 Pro Preview TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":16384,"knowledgeCutoff":"2025-01","lastUpdated":"2025-05-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"gemini-2.5-pro-preview-tts","displayName":"Gemini 2.5 Pro Preview TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2025-01"}},"gemini-3-flash-preview":{"metadata":{"displayName":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-12-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-3-flash-preview","displayName":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-3-pro-image":{"metadata":{"displayName":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["low","high"]},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"gemini-3-pro-image","displayName":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"gemini-3-pro-image-preview":{"metadata":{"displayName":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","lastUpdated":"2025-11-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"gemini-3-pro-image-preview","displayName":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"gemini-3.1-flash-image":{"metadata":{"displayName":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":65536,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["minimal","high"]},"modalities":{"input":["text","image","video","pdf"],"output":["text","image"]}},"entry":{"id":"gemini-3.1-flash-image","displayName":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","high"],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-01"}},"gemini-3.1-flash-image-preview":{"metadata":{"displayName":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":65536,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","lastUpdated":"2026-02-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["minimal","high"]},"modalities":{"input":["text","image","pdf"],"output":["text","image"]}},"entry":{"id":"gemini-3.1-flash-image-preview","displayName":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","high"],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-01"}},"gemini-3.1-flash-lite":{"metadata":{"displayName":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-3.1-flash-lite","displayName":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-3.1-flash-lite-image":{"metadata":{"displayName":"Nano Banana 2 Lite","description":"Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing","lifecycle":"active","contextWindow":65536,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":false,"lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","high"]},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"gemini-3.1-flash-lite-image","displayName":"Nano Banana 2 Lite","description":"Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","high"],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-01"}},"gemini-3.1-flash-lite-preview":{"metadata":{"displayName":"Gemini 3.1 Flash Lite Preview","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-03-03","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-3.1-flash-lite-preview","displayName":"Gemini 3.1 Flash Lite Preview","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-3.1-flash-live-preview":{"metadata":{"displayName":"Gemini 3.1 Flash Live Preview","description":"High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":false,"lastUpdated":"2026-03-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio"],"output":["text","audio"]}},"entry":{"id":"gemini-3.1-flash-live-preview","displayName":"Gemini 3.1 Flash Live Preview","description":"High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"gemini-3.1-flash-tts-preview":{"metadata":{"displayName":"Gemini 3.1 Flash TTS Preview","description":"Low-latency speech generation with steerable prompts and expressive audio tags","lifecycle":"active","contextWindow":8192,"maxOutputTokens":16384,"knowledgeCutoff":"2025-01","lastUpdated":"2026-04-15","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"gemini-3.1-flash-tts-preview","displayName":"Gemini 3.1 Flash TTS Preview","description":"Low-latency speech generation with steerable prompts and expressive audio tags","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2025-01"}},"gemini-3.1-pro-preview":{"metadata":{"displayName":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-02-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-3.1-pro-preview","displayName":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-3.1-pro-preview-customtools":{"metadata":{"displayName":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-02-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-3.1-pro-preview-customtools","displayName":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-3.5-flash":{"metadata":{"displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-3.5-flash","displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-3.5-flash-lite":{"metadata":{"displayName":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-07-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-3.5-flash-lite","displayName":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2026-03"}},"gemini-3.5-live-translate-preview":{"metadata":{"displayName":"Gemini 3.5 Live Translate Preview","description":"Low-latency audio-to-audio model for real-time speech translation across 70+ languages","lifecycle":"active","contextWindow":16384,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","lastUpdated":"2026-06-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["audio","text"]}},"entry":{"id":"gemini-3.5-live-translate-preview","displayName":"Gemini 3.5 Live Translate Preview","description":"Low-latency audio-to-audio model for real-time speech translation across 70+ languages","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16384,"defaultContextWindow":16384,"knowledgeCutoff":"2025-01"}},"gemini-3.6-flash":{"metadata":{"displayName":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-07-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-3.6-flash","displayName":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2026-03"}},"gemini-3.7-flash":{"metadata":{"displayName":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-08-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-3.7-flash","displayName":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2026-03"}},"gemini-3.8-flash":{"metadata":{"displayName":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-3.8-flash","displayName":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576}},"gemini-embedding-001":{"metadata":{"displayName":"Gemini Embedding 001","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":2048,"maxOutputTokens":1,"knowledgeCutoff":"2025-05","lastUpdated":"2025-05-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"gemini-embedding-001","displayName":"Gemini Embedding 001","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":2048,"defaultContextWindow":2048,"knowledgeCutoff":"2025-05"}},"gemini-embedding-2":{"metadata":{"displayName":"Gemini Embedding 2","description":"Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1,"knowledgeCutoff":"2025-11","lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]}},"entry":{"id":"gemini-embedding-2","displayName":"Gemini Embedding 2","description":"Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2025-11"}},"gemini-flash-latest":{"metadata":{"displayName":"Gemini Flash Latest","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-08-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-flash-latest","displayName":"Gemini Flash Latest","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2026-03"}},"gemini-flash-lite-latest":{"metadata":{"displayName":"Gemini Flash-Lite Latest","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-07-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-flash-lite-latest","displayName":"Gemini Flash-Lite Latest","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2026-03"}},"gemini-omni-flash-preview":{"metadata":{"displayName":"Gemini Omni Flash Preview","description":"Video generation and editing model for fast, conversational text- and image-to-video workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"modalities":{"input":["text","image","video"],"output":["video"]}},"entry":{"id":"gemini-omni-flash-preview","displayName":"Gemini Omni Flash Preview","description":"Video generation and editing model for fast, conversational text- and image-to-video workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"gemma-4-26b-a4b-it":{"metadata":{"displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gemma-4-26b-a4b-it","displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"gemma-4-31b-it":{"metadata":{"displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gemma-4-31b-it","displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"lyria-3-clip-preview":{"metadata":{"displayName":"Lyria 3 Clip Preview","description":"Music generation model for short 30-second clips, loops, and previews from text or image prompts","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"structuredOutput":false,"lastUpdated":"2026-03-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","audio"]}},"entry":{"id":"lyria-3-clip-preview","displayName":"Lyria 3 Clip Preview","description":"Music generation model for short 30-second clips, loops, and previews from text or image prompts","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}},"lyria-3-pro-preview":{"metadata":{"displayName":"Lyria 3 Pro Preview","description":"Music generation model for full-length songs from text or images with vocals and structure","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"structuredOutput":false,"lastUpdated":"2026-03-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","audio"]}},"entry":{"id":"lyria-3-pro-preview","displayName":"Lyria 3 Pro Preview","description":"Music generation model for full-length songs from text or images with vocals and structure","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}},"veo-3.1-fast-generate-preview":{"metadata":{"displayName":"Veo 3.1 fast","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","contextWindow":480,"maxOutputTokens":8192,"lastUpdated":"2026-01-01","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","video"],"output":["video"]}},"entry":{"id":"veo-3.1-fast-generate-preview","displayName":"Veo 3.1 fast","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":480,"defaultContextWindow":480}},"veo-3.1-generate-preview":{"metadata":{"displayName":"Veo 3.1","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"beta","contextWindow":480,"maxOutputTokens":8192,"lastUpdated":"2026-01","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["video"]}},"entry":{"id":"veo-3.1-generate-preview","displayName":"Veo 3.1","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":480,"defaultContextWindow":480}},"veo-3.1-lite-generate-preview":{"metadata":{"displayName":"Veo 3.1 lite","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","contextWindow":480,"maxOutputTokens":8192,"lastUpdated":"2026-03-31","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["video"]}},"entry":{"id":"veo-3.1-lite-generate-preview","displayName":"Veo 3.1 lite","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":480,"defaultContextWindow":480}}}},"deepseek":{"baseUrl":"https://api.deepseek.com","label":"DeepSeek","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider","applyPatchProtocol":"codex-v4a-freeform","responses":{"adapter":"open-responses","reasoningReplay":"plaintext-content"}},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["deepseek-v4-flash","deepseek-v4-flash-vision-exp","deepseek-v4-pro","deepseek-reasoner","deepseek-chat"],"models":{"deepseek-flash":{"metadata":{"displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true,"webSearch":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-flash","displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-08-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true,"webSearch":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash","displayName":"DeepSeek V4 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-flash-vision-exp":{"metadata":{"displayName":"DeepSeek-V4-Flash-Vision-Exp","description":"Experimental DeepSeek V4 Flash model for image understanding and multimodal agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-08-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true,"webSearch":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash-vision-exp","displayName":"DeepSeek-V4-Flash-Vision-Exp","description":"Experimental DeepSeek V4 Flash model for image understanding and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"webSearch":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-pro","displayName":"DeepSeek V4 Pro","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"deepseek-reasoner":{"metadata":{},"entry":{"id":"deepseek-reasoner","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"deepseek-chat":{"metadata":{},"entry":{"id":"deepseek-chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}}}},"moonshot":{"baseUrl":"https://api.moonshot.cn/v1","label":"Moonshot","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["kimi-k2.6","kimi-k2.7-code","kimi-k2.7-code-highspeed","kimi-k3"],"models":{"kimi-k2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.6","displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k2.7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.7-code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k2.7-code-highspeed":{"metadata":{"displayName":"Kimi K2.7 Code HighSpeed","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.7-code-highspeed","displayName":"Kimi K2.7 Code HighSpeed","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k3":{"metadata":{"displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k3","displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}}}},"moonshot-global":{"baseUrl":"https://api.moonshot.ai/v1","label":"Moonshot Global","authKind":"api_key","runtimeAdapter":{"kind":"openai","apiProtocol":"openai-responses","responses":{"adapter":"open-responses","reasoningReplay":"plaintext-summary"}},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["kimi-k3","kimi-k2.6","kimi-k2.7-code","kimi-k2.7-code-highspeed"],"models":{"kimi-k2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.6","displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k2.7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.7-code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k2.7-code-highspeed":{"metadata":{"displayName":"Kimi K2.7 Code HighSpeed","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.7-code-highspeed","displayName":"Kimi K2.7 Code HighSpeed","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k3":{"metadata":{"displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k3","displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}}}},"zai-coding-plan":{"baseUrl":"https://api.z.ai/api/coding/paas/v4","label":"Z.AI Coding Plan","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["glm-5.2","glm-5.1","glm-5-turbo","glm-4.7","glm-4.5-air"],"models":{"glm-4.7":{"metadata":{"displayName":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2025-12-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.7","displayName":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"glm-5-turbo":{"metadata":{"displayName":"GLM-5-Turbo","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":200000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-03-16","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5-turbo","displayName":"GLM-5-Turbo","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}},"glm-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5.2-highspeed":{"metadata":{"displayName":"GLM-5.2 Highspeed","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.2-highspeed","displayName":"GLM-5.2 Highspeed","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5.3":{"metadata":{"displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.3","displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5.3-flash":{"metadata":{"displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"glm-5.3-flash","displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5.3-highspeed":{"metadata":{"displayName":"GLM-5.3 Highspeed","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.3-highspeed","displayName":"GLM-5.3 Highspeed","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5.1":{"metadata":{"thinkingOptions":{"toggle":true}},"entry":{"id":"glm-5.1","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"glm-5v-turbo":{"metadata":{"thinkingOptions":{"toggle":true}},"entry":{"id":"glm-5v-turbo","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"glm-4.5-air":{"metadata":{"thinkingOptions":{"toggle":true}},"entry":{"id":"glm-4.5-air","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}}}},"MiniMax":{"baseUrl":"https://api.minimax.io/anthropic/v1","label":"MiniMax","authKind":"api_key","runtimeAdapter":{"kind":"anthropic","auth":"bearer","normalizeBaseUrl":false},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["MiniMax-M3"],"models":{"MiniMax-M2":{"metadata":{"displayName":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2025-10-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2","displayName":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.1":{"metadata":{"displayName":"MiniMax-M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2025-12-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.1","displayName":"MiniMax-M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.5","displayName":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.5-highspeed":{"metadata":{"displayName":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.5-highspeed","displayName":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.7":{"metadata":{"displayName":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.7","displayName":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.7-highspeed":{"metadata":{"displayName":"MiniMax-M2.7-highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.7-highspeed","displayName":"MiniMax-M2.7-highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":512000,"lastUpdated":"2026-06-25","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"MiniMax-M3","displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}}}},"MiniMax-cn":{"baseUrl":"https://api.minimaxi.com/anthropic/v1","label":"MiniMax 中国站","authKind":"api_key","runtimeAdapter":{"kind":"anthropic","auth":"bearer","normalizeBaseUrl":false},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["MiniMax-M3"],"models":{"MiniMax-M2":{"metadata":{"displayName":"MiniMax-M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2025-10-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2","displayName":"MiniMax-M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.1":{"metadata":{"displayName":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2025-12-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.1","displayName":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.5","displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.5-highspeed":{"metadata":{"displayName":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.5-highspeed","displayName":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.7":{"metadata":{"displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.7","displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M2.7-highspeed":{"metadata":{"displayName":"MiniMax-M2.7-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.7-highspeed","displayName":"MiniMax-M2.7-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax-M3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":512000,"lastUpdated":"2026-06-25","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"MiniMax-M3","displayName":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}}}},"siliconflow":{"baseUrl":"https://api.siliconflow.com/v1","label":"SiliconFlow","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol","query":{"sub_type":"chat"}},"fallbackModels":["moonshotai/Kimi-K2.6","baidu/ERNIE-4.5-300B-A47B","ByteDance-Seed/Seed-OSS-36B-Instruct","deepseek-ai/DeepSeek-R1","deepseek-ai/DeepSeek-V3","deepseek-ai/DeepSeek-V3.1","deepseek-ai/DeepSeek-V3.1-Terminus","deepseek-ai/DeepSeek-V3.2","deepseek-ai/DeepSeek-V3.2-Exp","deepseek-ai/DeepSeek-V4-Flash","deepseek-ai/DeepSeek-V4-Pro","google/gemma-4-26B-A4B-it","google/gemma-4-31B-it","inclusionAI/Ling-flash-2.0","MiniMaxAI/MiniMax-M2.5","moonshotai/Kimi-K2.5","openai/gpt-oss-120b","openai/gpt-oss-20b","Qwen/Qwen2.5-72B-Instruct","Qwen/Qwen2.5-7B-Instruct","Qwen/Qwen3-14B","Qwen/Qwen3-235B-A22B-Thinking-2507","Qwen/Qwen3-30B-A3B-Instruct-2507","Qwen/Qwen3-32B","Qwen/Qwen3-8B","Qwen/Qwen3-Coder-30B-A3B-Instruct","Qwen/Qwen3-Coder-480B-A35B-Instruct","Qwen/Qwen3-VL-235B-A22B-Instruct","Qwen/Qwen3-VL-235B-A22B-Thinking","Qwen/Qwen3-VL-30B-A3B-Instruct","Qwen/Qwen3-VL-30B-A3B-Thinking","Qwen/Qwen3-VL-32B-Instruct","Qwen/Qwen3-VL-32B-Thinking","Qwen/Qwen3-VL-8B-Instruct","Qwen/Qwen3.5-122B-A10B","Qwen/Qwen3.5-27B","Qwen/Qwen3.5-35B-A3B","Qwen/Qwen3.5-397B-A17B","Qwen/Qwen3.5-9B","Qwen/Qwen3.6-27B","Qwen/Qwen3.6-35B-A3B","stepfun-ai/Step-3.5-Flash","tencent/Hunyuan-A13B-Instruct","tencent/Hy3-preview","zai-org/GLM-4.5-Air","zai-org/GLM-5","zai-org/GLM-5.1","zai-org/GLM-5.2","zai-org/GLM-5V-Turbo"],"models":{"baidu/ERNIE-4.5-300B-A47B":{"metadata":{"displayName":"baidu/ERNIE-4.5-300B-A47B","description":"Tool-capable chat model for instruction following and agentic application workflows","lifecycle":"active","contextWindow":131000,"maxOutputTokens":131000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"baidu/ERNIE-4.5-300B-A47B","displayName":"baidu/ERNIE-4.5-300B-A47B","description":"Tool-capable chat model for instruction following and agentic application workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000}},"ByteDance-Seed/Seed-OSS-36B-Instruct":{"metadata":{"displayName":"ByteDance-Seed/Seed-OSS-36B-Instruct","description":"Tool-capable chat model for instruction following and agentic application workflows","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"ByteDance-Seed/Seed-OSS-36B-Instruct","displayName":"ByteDance-Seed/Seed-OSS-36B-Instruct","description":"Tool-capable chat model for instruction following and agentic application workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"deepseek-ai/DeepSeek-R1":{"metadata":{"displayName":"deepseek-ai/DeepSeek-R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","lifecycle":"active","contextWindow":164000,"maxOutputTokens":164000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-R1","displayName":"deepseek-ai/DeepSeek-R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":164000,"defaultContextWindow":164000}},"deepseek-ai/DeepSeek-V3":{"metadata":{"displayName":"deepseek-ai/DeepSeek-V3","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":164000,"maxOutputTokens":164000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3","displayName":"deepseek-ai/DeepSeek-V3","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":164000,"defaultContextWindow":164000}},"deepseek-ai/DeepSeek-V3.1":{"metadata":{"displayName":"deepseek-ai/DeepSeek-V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":164000,"maxOutputTokens":164000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3.1","displayName":"deepseek-ai/DeepSeek-V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":164000,"defaultContextWindow":164000}},"deepseek-ai/DeepSeek-V3.1-Terminus":{"metadata":{"displayName":"deepseek-ai/DeepSeek-V3.1-Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":164000,"maxOutputTokens":164000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3.1-Terminus","displayName":"deepseek-ai/DeepSeek-V3.1-Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":164000,"defaultContextWindow":164000}},"deepseek-ai/DeepSeek-V3.2":{"metadata":{"displayName":"deepseek-ai/DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":164000,"maxOutputTokens":164000,"structuredOutput":true,"lastUpdated":"2025-12-03","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3.2","displayName":"deepseek-ai/DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":164000,"defaultContextWindow":164000}},"deepseek-ai/DeepSeek-V3.2-Exp":{"metadata":{"displayName":"deepseek-ai/DeepSeek-V3.2-Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":164000,"maxOutputTokens":164000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3.2-Exp","displayName":"deepseek-ai/DeepSeek-V3.2-Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":164000,"defaultContextWindow":164000}},"deepseek-ai/DeepSeek-V4-Flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Flash","displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-ai/DeepSeek-V4-Pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Pro","displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"google/gemma-4-26B-A4B-it":{"metadata":{"displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"google/gemma-4-26B-A4B-it","displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"google/gemma-4-31B-it":{"metadata":{"displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"google/gemma-4-31B-it","displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"inclusionAI/Ling-flash-2.0":{"metadata":{"displayName":"inclusionAI/Ling-flash-2.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":131000,"maxOutputTokens":131000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionAI/Ling-flash-2.0","displayName":"inclusionAI/Ling-flash-2.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000}},"MiniMaxAI/MiniMax-M2.5":{"metadata":{"displayName":"MiniMaxAI/MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":197000,"maxOutputTokens":131000,"structuredOutput":false,"lastUpdated":"2026-06-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M2.5","displayName":"MiniMaxAI/MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":197000,"defaultContextWindow":197000}},"moonshotai/Kimi-K2.5":{"metadata":{"displayName":"moonshotai/Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2.5","displayName":"moonshotai/Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"moonshotai/Kimi-K2.6":{"metadata":{"displayName":"moonshotai/Kimi-K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2026-06-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2.6","displayName":"moonshotai/Kimi-K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"openai/gpt-oss-120b":{"metadata":{"displayName":"openai/gpt-oss-120b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131000,"maxOutputTokens":8000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-120b","displayName":"openai/gpt-oss-120b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000}},"openai/gpt-oss-20b":{"metadata":{"displayName":"openai/gpt-oss-20b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131000,"maxOutputTokens":8000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-20b","displayName":"openai/gpt-oss-20b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000}},"Qwen/Qwen2.5-72B-Instruct":{"metadata":{"displayName":"Qwen/Qwen2.5-72B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":33000,"maxOutputTokens":4000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen2.5-72B-Instruct","displayName":"Qwen/Qwen2.5-72B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":33000,"defaultContextWindow":33000}},"Qwen/Qwen2.5-7B-Instruct":{"metadata":{"displayName":"Qwen/Qwen2.5-7B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":33000,"maxOutputTokens":4000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen2.5-7B-Instruct","displayName":"Qwen/Qwen2.5-7B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":33000,"defaultContextWindow":33000}},"Qwen/Qwen3-14B":{"metadata":{"displayName":"Qwen/Qwen3-14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131000,"maxOutputTokens":131000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-14B","displayName":"Qwen/Qwen3-14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000}},"Qwen/Qwen3-235B-A22B-Thinking-2507":{"metadata":{"displayName":"Qwen/Qwen3-235B-A22B-Thinking-2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","displayName":"Qwen/Qwen3-235B-A22B-Thinking-2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"Qwen/Qwen3-30B-A3B-Instruct-2507":{"metadata":{"displayName":"Qwen/Qwen3-30B-A3B-Instruct-2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-30B-A3B-Instruct-2507","displayName":"Qwen/Qwen3-30B-A3B-Instruct-2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"Qwen/Qwen3-32B":{"metadata":{"displayName":"Qwen/Qwen3-32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131000,"maxOutputTokens":131000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-32B","displayName":"Qwen/Qwen3-32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000}},"Qwen/Qwen3-8B":{"metadata":{"displayName":"Qwen/Qwen3-8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131000,"maxOutputTokens":131000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-8B","displayName":"Qwen/Qwen3-8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000}},"Qwen/Qwen3-Coder-30B-A3B-Instruct":{"metadata":{"displayName":"Qwen/Qwen3-Coder-30B-A3B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","displayName":"Qwen/Qwen3-Coder-30B-A3B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"Qwen/Qwen3-Coder-480B-A35B-Instruct":{"metadata":{"displayName":"Qwen/Qwen3-Coder-480B-A35B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","displayName":"Qwen/Qwen3-Coder-480B-A35B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"Qwen/Qwen3-VL-235B-A22B-Instruct":{"metadata":{"displayName":"Qwen/Qwen3-VL-235B-A22B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-VL-235B-A22B-Instruct","displayName":"Qwen/Qwen3-VL-235B-A22B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"Qwen/Qwen3-VL-235B-A22B-Thinking":{"metadata":{"displayName":"Qwen/Qwen3-VL-235B-A22B-Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":true,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-VL-235B-A22B-Thinking","displayName":"Qwen/Qwen3-VL-235B-A22B-Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"Qwen/Qwen3-VL-30B-A3B-Instruct":{"metadata":{"displayName":"Qwen/Qwen3-VL-30B-A3B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-VL-30B-A3B-Instruct","displayName":"Qwen/Qwen3-VL-30B-A3B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"Qwen/Qwen3-VL-30B-A3B-Thinking":{"metadata":{"displayName":"Qwen/Qwen3-VL-30B-A3B-Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":true,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-VL-30B-A3B-Thinking","displayName":"Qwen/Qwen3-VL-30B-A3B-Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"Qwen/Qwen3-VL-32B-Instruct":{"metadata":{"displayName":"Qwen/Qwen3-VL-32B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-VL-32B-Instruct","displayName":"Qwen/Qwen3-VL-32B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"Qwen/Qwen3-VL-32B-Thinking":{"metadata":{"displayName":"Qwen/Qwen3-VL-32B-Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":true,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-VL-32B-Thinking","displayName":"Qwen/Qwen3-VL-32B-Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"Qwen/Qwen3-VL-8B-Instruct":{"metadata":{"displayName":"Qwen/Qwen3-VL-8B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-VL-8B-Instruct","displayName":"Qwen/Qwen3-VL-8B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"Qwen/Qwen3.5-122B-A10B":{"metadata":{"displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-122B-A10B","displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.5-27B":{"metadata":{"displayName":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-27B","displayName":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.5-35B-A3B":{"metadata":{"displayName":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-35B-A3B","displayName":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.5-397B-A17B":{"metadata":{"displayName":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-02-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-397B-A17B","displayName":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.5-9B":{"metadata":{"displayName":"Qwen/Qwen3.5-9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-9B","displayName":"Qwen/Qwen3.5-9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.6-27B":{"metadata":{"displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.6-27B","displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.6-35B-A3B":{"metadata":{"displayName":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-04-17","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.6-35B-A3B","displayName":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"stepfun-ai/Step-3.5-Flash":{"metadata":{"displayName":"stepfun-ai/Step-3.5-Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2026-02-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"stepfun-ai/Step-3.5-Flash","displayName":"stepfun-ai/Step-3.5-Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"tencent/Hunyuan-A13B-Instruct":{"metadata":{"displayName":"tencent/Hunyuan-A13B-Instruct","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":131000,"maxOutputTokens":131000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/Hunyuan-A13B-Instruct","displayName":"tencent/Hunyuan-A13B-Instruct","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000}},"tencent/Hy3-preview":{"metadata":{"displayName":"Hy3 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"lastUpdated":"2026-04-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/Hy3-preview","displayName":"Hy3 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"zai-org/GLM-4.5-Air":{"metadata":{"displayName":"zai-org/GLM-4.5-Air","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":131000,"maxOutputTokens":131000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-4.5-Air","displayName":"zai-org/GLM-4.5-Air","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000}},"zai-org/GLM-5":{"metadata":{"displayName":"zai-org/GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":205000,"maxOutputTokens":205000,"structuredOutput":true,"lastUpdated":"2026-06-15","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5","displayName":"zai-org/GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":205000,"defaultContextWindow":205000}},"zai-org/GLM-5.1":{"metadata":{"displayName":"zai-org/GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":205000,"maxOutputTokens":205000,"structuredOutput":true,"lastUpdated":"2026-04-08","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.1","displayName":"zai-org/GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":205000,"defaultContextWindow":205000}},"zai-org/GLM-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1049000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true,"chat":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1049000,"defaultContextWindow":1049000}},"zai-org/GLM-5V-Turbo":{"metadata":{"displayName":"zai-org/GLM-5V-Turbo","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":131072,"lastUpdated":"2026-04-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true,"chat":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5V-Turbo","displayName":"zai-org/GLM-5V-Turbo","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}}}},"vercel":{"baseUrl":"https://ai-gateway.vercel.sh/v1","label":"Vercel AI Gateway","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol","auth":"none","filter":"language-models"},"fallbackModels":["anthropic/claude-opus-4.8","alibaba/qwen-3-14b","alibaba/qwen-3-235b","alibaba/qwen-3-30b","alibaba/qwen-3-32b","alibaba/qwen-3.6-max-preview","alibaba/qwen3-235b-a22b-thinking","alibaba/qwen3-coder","alibaba/qwen3-coder-30b-a3b","alibaba/qwen3-coder-next","alibaba/qwen3-coder-plus","alibaba/qwen3-max","alibaba/qwen3-max-preview","alibaba/qwen3-max-thinking","alibaba/qwen3-next-80b-a3b-instruct","alibaba/qwen3-next-80b-a3b-thinking","alibaba/qwen3-vl-instruct","alibaba/qwen3-vl-thinking","alibaba/qwen3.5-flash","alibaba/qwen3.5-plus","alibaba/qwen3.6-27b","alibaba/qwen3.6-plus","alibaba/qwen3.7-flash","alibaba/qwen3.7-max","alibaba/qwen3.7-plus","alibaba/qwen3.8-2.4t-a95b","alibaba/qwen3.8-27b","alibaba/qwen3.8-flash","alibaba/qwen3.8-max","alibaba/qwen3.8-max-0902","amazon/nova-lite","amazon/nova-micro","amazon/nova-pro","anthropic/claude-3-haiku","anthropic/claude-fable-5","anthropic/claude-fable-5.1","anthropic/claude-haiku-4.5","anthropic/claude-opus-4","anthropic/claude-opus-4.5","anthropic/claude-opus-4.6","anthropic/claude-opus-4.7","anthropic/claude-opus-4.8-fast","anthropic/claude-opus-5","anthropic/claude-opus-5-fast","anthropic/claude-sonnet-4","anthropic/claude-sonnet-4.5","anthropic/claude-sonnet-4.6","anthropic/claude-sonnet-5","arcee-ai/trinity-large-thinking","bytedance/seed-1.6","bytedance/seed-1.8","bytedance/seed-2.1-turbo","cohere/command-a","deepseek/deepseek-v3.1","deepseek/deepseek-v3.1-terminus","deepseek/deepseek-v3.2-thinking","deepseek/deepseek-v4-flash","deepseek/deepseek-v4-flash-0731","deepseek/deepseek-v4-flash-vision-exp","deepseek/deepseek-v4-pro","deepseek/deepseek-v4-pro-0813","deepseek/deepseek-v4.1-flash","google/gemini-2.5-flash","google/gemini-2.5-flash-lite","google/gemini-2.5-pro","google/gemini-3-flash","google/gemini-3.1-flash-lite","google/gemini-3.1-pro-preview","google/gemini-3.5-flash","google/gemini-3.5-flash-lite","google/gemini-3.6-flash","google/gemini-3.7-flash","google/gemini-3.8-flash","google/gemma-4-26b-a4b-it","google/gemma-4-31b-it","inception/mercury-2","inception/mercury-2.5","inception/mercury-coder-small","inclusionai/ling-3.0-flash","inclusionai/ling-3.0-flash-fin","inclusionai/ling-3.0-flash-fin-free","inclusionai/ling-3.0-flash-sante","inclusionai/ling-3.0-flash-sante-free","inclusionai/ling-3.0-flash-vl","inclusionai/ling-3.0-flash-vl-free","kwaipilot/kat-coder-air-v2.5","kwaipilot/kat-coder-pro-v2","kwaipilot/kat-coder-pro-v2.5","meta/llama-3.1-70b","meta/llama-3.1-8b","meta/llama-3.3-70b","meta/llama-4-maverick","meta/llama-4-scout","meta/muse-glimmer-30b","meta/muse-spark-1.1","meta/muse-spark-1.2","meta/muse-spark-1.2-contributor","meta/muse-spark-1.3","meta/muse-spark-1.3-contributor","minimax/minimax-m2","minimax/minimax-m2.1","minimax/minimax-m2.1-lightning","minimax/minimax-m2.5","minimax/minimax-m2.5-highspeed","minimax/minimax-m2.7","minimax/minimax-m2.7-highspeed","minimax/minimax-m3","mistral/codestral","mistral/devstral-2","mistral/devstral-small-2","mistral/ministral-3b","mistral/ministral-8b","mistral/mistral-medium","mistral/mistral-medium-3.5","mistral/mistral-nemo","mistral/mistral-small","mistral/pixtral-12b","moonshotai/kimi-k2","moonshotai/kimi-k2-thinking","moonshotai/kimi-k2.5","moonshotai/kimi-k2.6","moonshotai/kimi-k2.7-code","moonshotai/kimi-k2.7-code-highspeed","moonshotai/kimi-k3","moonshotai/kimi-k3-fast","nvidia/nemotron-3-ultra-550b-a55b","nvidia/nemotron-3.5-lightning","nvidia/nemotron-nano-12b-v2-vl","nvidia/nemotron-nano-9b-v2","openai/gpt-4.1","openai/gpt-4.1-fast","openai/gpt-4.1-mini","openai/gpt-4.1-mini-fast","openai/gpt-4.1-nano-fast","openai/gpt-4o","openai/gpt-4o-fast","openai/gpt-4o-mini","openai/gpt-4o-mini-fast","openai/gpt-5","openai/gpt-5-codex","openai/gpt-5-fast","openai/gpt-5-mini","openai/gpt-5-mini-fast","openai/gpt-5-nano","openai/gpt-5-pro","openai/gpt-5.1-codex","openai/gpt-5.1-codex-max","openai/gpt-5.1-codex-mini","openai/gpt-5.1-thinking","openai/gpt-5.1-thinking-fast","openai/gpt-5.2","openai/gpt-5.2-codex","openai/gpt-5.2-fast","openai/gpt-5.2-pro","openai/gpt-5.3-codex","openai/gpt-5.3-codex-fast","openai/gpt-5.4","openai/gpt-5.4-fast","openai/gpt-5.4-mini","openai/gpt-5.4-mini-fast","openai/gpt-5.4-nano","openai/gpt-5.4-pro","openai/gpt-5.5","openai/gpt-5.5-fast","openai/gpt-5.5-pro","openai/gpt-5.6-luna","openai/gpt-5.6-luna-fast","openai/gpt-5.6-sol","openai/gpt-5.6-sol-fast","openai/gpt-5.6-terra","openai/gpt-5.6-terra-fast","openai/gpt-6-astra","openai/gpt-6-astra-fast","openai/gpt-oss-120b","openai/gpt-oss-20b","openai/gpt-oss-safeguard-120b","openai/gpt-oss-safeguard-20b","openai/o3","openai/o3-fast","openai/o3-pro","openai/o4-mini-fast","perplexity/sonar","perplexity/sonar-pro","poolside/laguna-s-2.1","poolside/laguna-s-2.1-free","sakana/fugu-max","sakana/fugu-ultra","sakana/fugu-ultra-v2","sakana/namazu","spacexai/grok-4.1-fast-non-reasoning","spacexai/grok-4.1-fast-reasoning","spacexai/grok-4.20-multi-agent","spacexai/grok-4.20-multi-agent-beta","spacexai/grok-4.20-non-reasoning","spacexai/grok-4.20-non-reasoning-beta","spacexai/grok-4.20-reasoning","spacexai/grok-4.20-reasoning-beta","spacexai/grok-4.3","spacexai/grok-4.5","spacexai/grok-4.6","spacexai/grok-build-0.1","stepfun/step-3.5-flash","stepfun/step-3.7-flash","tencent/hy3","tencent/hy4-preview","thinkingmachines/inkling","thinkingmachines/inkling-small","xiaomi/mimo-v2.5","xiaomi/mimo-v2.5-pro","zai/glm-4.5","zai/glm-4.5-air","zai/glm-4.5v","zai/glm-4.6","zai/glm-4.7","zai/glm-4.7-flash","zai/glm-4.7-flashx","zai/glm-5","zai/glm-5-turbo","zai/glm-5.1","zai/glm-5.2","zai/glm-5.2-fast","zai/glm-5.3","zai/glm-5.3-fast","zai/glm-5.3-flash","zai/glm-5v-turbo"],"models":{"alibaba/qwen-3-14b":{"metadata":{"displayName":"Qwen3-14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":40960,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen-3-14b","displayName":"Qwen3-14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":40960,"defaultContextWindow":40960,"knowledgeCutoff":"2025-04"}},"alibaba/qwen-3-235b":{"metadata":{"displayName":"Qwen3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen-3-235b","displayName":"Qwen3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"alibaba/qwen-3-30b":{"metadata":{"displayName":"Qwen3-30B-A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":40960,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen-3-30b","displayName":"Qwen3-30B-A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":40960,"defaultContextWindow":40960,"knowledgeCutoff":"2025-04"}},"alibaba/qwen-3-32b":{"metadata":{"displayName":"Qwen 3.32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen-3-32b","displayName":"Qwen 3.32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-04"}},"alibaba/qwen-3.6-max-preview":{"metadata":{"displayName":"Qwen 3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","lifecycle":"active","contextWindow":240000,"maxOutputTokens":64000,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen-3.6-max-preview","displayName":"Qwen 3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":240000,"defaultContextWindow":240000}},"alibaba/qwen3-235b-a22b-thinking":{"metadata":{"displayName":"Qwen3 235B A22B Thinking 2507","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-235b-a22b-thinking","displayName":"Qwen3 235B A22B Thinking 2507","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3-coder":{"metadata":{"displayName":"Qwen3 Coder 480B A35B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-coder","displayName":"Qwen3 Coder 480B A35B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3-coder-30b-a3b":{"metadata":{"displayName":"Qwen 3 Coder 30B A3B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":8192,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-coder-30b-a3b","displayName":"Qwen 3 Coder 30B A3B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3-coder-next":{"metadata":{"displayName":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-09","structuredOutput":true,"lastUpdated":"2026-02-03","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-coder-next","displayName":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-09"}},"alibaba/qwen3-coder-plus":{"metadata":{"displayName":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-coder-plus","displayName":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3-embedding-0.6b":{"metadata":{"displayName":"Qwen3 Embedding 0.6B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":32768,"maxOutputTokens":32768,"lastUpdated":"2025-11-14","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-embedding-0.6b","displayName":"Qwen3 Embedding 0.6B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"alibaba/qwen3-embedding-4b":{"metadata":{"displayName":"Qwen3 Embedding 4B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":32768,"maxOutputTokens":32768,"lastUpdated":"2025-06-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-embedding-4b","displayName":"Qwen3 Embedding 4B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"alibaba/qwen3-embedding-8b":{"metadata":{"displayName":"Qwen3 Embedding 8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":32768,"maxOutputTokens":32768,"lastUpdated":"2025-06-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-embedding-8b","displayName":"Qwen3 Embedding 8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"alibaba/qwen3-max":{"metadata":{"displayName":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-max","displayName":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3-max-preview":{"metadata":{"displayName":"Qwen3 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-max-preview","displayName":"Qwen3 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3-max-thinking":{"metadata":{"displayName":"Qwen 3 Max Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":256000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","lastUpdated":"2025-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-max-thinking","displayName":"Qwen 3 Max Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-01"}},"alibaba/qwen3-next-80b-a3b-instruct":{"metadata":{"displayName":"Qwen3 Next 80B A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-next-80b-a3b-instruct","displayName":"Qwen3 Next 80B A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3-next-80b-a3b-thinking":{"metadata":{"displayName":"Qwen3 Next 80B A3B Thinking","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-next-80b-a3b-thinking","displayName":"Qwen3 Next 80B A3B Thinking","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3-vl-235b-a22b-instruct":{"metadata":{"displayName":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":129024,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-09-23","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-vl-235b-a22b-instruct","displayName":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-03-31"}},"alibaba/qwen3-vl-instruct":{"metadata":{"displayName":"Qwen3 VL Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":129024,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-24","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-vl-instruct","displayName":"Qwen3 VL Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3-vl-thinking":{"metadata":{"displayName":"Qwen3 VL Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-09","lastUpdated":"2025-09-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"alibaba/qwen3-vl-thinking","displayName":"Qwen3 VL Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-09"}},"alibaba/qwen3.5-flash":{"metadata":{"displayName":"Qwen 3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.5-flash","displayName":"Qwen 3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"alibaba/qwen3.5-plus":{"metadata":{"displayName":"Qwen 3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.5-plus","displayName":"Qwen 3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3.6-27b":{"metadata":{"displayName":"Qwen 3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.6-27b","displayName":"Qwen 3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"alibaba/qwen3.6-plus":{"metadata":{"displayName":"Qwen 3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-04","lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.6-plus","displayName":"Qwen 3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3.7-flash":{"metadata":{"displayName":"Qwen 3.7 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":991000,"maxOutputTokens":64000,"structuredOutput":true,"lastUpdated":"2026-07-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.7-flash","displayName":"Qwen 3.7 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":991000,"defaultContextWindow":991000}},"alibaba/qwen3.7-max":{"metadata":{"displayName":"Qwen 3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","lifecycle":"active","contextWindow":991000,"maxOutputTokens":64000,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.7-max","displayName":"Qwen 3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":991000,"defaultContextWindow":991000}},"alibaba/qwen3.7-plus":{"metadata":{"displayName":"Qwen 3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-04","lastUpdated":"2026-06-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.7-plus","displayName":"Qwen 3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"alibaba/qwen3.8-2.4t-a95b":{"metadata":{"displayName":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.8-2.4t-a95b","displayName":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":262144,"defaultContextWindow":262144}},"alibaba/qwen3.8-27b":{"metadata":{"displayName":"Qwen3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.8-27b","displayName":"Qwen3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"alibaba/qwen3.8-flash":{"metadata":{"displayName":"Qwen 3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":991000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.8-flash","displayName":"Qwen 3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":991000,"defaultContextWindow":991000}},"alibaba/qwen3.8-max":{"metadata":{"displayName":"Qwen 3.8 Max","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"lastUpdated":"2026-07-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.8-max","displayName":"Qwen 3.8 Max","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"alibaba/qwen3.8-max-0902":{"metadata":{"displayName":"Qwen3.8 Max 0902","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":991000,"maxOutputTokens":128000,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"alibaba/qwen3.8-max-0902","displayName":"Qwen3.8 Max 0902","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":991000,"defaultContextWindow":991000}},"alibaba/wan-v2.5-t2v-preview":{"metadata":{"displayName":"Wan v2.5 Text-to-Video Preview","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2025-09-24","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"alibaba/wan-v2.5-t2v-preview","displayName":"Wan v2.5 Text-to-Video Preview","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"alibaba/wan-v2.6-i2v":{"metadata":{"displayName":"Wan v2.6 Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-12-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"alibaba/wan-v2.6-i2v","displayName":"Wan v2.6 Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"alibaba/wan-v2.6-i2v-flash":{"metadata":{"displayName":"Wan v2.6 Image-to-Video Flash","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-12-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"alibaba/wan-v2.6-i2v-flash","displayName":"Wan v2.6 Image-to-Video Flash","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"alibaba/wan-v2.6-r2v":{"metadata":{"displayName":"Wan v2.6 Reference-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2025-12-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"alibaba/wan-v2.6-r2v","displayName":"Wan v2.6 Reference-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"alibaba/wan-v2.6-r2v-flash":{"metadata":{"displayName":"Wan v2.6 Reference-to-Video Flash","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2025-12-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"alibaba/wan-v2.6-r2v-flash","displayName":"Wan v2.6 Reference-to-Video Flash","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"alibaba/wan-v2.6-t2v":{"metadata":{"displayName":"Wan v2.6 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2025-12-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"alibaba/wan-v2.6-t2v","displayName":"Wan v2.6 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"alibaba/wan-v2.7-r2v":{"metadata":{"displayName":"Wan v2.7 Reference-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"alibaba/wan-v2.7-r2v","displayName":"Wan v2.7 Reference-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"alibaba/wan-v2.7-t2v":{"metadata":{"displayName":"Wan v2.7 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"alibaba/wan-v2.7-t2v","displayName":"Wan v2.7 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"alibaba/wan-v3.0-video":{"metadata":{"displayName":"Wan v3.0 Video","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-08-23","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["video"]}},"entry":{"id":"alibaba/wan-v3.0-video","displayName":"Wan v3.0 Video","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"alibaba/wan-v3.0-video-prime":{"metadata":{"displayName":"Wan v3.0 Video Prime","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-08-28","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["video"]}},"entry":{"id":"alibaba/wan-v3.0-video-prime","displayName":"Wan v3.0 Video Prime","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"amazon/nova-2-lite":{"metadata":{"displayName":"Nova 2 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":1000000,"knowledgeCutoff":"2024-10","lastUpdated":"2024-12-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"amazon/nova-2-lite","displayName":"Nova 2 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-10"}},"amazon/nova-lite":{"metadata":{"displayName":"Nova Lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":300000,"maxOutputTokens":10000,"knowledgeCutoff":"2024-10","lastUpdated":"2024-12-03","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"amazon/nova-lite","displayName":"Nova Lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":300000,"defaultContextWindow":300000,"knowledgeCutoff":"2024-10"}},"amazon/nova-micro":{"metadata":{"displayName":"Nova Micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":128000,"maxOutputTokens":10000,"knowledgeCutoff":"2024-10","lastUpdated":"2024-12-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"amazon/nova-micro","displayName":"Nova Micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-10"}},"amazon/nova-pro":{"metadata":{"displayName":"Nova Pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":300000,"maxOutputTokens":10000,"knowledgeCutoff":"2024-10","lastUpdated":"2024-12-03","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"amazon/nova-pro","displayName":"Nova Pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":300000,"defaultContextWindow":300000,"knowledgeCutoff":"2024-10"}},"amazon/titan-embed-text-v2":{"metadata":{"displayName":"Titan Text Embeddings V2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2024-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"amazon/titan-embed-text-v2","displayName":"Titan Text Embeddings V2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"anthropic/claude-3-haiku":{"metadata":{"displayName":"Claude Haiku 3","description":"Legacy model retained for compatibility with older integrations","lifecycle":"active","contextWindow":200000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-08-31","lastUpdated":"2024-03-13","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"anthropic/claude-3-haiku","displayName":"Claude Haiku 3","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2023-08-31"}},"anthropic/claude-fable-5":{"metadata":{"displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-06-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-fable-5","displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"anthropic/claude-fable-5.1":{"metadata":{"displayName":"Claude Fable 5.1","description":"Claude model for creative writing, analysis, and controlled agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-06","lastUpdated":"2026-09-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-fable-5.1","displayName":"Claude Fable 5.1","description":"Claude model for creative writing, analysis, and controlled agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-06"}},"anthropic/claude-haiku-4.5":{"metadata":{"displayName":"Claude Haiku 4.5","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-02-28","lastUpdated":"2025-10-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-haiku-4.5","displayName":"Claude Haiku 4.5","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-02-28"}},"anthropic/claude-opus-4":{"metadata":{"displayName":"Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":8192,"knowledgeCutoff":"2025-03-31","lastUpdated":"2025-05-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4","displayName":"Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-03-31"}},"anthropic/claude-opus-4.5":{"metadata":{"displayName":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-05","lastUpdated":"2025-11-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4.5","displayName":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-05"}},"anthropic/claude-opus-4.6":{"metadata":{"displayName":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-05-31","lastUpdated":"2026-03-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4.6","displayName":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05-31"}},"anthropic/claude-opus-4.7":{"metadata":{"displayName":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4.7","displayName":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"anthropic/claude-opus-4.8":{"metadata":{"displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01","lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4.8","displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01"}},"anthropic/claude-opus-4.8-fast":{"metadata":{"displayName":"Claude Opus 4.8 (Fast)","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01","lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4.8-fast","displayName":"Claude Opus 4.8 (Fast)","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01"}},"anthropic/claude-opus-5":{"metadata":{"displayName":"Claude Opus 5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-05","lastUpdated":"2026-07-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-5","displayName":"Claude Opus 5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-05"}},"anthropic/claude-opus-5-fast":{"metadata":{"displayName":"Claude Opus 5 (Fast)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-05","lastUpdated":"2026-07-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-5-fast","displayName":"Claude Opus 5 (Fast)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-05"}},"anthropic/claude-sonnet-4":{"metadata":{"displayName":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":8192,"knowledgeCutoff":"2025-03-31","lastUpdated":"2025-05-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-sonnet-4","displayName":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-03-31"}},"anthropic/claude-sonnet-4.5":{"metadata":{"displayName":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-07-31","structuredOutput":true,"lastUpdated":"2025-09-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-sonnet-4.5","displayName":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-07-31"}},"anthropic/claude-sonnet-4.6":{"metadata":{"displayName":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-03-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-sonnet-4.6","displayName":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-08-31"}},"anthropic/claude-sonnet-5":{"metadata":{"displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-sonnet-5","displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"arcee-ai/trinity-large-thinking":{"metadata":{"displayName":"Trinity Large Thinking","description":"Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use","lifecycle":"active","contextWindow":262100,"maxOutputTokens":80000,"lastUpdated":"2026-04-03","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"arcee-ai/trinity-large-thinking","displayName":"Trinity Large Thinking","description":"Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262100,"defaultContextWindow":262100}},"bfl/flux-2-flex":{"metadata":{"displayName":"FLUX.2 [flex]","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-06-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bfl/flux-2-flex","displayName":"FLUX.2 [flex]","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"bfl/flux-2-klein-4b":{"metadata":{"displayName":"FLUX.2 [klein] 4B","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-06-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bfl/flux-2-klein-4b","displayName":"FLUX.2 [klein] 4B","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"bfl/flux-2-klein-9b":{"metadata":{"displayName":"FLUX.2 [klein] 9B","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-06-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bfl/flux-2-klein-9b","displayName":"FLUX.2 [klein] 9B","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"bfl/flux-2-max":{"metadata":{"displayName":"FLUX.2 [max]","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":67300,"maxOutputTokens":67300,"lastUpdated":"2026-06-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bfl/flux-2-max","displayName":"FLUX.2 [max]","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":67300,"defaultContextWindow":67300}},"bfl/flux-2-pro":{"metadata":{"displayName":"FLUX.2 [pro]","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":67300,"maxOutputTokens":67300,"lastUpdated":"2026-06-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bfl/flux-2-pro","displayName":"FLUX.2 [pro]","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":67300,"defaultContextWindow":67300}},"bfl/flux-3-video":{"metadata":{"displayName":"Flux 3","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-08-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"bfl/flux-3-video","displayName":"Flux 3","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"bfl/flux-kontext-max":{"metadata":{"displayName":"FLUX.1 Kontext Max","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":512,"lastUpdated":"2025-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bfl/flux-kontext-max","displayName":"FLUX.1 Kontext Max","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":512,"defaultContextWindow":512}},"bfl/flux-kontext-pro":{"metadata":{"displayName":"FLUX.1 Kontext Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":512,"lastUpdated":"2025-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bfl/flux-kontext-pro","displayName":"FLUX.1 Kontext Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":512,"defaultContextWindow":512}},"bfl/flux-pro-1.0-fill":{"metadata":{"displayName":"FLUX.1 Fill [pro]","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":512,"lastUpdated":"2024-10","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bfl/flux-pro-1.0-fill","displayName":"FLUX.1 Fill [pro]","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":512,"defaultContextWindow":512}},"bfl/flux-pro-1.1":{"metadata":{"displayName":"FLUX1.1 [pro]","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":512,"lastUpdated":"2024-10","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bfl/flux-pro-1.1","displayName":"FLUX1.1 [pro]","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":512,"defaultContextWindow":512}},"bfl/flux-pro-1.1-ultra":{"metadata":{"displayName":"FLUX1.1 [pro] Ultra","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":512,"lastUpdated":"2024-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bfl/flux-pro-1.1-ultra","displayName":"FLUX1.1 [pro] Ultra","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":512,"defaultContextWindow":512}},"bytedance/seed-1.6":{"metadata":{"displayName":"Seed 1.6","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"knowledgeCutoff":"2024-10","lastUpdated":"2025-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"bytedance/seed-1.6","displayName":"Seed 1.6","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-10"}},"bytedance/seed-1.8":{"metadata":{"displayName":"Seed 1.8","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2024-10","lastUpdated":"2025-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"bytedance/seed-1.8","displayName":"Seed 1.8","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-10"}},"bytedance/seed-2.1-turbo":{"metadata":{"displayName":"Seed 2.1 Turbo","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"lastUpdated":"2026-06-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","minimal","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"bytedance/seed-2.1-turbo","displayName":"Seed 2.1 Turbo","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","minimal","low","medium","high","xhigh","max"],"contextWindow":262144,"defaultContextWindow":262144}},"bytedance/seedance-2.0":{"metadata":{"displayName":"Seedance 2.0","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["video"]}},"entry":{"id":"bytedance/seedance-2.0","displayName":"Seedance 2.0","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"bytedance/seedance-2.0-fast":{"metadata":{"displayName":"Seedance 2.0 Fast","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["video"]}},"entry":{"id":"bytedance/seedance-2.0-fast","displayName":"Seedance 2.0 Fast","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"bytedance/seedance-2.0-mini":{"metadata":{"displayName":"Seedance 2.0 Mini","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-06-22","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["video"]}},"entry":{"id":"bytedance/seedance-2.0-mini","displayName":"Seedance 2.0 Mini","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"bytedance/seedance-2.5":{"metadata":{"displayName":"Seedance 2.5","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-08-07","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"bytedance/seedance-2.5","displayName":"Seedance 2.5","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"bytedance/seedance-v1.0-pro":{"metadata":{"displayName":"Seedance v1.0 Pro","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2025-06-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"bytedance/seedance-v1.0-pro","displayName":"Seedance v1.0 Pro","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"bytedance/seedance-v1.0-pro-fast":{"metadata":{"displayName":"Seedance v1.0 Pro Fast","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2025-10-31","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"bytedance/seedance-v1.0-pro-fast","displayName":"Seedance v1.0 Pro Fast","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"bytedance/seedance-v1.5-pro":{"metadata":{"displayName":"Seedance v1.5 Pro","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2025-12-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"bytedance/seedance-v1.5-pro","displayName":"Seedance v1.5 Pro","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"bytedance/seedream-4.0":{"metadata":{"displayName":"Seedream 4.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-08-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bytedance/seedream-4.0","displayName":"Seedream 4.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"bytedance/seedream-4.5":{"metadata":{"displayName":"Seedream 4.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-11-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bytedance/seedream-4.5","displayName":"Seedream 4.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"bytedance/seedream-5.0-lite":{"metadata":{"displayName":"Seedream 5.0 Lite","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-01-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bytedance/seedream-5.0-lite","displayName":"Seedream 5.0 Lite","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"bytedance/seedream-5.0-pro":{"metadata":{"displayName":"Seedream 5.0 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-07-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"bytedance/seedream-5.0-pro","displayName":"Seedream 5.0 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"cohere/command-a":{"metadata":{"displayName":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","lifecycle":"active","contextWindow":256000,"maxOutputTokens":8000,"knowledgeCutoff":"2024-10","lastUpdated":"2025-03-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"cohere/command-a","displayName":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-10"}},"cohere/embed-v4.0":{"metadata":{"displayName":"Embed v4.0","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":128000,"maxOutputTokens":1536,"lastUpdated":"2025-04-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"cohere/embed-v4.0","displayName":"Embed v4.0","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"cohere/rerank-v3.5":{"metadata":{"displayName":"Cohere Rerank 3.5","description":"Reranking model for improving retrieval quality in search and recommendation systems","lifecycle":"active","contextWindow":4096,"maxOutputTokens":4096,"lastUpdated":"2024-12-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"cohere/rerank-v3.5","displayName":"Cohere Rerank 3.5","description":"Reranking model for improving retrieval quality in search and recommendation systems","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":4096,"defaultContextWindow":4096}},"cohere/rerank-v4-fast":{"metadata":{"displayName":"Cohere Rerank 4 Fast","description":"Reranking model for improving retrieval quality in search and recommendation systems","lifecycle":"active","contextWindow":32000,"maxOutputTokens":32000,"lastUpdated":"2025-12-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"cohere/rerank-v4-fast","displayName":"Cohere Rerank 4 Fast","description":"Reranking model for improving retrieval quality in search and recommendation systems","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"cohere/rerank-v4-pro":{"metadata":{"displayName":"Cohere Rerank 4 Pro","description":"Reranking model for improving retrieval quality in search and recommendation systems","lifecycle":"active","contextWindow":32000,"maxOutputTokens":32000,"lastUpdated":"2025-12-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"cohere/rerank-v4-pro","displayName":"Cohere Rerank 4 Pro","description":"Reranking model for improving retrieval quality in search and recommendation systems","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"deepseek/deepseek-r1":{"metadata":{"displayName":"DeepSeek-R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","lifecycle":"active","contextWindow":128000,"maxOutputTokens":32768,"knowledgeCutoff":"2024-07","lastUpdated":"2025-05-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-r1","displayName":"DeepSeek-R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-07"}},"deepseek/deepseek-v3.1":{"metadata":{"displayName":"DeepSeek-V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":128000,"lastUpdated":"2025-08-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v3.1","displayName":"DeepSeek-V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840}},"deepseek/deepseek-v3.1-terminus":{"metadata":{"displayName":"DeepSeek V3.1 Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"knowledgeCutoff":"2025-07","lastUpdated":"2025-09-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v3.1-terminus","displayName":"DeepSeek V3.1 Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-07"}},"deepseek/deepseek-v3.2":{"metadata":{"displayName":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8000,"knowledgeCutoff":"2024-07","structuredOutput":true,"lastUpdated":"2025-12-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v3.2","displayName":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-07"}},"deepseek/deepseek-v3.2-thinking":{"metadata":{"displayName":"DeepSeek V3.2 Thinking","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8000,"knowledgeCutoff":"2024-07","lastUpdated":"2025-12-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v3.2-thinking","displayName":"DeepSeek V3.2 Thinking","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-07"}},"deepseek/deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-flash","displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek/deepseek-v4-flash-0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-flash-0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek/deepseek-v4-flash-vision-exp":{"metadata":{"displayName":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"structuredOutput":true,"lastUpdated":"2026-08-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-flash-vision-exp","displayName":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"deepseek/deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-pro","displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek/deepseek-v4-pro-0813":{"metadata":{"displayName":"DeepSeek V4 Pro 0813","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-pro-0813","displayName":"DeepSeek V4 Pro 0813","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"deepseek/deepseek-v4.1-flash":{"metadata":{"displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4.1-flash","displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"fish-audio/s1":{"metadata":{"displayName":"S1","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2025-10-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"fish-audio/s1","displayName":"S1","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"fish-audio/s1-free":{"metadata":{"displayName":"S1 (Free)","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2025-10-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"fish-audio/s1-free","displayName":"S1 (Free)","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"fish-audio/s2-pro":{"metadata":{"displayName":"S2 Pro","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-03-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"fish-audio/s2-pro","displayName":"S2 Pro","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"fish-audio/s2-pro-free":{"metadata":{"displayName":"S2 Pro (Free)","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-03-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"fish-audio/s2-pro-free","displayName":"S2 Pro (Free)","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"fish-audio/s2.1-pro":{"metadata":{"displayName":"S2.1 Pro","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-07-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"fish-audio/s2.1-pro","displayName":"S2.1 Pro","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"fish-audio/s2.1-pro-free":{"metadata":{"displayName":"S2.1 Pro (Free)","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-07-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"fish-audio/s2.1-pro-free","displayName":"S2.1 Pro (Free)","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"fish-audio/transcribe-1":{"metadata":{"displayName":"Transcribe-1","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2026-03-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"fish-audio/transcribe-1","displayName":"Transcribe-1","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"fish-audio/transcribe-1-free":{"metadata":{"displayName":"Transcribe-1 (Free)","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2026-03-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"fish-audio/transcribe-1-free","displayName":"Transcribe-1 (Free)","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"google/gemini-2.5-flash":{"metadata":{"displayName":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-06-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-2.5-flash","displayName":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-2.5-flash-image":{"metadata":{"displayName":"Nano Banana (Gemini 2.5 Flash Image)","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","lifecycle":"active","contextWindow":32768,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","lastUpdated":"2025-08-26","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"google/gemini-2.5-flash-image","displayName":"Nano Banana (Gemini 2.5 Flash Image)","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2025-01"}},"google/gemini-2.5-flash-lite":{"metadata":{"displayName":"Gemini 2.5 Flash Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-06-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-2.5-flash-lite","displayName":"Gemini 2.5 Flash Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-2.5-pro":{"metadata":{"displayName":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-06-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-2.5-pro","displayName":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-3-flash":{"metadata":{"displayName":"Gemini 3 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65000,"knowledgeCutoff":"2025-03","lastUpdated":"2025-12-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3-flash","displayName":"Gemini 3 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-03"}},"google/gemini-3-pro-image":{"metadata":{"displayName":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","lifecycle":"active","contextWindow":65536,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"google/gemini-3-pro-image","displayName":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-flash-image":{"metadata":{"displayName":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["minimal","high"]},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"google/gemini-3.1-flash-image","displayName":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","high"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-flash-image-preview":{"metadata":{"displayName":"Gemini 3.1 Flash Image Preview (Nano Banana 2)","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","lastUpdated":"2026-02-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["minimal","high"]},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"google/gemini-3.1-flash-image-preview","displayName":"Gemini 3.1 Flash Image Preview (Nano Banana 2)","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","high"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-flash-lite":{"metadata":{"displayName":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65000,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.1-flash-lite","displayName":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-flash-lite-image":{"metadata":{"displayName":"Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":65536,"maxOutputTokens":4096,"knowledgeCutoff":"2025-01","structuredOutput":false,"lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"google/gemini-3.1-flash-lite-image","displayName":"Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-pro-preview":{"metadata":{"displayName":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-02-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.1-pro-preview","displayName":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-01"}},"google/gemini-3.5-flash":{"metadata":{"displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.5-flash","displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-01"}},"google/gemini-3.5-flash-lite":{"metadata":{"displayName":"Gemini 3.5 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65000,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-07-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.5-flash-lite","displayName":"Gemini 3.5 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-03"}},"google/gemini-3.5-transcribe":{"metadata":{"displayName":"Gemini 3.5 Transcribe","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2026-08-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"google/gemini-3.5-transcribe","displayName":"Gemini 3.5 Transcribe","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"google/gemini-3.5-transcribe-live":{"metadata":{"displayName":"Gemini 3.5 Transcribe Live","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2026-08-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"google/gemini-3.5-transcribe-live","displayName":"Gemini 3.5 Transcribe Live","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"google/gemini-3.6-flash":{"metadata":{"displayName":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-07-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.6-flash","displayName":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-03"}},"google/gemini-3.7-flash":{"metadata":{"displayName":"Gemini 3.7 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-08-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.7-flash","displayName":"Gemini 3.7 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-03"}},"google/gemini-3.8-flash":{"metadata":{"displayName":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.8-flash","displayName":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"google/gemini-embedding-001":{"metadata":{"displayName":"Gemini Embedding 001","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"knowledgeCutoff":"2025-05","lastUpdated":"2025-05-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"google/gemini-embedding-001","displayName":"Gemini Embedding 001","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2025-05"}},"google/gemini-embedding-2":{"metadata":{"displayName":"Gemini Embedding 2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","knowledgeCutoff":"2025-11","lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"google/gemini-embedding-2","displayName":"Gemini Embedding 2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"knowledgeCutoff":"2025-11"}},"google/gemini-omni-flash-preview":{"metadata":{"displayName":"Gemini Omni Flash Preview","description":"Omni-modal model for text, vision, audio, and multimodal agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":57920,"lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-omni-flash-preview","displayName":"Gemini Omni Flash Preview","description":"Omni-modal model for text, vision, audio, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"google/gemma-4-26b-a4b-it":{"metadata":{"displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemma-4-26b-a4b-it","displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"google/gemma-4-31b-it":{"metadata":{"displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"google/gemma-4-31b-it","displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"google/text-embedding-005":{"metadata":{"displayName":"Text Embedding 005","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2024-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"google/text-embedding-005","displayName":"Text Embedding 005","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"google/text-multilingual-embedding-002":{"metadata":{"displayName":"Text Multilingual Embedding 002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2024-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"google/text-multilingual-embedding-002","displayName":"Text Multilingual Embedding 002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"google/veo-3.0-fast-generate-001":{"metadata":{"displayName":"Veo 3.0 Fast Generate","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-06-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"google/veo-3.0-fast-generate-001","displayName":"Veo 3.0 Fast Generate","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"google/veo-3.0-generate-001":{"metadata":{"displayName":"Veo 3.0","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-06-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"google/veo-3.0-generate-001","displayName":"Veo 3.0","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"google/veo-3.1-fast-generate-001":{"metadata":{"displayName":"Veo 3.1 Fast Generate","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-06-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"google/veo-3.1-fast-generate-001","displayName":"Veo 3.1 Fast Generate","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"google/veo-3.1-generate-001":{"metadata":{"displayName":"Veo 3.1","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-06-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"google/veo-3.1-generate-001","displayName":"Veo 3.1","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"google/veo-3.1-lite-generate-001":{"metadata":{"displayName":"Veo 3.1 Lite Generate","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-04-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"google/veo-3.1-lite-generate-001","displayName":"Veo 3.1 Lite Generate","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"inception/mercury-2":{"metadata":{"displayName":"Mercury 2","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"lastUpdated":"2026-03-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inception/mercury-2","displayName":"Mercury 2","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":128000,"defaultContextWindow":128000}},"inception/mercury-2.5":{"metadata":{"displayName":"Mercury 2.5","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":260000,"maxOutputTokens":65536,"lastUpdated":"2026-09-08","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inception/mercury-2.5","displayName":"Mercury 2.5","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high"],"contextWindow":260000,"defaultContextWindow":260000}},"inception/mercury-coder-small":{"metadata":{"displayName":"Mercury Coder Small Beta","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":32000,"maxOutputTokens":16384,"lastUpdated":"2025-02-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inception/mercury-coder-small","displayName":"Mercury Coder Small Beta","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"inclusionai/ling-3.0-flash":{"metadata":{"displayName":"Ling 3.0 Flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"lastUpdated":"2026-08-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash","displayName":"Ling 3.0 Flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"inclusionai/ling-3.0-flash-fin":{"metadata":{"displayName":"Ling 3.0 Flash Fin","description":"Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"lastUpdated":"2026-08-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash-fin","displayName":"Ling 3.0 Flash Fin","description":"Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"inclusionai/ling-3.0-flash-fin-free":{"metadata":{"displayName":"Ling 3.0 Flash Fin (Free)","description":"Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"lastUpdated":"2026-08-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash-fin-free","displayName":"Ling 3.0 Flash Fin (Free)","description":"Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"inclusionai/ling-3.0-flash-sante":{"metadata":{"displayName":"Ling 3.0 Flash Sante","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"lastUpdated":"2026-09-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash-sante","displayName":"Ling 3.0 Flash Sante","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"inclusionai/ling-3.0-flash-sante-free":{"metadata":{"displayName":"Ling 3.0 Flash Sante (Free)","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"lastUpdated":"2026-09-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash-sante-free","displayName":"Ling 3.0 Flash Sante (Free)","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"inclusionai/ling-3.0-flash-vl":{"metadata":{"displayName":"Ling 3.0 Flash VL","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"lastUpdated":"2026-09-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash-vl","displayName":"Ling 3.0 Flash VL","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"inclusionai/ling-3.0-flash-vl-free":{"metadata":{"displayName":"Ling 3.0 Flash VL (Free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"lastUpdated":"2026-09-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash-vl-free","displayName":"Ling 3.0 Flash VL (Free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"interfaze/interfaze-beta":{"metadata":{"displayName":"Interfaze Beta","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":32000,"lastUpdated":"2026-04-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"interfaze/interfaze-beta","displayName":"Interfaze Beta","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000}},"klingai/kling-v2.5-turbo-i2v":{"metadata":{"displayName":"Kling v2.5 Turbo Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-09-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"klingai/kling-v2.5-turbo-i2v","displayName":"Kling v2.5 Turbo Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"klingai/kling-v2.5-turbo-t2v":{"metadata":{"displayName":"Kling v2.5 Turbo Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2025-09-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"klingai/kling-v2.5-turbo-t2v","displayName":"Kling v2.5 Turbo Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"klingai/kling-v2.6-i2v":{"metadata":{"displayName":"Kling v2.6 Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-12-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"klingai/kling-v2.6-i2v","displayName":"Kling v2.6 Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"klingai/kling-v2.6-motion-control":{"metadata":{"displayName":"Kling v2.6 Motion Control","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2025-12-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"klingai/kling-v2.6-motion-control","displayName":"Kling v2.6 Motion Control","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"klingai/kling-v2.6-t2v":{"metadata":{"displayName":"Kling v2.6 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2025-12-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"klingai/kling-v2.6-t2v","displayName":"Kling v2.6 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"klingai/kling-v3.0-i2v":{"metadata":{"displayName":"Kling v3.0 Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-02-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"klingai/kling-v3.0-i2v","displayName":"Kling v3.0 Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"klingai/kling-v3.0-motion-control":{"metadata":{"displayName":"Kling v3.0 Motion Control","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-03-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"klingai/kling-v3.0-motion-control","displayName":"Kling v3.0 Motion Control","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"klingai/kling-v3.0-t2v":{"metadata":{"displayName":"Kling v3.0 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-02-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"klingai/kling-v3.0-t2v","displayName":"Kling v3.0 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"kwaipilot/kat-coder-air-v2.5":{"metadata":{"displayName":"Kat Coder Air V2.5","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":80000,"lastUpdated":"2026-07-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"kwaipilot/kat-coder-air-v2.5","displayName":"Kat Coder Air V2.5","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"kwaipilot/kat-coder-pro-v1":{"metadata":{"displayName":"KAT-Coder-Pro V1","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"knowledgeCutoff":"2024-10","lastUpdated":"2025-10-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"kwaipilot/kat-coder-pro-v1","displayName":"KAT-Coder-Pro V1","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-10"}},"kwaipilot/kat-coder-pro-v2":{"metadata":{"displayName":"Kat Coder Pro V2","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"lastUpdated":"2026-03-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"kwaipilot/kat-coder-pro-v2","displayName":"Kat Coder Pro V2","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"kwaipilot/kat-coder-pro-v2.5":{"metadata":{"displayName":"Kat Coder Pro V2.5","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":80000,"lastUpdated":"2026-07-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"kwaipilot/kat-coder-pro-v2.5","displayName":"Kat Coder Pro V2.5","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"meta/llama-3.1-70b":{"metadata":{"displayName":"Llama 3.1 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"knowledgeCutoff":"2023-12","lastUpdated":"2024-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta/llama-3.1-70b","displayName":"Llama 3.1 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-12"}},"meta/llama-3.1-8b":{"metadata":{"displayName":"Llama 3.1 8B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"knowledgeCutoff":"2023-12","lastUpdated":"2024-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta/llama-3.1-8b","displayName":"Llama 3.1 8B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-12"}},"meta/llama-3.3-70b":{"metadata":{"displayName":"Llama-3.3-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-12","lastUpdated":"2024-12-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta/llama-3.3-70b","displayName":"Llama-3.3-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-12"}},"meta/llama-4-maverick":{"metadata":{"displayName":"Llama-4-Maverick-17B-128E-Instruct-FP8","description":"Open multimodal Llama model for strong reasoning and fast responses","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2024-08","lastUpdated":"2025-04-05","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta/llama-4-maverick","displayName":"Llama-4-Maverick-17B-128E-Instruct-FP8","description":"Open multimodal Llama model for strong reasoning and fast responses","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-08"}},"meta/llama-4-scout":{"metadata":{"displayName":"Llama-4-Scout-17B-16E-Instruct-FP8","description":"Open multimodal Llama model for long-context analysis and efficient agents","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2024-08","lastUpdated":"2025-04-05","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta/llama-4-scout","displayName":"Llama-4-Scout-17B-16E-Instruct-FP8","description":"Open multimodal Llama model for long-context analysis and efficient agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-08"}},"meta/muse-glimmer-30b":{"metadata":{"displayName":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2026-01-04","structuredOutput":true,"lastUpdated":"2026-08-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta/muse-glimmer-30b","displayName":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2026-01-04"}},"meta/muse-image-1.0":{"metadata":{"displayName":"Muse Image 1.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["image"]}},"entry":{"id":"meta/muse-image-1.0","displayName":"Muse Image 1.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"meta/muse-spark-1.1":{"metadata":{"displayName":"Muse Spark 1.1","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"meta/muse-spark-1.1","displayName":"Muse Spark 1.1","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"meta/muse-spark-1.2":{"metadata":{"displayName":"Muse Spark 1.2","description":"Open Llama multimodal model for image understanding and text reasoning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"structuredOutput":true,"lastUpdated":"2026-08-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"meta/muse-spark-1.2","displayName":"Muse Spark 1.2","description":"Open Llama multimodal model for image understanding and text reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}},"meta/muse-spark-1.2-contributor":{"metadata":{"displayName":"Muse Spark 1.2 Contributor","description":"Open Llama multimodal model for image understanding and text reasoning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"lastUpdated":"2026-08-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"meta/muse-spark-1.2-contributor","displayName":"Muse Spark 1.2 Contributor","description":"Open Llama multimodal model for image understanding and text reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"meta/muse-spark-1.3":{"metadata":{"displayName":"Muse Spark 1.3","description":"Open Llama multimodal model for image understanding and text reasoning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"meta/muse-spark-1.3","displayName":"Muse Spark 1.3","description":"Open Llama multimodal model for image understanding and text reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"meta/muse-spark-1.3-contributor":{"metadata":{"displayName":"Muse Spark 1.3 Contributor","description":"Open Llama multimodal model for image understanding and text reasoning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"meta/muse-spark-1.3-contributor","displayName":"Muse Spark 1.3 Contributor","description":"Open Llama multimodal model for image understanding and text reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"minimax/minimax-h3":{"metadata":{"displayName":"MiniMax H3","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-07-30","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["video"]}},"entry":{"id":"minimax/minimax-h3","displayName":"MiniMax H3","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"minimax/minimax-h3-max":{"metadata":{"displayName":"MiniMax H3 Max","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","lastUpdated":"2026-08-27","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["video"]}},"entry":{"id":"minimax/minimax-h3-max","displayName":"MiniMax H3 Max","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"minimax/minimax-m2":{"metadata":{"displayName":"MiniMax M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","lifecycle":"active","contextWindow":205000,"maxOutputTokens":205000,"knowledgeCutoff":"2024-10","lastUpdated":"2025-10-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2","displayName":"MiniMax M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":205000,"defaultContextWindow":205000,"knowledgeCutoff":"2024-10"}},"minimax/minimax-m2.1":{"metadata":{"displayName":"MiniMax M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2025-12-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2.1","displayName":"MiniMax M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"minimax/minimax-m2.1-lightning":{"metadata":{"displayName":"MiniMax M2.1 Lightning","description":"High-speed MiniMax model for low-latency coding and agent workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2024-10","lastUpdated":"2025-10-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2.1-lightning","displayName":"MiniMax M2.1 Lightning","description":"High-speed MiniMax model for low-latency coding and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2024-10"}},"minimax/minimax-m2.5":{"metadata":{"displayName":"MiniMax M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131000,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2.5","displayName":"MiniMax M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"minimax/minimax-m2.5-highspeed":{"metadata":{"displayName":"MiniMax M2.5 High Speed","description":"High-speed MiniMax model for low-latency coding and agent workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131000,"lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2.5-highspeed","displayName":"MiniMax M2.5 High Speed","description":"High-speed MiniMax model for low-latency coding and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"minimax/minimax-m2.7":{"metadata":{"displayName":"Minimax M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131000,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2.7","displayName":"Minimax M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"minimax/minimax-m2.7-highspeed":{"metadata":{"displayName":"MiniMax M2.7 High Speed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131100,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2.7-highspeed","displayName":"MiniMax M2.7 High Speed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"minimax/minimax-m3":{"metadata":{"displayName":"MiniMax M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","lifecycle":"active","contextWindow":512000,"maxOutputTokens":512000,"lastUpdated":"2026-06-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"minimax/minimax-m3","displayName":"MiniMax M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":512000,"defaultContextWindow":512000}},"mistral/codestral":{"metadata":{"displayName":"Codestral (latest)","description":"Mistral code model for completions, refactors, and developer IDE workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":4096,"knowledgeCutoff":"2024-10","lastUpdated":"2025-01-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistral/codestral","displayName":"Codestral (latest)","description":"Mistral code model for completions, refactors, and developer IDE workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-10"}},"mistral/codestral-embed":{"metadata":{"displayName":"Codestral Embed","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2025-05-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistral/codestral-embed","displayName":"Codestral Embed","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"mistral/devstral-2":{"metadata":{"displayName":"Devstral 2","description":"Mistral coding agent model for repository tasks and software engineering workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2024-10","lastUpdated":"2025-12-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistral/devstral-2","displayName":"Devstral 2","description":"Mistral coding agent model for repository tasks and software engineering workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-10"}},"mistral/devstral-small-2":{"metadata":{"displayName":"Devstral Small 2","description":"Mistral coding agent model for repository tasks and software engineering workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2024-10","lastUpdated":"2025-05-07","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral/devstral-small-2","displayName":"Devstral Small 2","description":"Mistral coding agent model for repository tasks and software engineering workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-10"}},"mistral/ministral-14b":{"metadata":{"displayName":"Ministral 14B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2024-10","lastUpdated":"2025-12-01","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"mistral/ministral-14b","displayName":"Ministral 14B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-10"}},"mistral/ministral-3b":{"metadata":{"displayName":"Ministral 3B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-10","lastUpdated":"2024-10-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistral/ministral-3b","displayName":"Ministral 3B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-10"}},"mistral/ministral-8b":{"metadata":{"displayName":"Ministral 8B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-10","lastUpdated":"2024-10-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistral/ministral-8b","displayName":"Ministral 8B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-10"}},"mistral/mistral-embed":{"metadata":{"displayName":"Mistral Embed","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2023-12-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistral/mistral-embed","displayName":"Mistral Embed","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"mistral/mistral-large-3":{"metadata":{"displayName":"Mistral Large 3","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2024-10","lastUpdated":"2025-12-02","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral/mistral-large-3","displayName":"Mistral Large 3","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-10"}},"mistral/mistral-medium":{"metadata":{"displayName":"Mistral Medium 3.1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2024-10","lastUpdated":"2025-05-07","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral/mistral-medium","displayName":"Mistral Medium 3.1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-10"}},"mistral/mistral-medium-3.5":{"metadata":{"displayName":"Mistral Medium Latest","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"lastUpdated":"2026-05-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral/mistral-medium-3.5","displayName":"Mistral Medium Latest","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","high"],"contextWindow":256000,"defaultContextWindow":256000}},"mistral/mistral-nemo":{"metadata":{"displayName":"Mistral Nemo","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-04","lastUpdated":"2024-07-01","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral/mistral-nemo","displayName":"Mistral Nemo","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-04"}},"mistral/mistral-small":{"metadata":{"displayName":"Mistral Small (latest)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","lifecycle":"active","contextWindow":32000,"maxOutputTokens":4000,"knowledgeCutoff":"2025-06","lastUpdated":"2026-03-16","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral/mistral-small","displayName":"Mistral Small (latest)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000,"knowledgeCutoff":"2025-06"}},"mistral/pixtral-12b":{"metadata":{"displayName":"Pixtral 12B","description":"Mistral vision-language model for image understanding and multimodal chat","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09","lastUpdated":"2024-09-01","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral/pixtral-12b","displayName":"Pixtral 12B","description":"Mistral vision-language model for image understanding and multimodal chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-09"}},"moonshotai/kimi-k2":{"metadata":{"displayName":"Kimi K2 Instruct","description":"Kimi model for long-context chat, coding, and agentic reasoning","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"lastUpdated":"2025-09-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2","displayName":"Kimi K2 Instruct","description":"Kimi model for long-context chat, coding, and agentic reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"moonshotai/kimi-k2-thinking":{"metadata":{"displayName":"Kimi K2 Thinking","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","lifecycle":"active","contextWindow":216144,"maxOutputTokens":216144,"knowledgeCutoff":"2024-08","lastUpdated":"2025-11-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2-thinking","displayName":"Kimi K2 Thinking","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":216144,"defaultContextWindow":216144,"knowledgeCutoff":"2024-08"}},"moonshotai/kimi-k2.5":{"metadata":{"displayName":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","lifecycle":"active","contextWindow":262114,"maxOutputTokens":262114,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.5","displayName":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262114,"defaultContextWindow":262114,"knowledgeCutoff":"2025-01"}},"moonshotai/kimi-k2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.6","displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000,"knowledgeCutoff":"2025-01"}},"moonshotai/kimi-k2.7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.7-code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-01"}},"moonshotai/kimi-k2.7-code-highspeed":{"metadata":{"displayName":"Kimi K2.7 Code High Speed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.7-code-highspeed","displayName":"Kimi K2.7 Code High Speed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/kimi-k3":{"metadata":{"displayName":"Kimi K3","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k3","displayName":"Kimi K3","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"moonshotai/kimi-k3-fast":{"metadata":{"displayName":"Kimi K3 Fast","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k3-fast","displayName":"Kimi K3 Fast","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"morph/morph-v3-fast":{"metadata":{"displayName":"Morph v3 Fast","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":16000,"maxOutputTokens":16000,"lastUpdated":"2024-08-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"morph/morph-v3-fast","displayName":"Morph v3 Fast","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16000,"defaultContextWindow":16000}},"morph/morph-v3-large":{"metadata":{"displayName":"Morph v3 Large","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":32000,"maxOutputTokens":32000,"lastUpdated":"2024-08-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"morph/morph-v3-large","displayName":"Morph v3 Large","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"nvidia/nemotron-3-nano-30b-a3b":{"metadata":{"displayName":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"lastUpdated":"2025-12-15","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-nano-30b-a3b","displayName":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"nvidia/nemotron-3-super-120b-a12b":{"metadata":{"displayName":"NVIDIA Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"lastUpdated":"2026-03-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-super-120b-a12b","displayName":"NVIDIA Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"nvidia/nemotron-3-ultra-550b-a55b":{"metadata":{"displayName":"Nemotron 3 Ultra","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65000,"lastUpdated":"2026-06-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-ultra-550b-a55b","displayName":"Nemotron 3 Ultra","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"nvidia/nemotron-3.5-lightning":{"metadata":{"displayName":"Nemotron 3.5 Lightning 30B","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3.5-lightning","displayName":"Nemotron 3.5 Lightning 30B","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"nvidia/nemotron-nano-12b-v2-vl":{"metadata":{"displayName":"Nvidia Nemotron Nano 12B V2 VL","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"lastUpdated":"2025-10-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-nano-12b-v2-vl","displayName":"Nvidia Nemotron Nano 12B V2 VL","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"nvidia/nemotron-nano-9b-v2":{"metadata":{"displayName":"Nvidia Nemotron Nano 9B V2","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"lastUpdated":"2025-08-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-nano-9b-v2","displayName":"Nvidia Nemotron Nano 9B V2","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"openai/gpt-3.5-turbo":{"metadata":{"displayName":"GPT-3.5 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":16385,"inputLimit":12289,"maxOutputTokens":4096,"knowledgeCutoff":"2021-09","structuredOutput":false,"lastUpdated":"2023-11-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-3.5-turbo","displayName":"GPT-3.5 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16385,"inputLimit":12289,"defaultContextWindow":16385,"defaultInputLimit":12289,"knowledgeCutoff":"2021-09"}},"openai/gpt-4-turbo":{"metadata":{"displayName":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-12","structuredOutput":false,"lastUpdated":"2024-04-09","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openai/gpt-4-turbo","displayName":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-12"}},"openai/gpt-4.1":{"metadata":{"displayName":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","lifecycle":"active","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4.1","displayName":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"openai/gpt-4.1-fast":{"metadata":{"displayName":"GPT-4.1 (Fast)","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","lifecycle":"active","contextWindow":1047576,"inputLimit":1014808,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4.1-fast","displayName":"GPT-4.1 (Fast)","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"inputLimit":1014808,"defaultContextWindow":1047576,"defaultInputLimit":1014808,"knowledgeCutoff":"2024-04"}},"openai/gpt-4.1-mini":{"metadata":{"displayName":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","lifecycle":"active","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4.1-mini","displayName":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"openai/gpt-4.1-mini-fast":{"metadata":{"displayName":"GPT-4.1 mini (Fast)","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","lifecycle":"active","contextWindow":1047576,"inputLimit":1014808,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4.1-mini-fast","displayName":"GPT-4.1 mini (Fast)","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"inputLimit":1014808,"defaultContextWindow":1047576,"defaultInputLimit":1014808,"knowledgeCutoff":"2024-04"}},"openai/gpt-4.1-nano":{"metadata":{"displayName":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","lifecycle":"deprecated","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openai/gpt-4.1-nano","displayName":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"openai/gpt-4.1-nano-fast":{"metadata":{"displayName":"GPT-4.1 nano (Fast)","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","lifecycle":"active","contextWindow":1047576,"inputLimit":1014808,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4.1-nano-fast","displayName":"GPT-4.1 nano (Fast)","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"inputLimit":1014808,"defaultContextWindow":1047576,"defaultInputLimit":1014808,"knowledgeCutoff":"2024-04"}},"openai/gpt-4o":{"metadata":{"displayName":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-08-06","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4o","displayName":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"openai/gpt-4o-fast":{"metadata":{"displayName":"GPT-4o (Fast)","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","lifecycle":"active","contextWindow":128000,"inputLimit":111616,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-08-06","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4o-fast","displayName":"GPT-4o (Fast)","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"inputLimit":111616,"defaultContextWindow":128000,"defaultInputLimit":111616,"knowledgeCutoff":"2023-09"}},"openai/gpt-4o-mini":{"metadata":{"displayName":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-07-18","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4o-mini","displayName":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"openai/gpt-4o-mini-fast":{"metadata":{"displayName":"GPT-4o mini (Fast)","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","lifecycle":"active","contextWindow":128000,"inputLimit":111616,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-07-18","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4o-mini-fast","displayName":"GPT-4o mini (Fast)","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"inputLimit":111616,"defaultContextWindow":128000,"defaultInputLimit":111616,"knowledgeCutoff":"2023-09"}},"openai/gpt-4o-mini-transcribe":{"metadata":{"displayName":"GPT-4o mini Transcribe","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2024-03-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"openai/gpt-4o-mini-transcribe","displayName":"GPT-4o mini Transcribe","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-4o-transcribe":{"metadata":{"displayName":"GPT-4o Transcribe","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2024-03-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"openai/gpt-4o-transcribe","displayName":"GPT-4o Transcribe","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-5":{"metadata":{"displayName":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openai/gpt-5","displayName":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5-codex":{"metadata":{"displayName":"GPT-5-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-09-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5-codex","displayName":"GPT-5-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5-fast":{"metadata":{"displayName":"GPT-5 (Fast)","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5-fast","displayName":"GPT-5 (Fast)","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5-mini":{"metadata":{"displayName":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-05-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openai/gpt-5-mini","displayName":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-05-30"}},"openai/gpt-5-mini-fast":{"metadata":{"displayName":"GPT-5 mini (Fast)","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-05-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5-mini-fast","displayName":"GPT-5 mini (Fast)","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-05-30"}},"openai/gpt-5-nano":{"metadata":{"displayName":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-05-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openai/gpt-5-nano","displayName":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-05-30"}},"openai/gpt-5-pro":{"metadata":{"displayName":"GPT-5 pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","lifecycle":"active","contextWindow":400000,"inputLimit":128000,"maxOutputTokens":272000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-10-06","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5-pro","displayName":"GPT-5 pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high"],"contextWindow":400000,"inputLimit":128000,"defaultContextWindow":400000,"defaultInputLimit":128000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5.1-codex":{"metadata":{"displayName":"GPT-5.1-Codex","description":"Codex GPT for repository edits, code review, and practical software agents","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.1-codex","displayName":"GPT-5.1-Codex","description":"Codex GPT for repository edits, code review, and practical software agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5.1-codex-max":{"metadata":{"displayName":"GPT 5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.1-codex-max","displayName":"GPT 5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5.1-codex-mini":{"metadata":{"displayName":"GPT-5.1 Codex mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.1-codex-mini","displayName":"GPT-5.1 Codex mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5.1-thinking":{"metadata":{"displayName":"GPT 5.1 Thinking","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-10","lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text","image"]}},"entry":{"id":"openai/gpt-5.1-thinking","displayName":"GPT 5.1 Thinking","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-10"}},"openai/gpt-5.1-thinking-fast":{"metadata":{"displayName":"GPT 5.1 Thinking (Fast)","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"lastUpdated":"2025-11-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.1-thinking-fast","displayName":"GPT 5.1 Thinking (Fast)","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000}},"openai/gpt-5.2":{"metadata":{"displayName":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-10","structuredOutput":true,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.2","displayName":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-10"}},"openai/gpt-5.2-codex":{"metadata":{"displayName":"GPT-5.2-Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.2-codex","displayName":"GPT-5.2-Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.2-fast":{"metadata":{"displayName":"GPT 5.2 (Fast)","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.2-fast","displayName":"GPT 5.2 (Fast)","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.2-pro":{"metadata":{"displayName":"GPT 5.2 ","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":false,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.2-pro","displayName":"GPT 5.2 ","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.3-codex":{"metadata":{"displayName":"GPT 5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-02-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.3-codex","displayName":"GPT 5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.3-codex-fast":{"metadata":{"displayName":"GPT 5.3 Codex (Fast)","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-02-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.3-codex-fast","displayName":"GPT 5.3 Codex (Fast)","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4":{"metadata":{"displayName":"GPT 5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.4","displayName":"GPT 5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4-fast":{"metadata":{"displayName":"GPT 5.4 (Fast)","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.4-fast","displayName":"GPT 5.4 (Fast)","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4-mini":{"metadata":{"displayName":"GPT 5.4 Mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.4-mini","displayName":"GPT 5.4 Mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4-mini-fast":{"metadata":{"displayName":"GPT 5.4 Mini (Fast)","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.4-mini-fast","displayName":"GPT 5.4 Mini (Fast)","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4-nano":{"metadata":{"displayName":"GPT 5.4 Nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.4-nano","displayName":"GPT 5.4 Nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4-pro":{"metadata":{"displayName":"GPT 5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":false,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.4-pro","displayName":"GPT 5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.5":{"metadata":{"displayName":"GPT 5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","lifecycle":"active","contextWindow":1000000,"inputLimit":872000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.5","displayName":"GPT 5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1000000,"inputLimit":872000,"defaultContextWindow":1000000,"defaultInputLimit":872000,"knowledgeCutoff":"2025-12-01"}},"openai/gpt-5.5-fast":{"metadata":{"displayName":"GPT 5.5 (Fast)","description":"Default frontier GPT for coding, computer use, research, and knowledge work","lifecycle":"active","contextWindow":1000000,"inputLimit":872000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.5-fast","displayName":"GPT 5.5 (Fast)","description":"Default frontier GPT for coding, computer use, research, and knowledge work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1000000,"inputLimit":872000,"defaultContextWindow":1000000,"defaultInputLimit":872000,"knowledgeCutoff":"2025-12-01"}},"openai/gpt-5.5-pro":{"metadata":{"displayName":"GPT 5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","lifecycle":"active","contextWindow":1000000,"inputLimit":872000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.5-pro","displayName":"GPT 5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1000000,"inputLimit":872000,"defaultContextWindow":1000000,"defaultInputLimit":872000,"knowledgeCutoff":"2025-12-01"}},"openai/gpt-5.6-luna":{"metadata":{"displayName":"GPT 5.6 Luna","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-luna","displayName":"GPT 5.6 Luna","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-luna-fast":{"metadata":{"displayName":"GPT 5.6 Luna (Fast)","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-luna-fast","displayName":"GPT 5.6 Luna (Fast)","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-sol":{"metadata":{"displayName":"GPT 5.6 Sol","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-sol","displayName":"GPT 5.6 Sol","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-sol-fast":{"metadata":{"displayName":"GPT 5.6 Sol (Fast)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-sol-fast","displayName":"GPT 5.6 Sol (Fast)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-terra":{"metadata":{"displayName":"GPT 5.6 Terra","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-terra","displayName":"GPT 5.6 Terra","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-terra-fast":{"metadata":{"displayName":"GPT 5.6 Terra (Fast)","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-terra-fast","displayName":"GPT 5.6 Terra (Fast)","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-6-astra":{"metadata":{"displayName":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-04-30","structuredOutput":true,"lastUpdated":"2026-09-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-6-astra","displayName":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-04-30"}},"openai/gpt-6-astra-fast":{"metadata":{"displayName":"GPT-6 Astra (Fast)","description":"Fast variant of GPT-6 Astra for low-latency assistance and high-volume workloads.","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-09-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-6-astra-fast","displayName":"GPT-6 Astra (Fast)","description":"Fast variant of GPT-6 Astra for low-latency assistance and high-volume workloads.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000}},"openai/gpt-image-1":{"metadata":{"displayName":"GPT Image 1","description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","lifecycle":"active","lastUpdated":"2025-04-24","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"openai/gpt-image-1","displayName":"GPT Image 1","description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-image-1-mini":{"metadata":{"displayName":"GPT Image 1 Mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-10-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"openai/gpt-image-1-mini","displayName":"GPT Image 1 Mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-image-1.5":{"metadata":{"displayName":"GPT Image 1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"openai/gpt-image-1.5","displayName":"GPT Image 1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-image-2":{"metadata":{"displayName":"GPT Image 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-04-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"openai/gpt-image-2","displayName":"GPT Image 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-image-2.5-flare":{"metadata":{"displayName":"GPT Image 2.5 Flare","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-09-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"openai/gpt-image-2.5-flare","displayName":"GPT Image 2.5 Flare","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-image-2.5-sunburst":{"metadata":{"displayName":"GPT Image 2.5 Sunburst","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-09-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"openai/gpt-image-2.5-sunburst","displayName":"GPT Image 2.5 Sunburst","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-oss-120b":{"metadata":{"displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2024-10","structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-120b","displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-10"}},"openai/gpt-oss-20b":{"metadata":{"displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"inputLimit":122880,"maxOutputTokens":8192,"knowledgeCutoff":"2024-10","structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-20b","displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"inputLimit":122880,"defaultContextWindow":131072,"defaultInputLimit":122880,"knowledgeCutoff":"2024-10"}},"openai/gpt-oss-safeguard-120b":{"metadata":{"displayName":"GPT OSS Safeguard 120B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"active","contextWindow":128000,"inputLimit":112000,"maxOutputTokens":16000,"structuredOutput":true,"lastUpdated":"2025-10-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-safeguard-120b","displayName":"GPT OSS Safeguard 120B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":128000,"inputLimit":112000,"defaultContextWindow":128000,"defaultInputLimit":112000}},"openai/gpt-oss-safeguard-20b":{"metadata":{"displayName":"gpt-oss-safeguard-20b","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"active","contextWindow":128000,"inputLimit":112000,"maxOutputTokens":16000,"structuredOutput":true,"lastUpdated":"2025-10-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-safeguard-20b","displayName":"gpt-oss-safeguard-20b","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":128000,"inputLimit":112000,"defaultContextWindow":128000,"defaultInputLimit":112000}},"openai/gpt-realtime-1.5":{"metadata":{"displayName":"GPT-Realtime-1.5","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-02-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","audio"],"output":["text","audio"]}},"entry":{"id":"openai/gpt-realtime-1.5","displayName":"GPT-Realtime-1.5","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-realtime-2":{"metadata":{"displayName":"gpt-realtime-2","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-05-07","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","audio"],"output":["text","audio"]}},"entry":{"id":"openai/gpt-realtime-2","displayName":"gpt-realtime-2","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-realtime-2.1":{"metadata":{"displayName":"gpt-realtime-2.1","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":128000,"inputLimit":96000,"maxOutputTokens":32000,"knowledgeCutoff":"2024-09-30","structuredOutput":false,"lastUpdated":"2026-07-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","audio"],"output":["text","audio"]}},"entry":{"id":"openai/gpt-realtime-2.1","displayName":"gpt-realtime-2.1","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":128000,"inputLimit":96000,"defaultContextWindow":128000,"defaultInputLimit":96000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-realtime-mini":{"metadata":{"displayName":"GPT-Realtime mini","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2025-10-10","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","audio"],"output":["text","audio"]}},"entry":{"id":"openai/gpt-realtime-mini","displayName":"GPT-Realtime mini","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-realtime-whisper":{"metadata":{"displayName":"gpt-realtime-whisper","description":"Streaming speech-to-text model for low-latency transcript deltas from live audio","lifecycle":"active","lastUpdated":"2026-05-07","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"openai/gpt-realtime-whisper","displayName":"gpt-realtime-whisper","description":"Streaming speech-to-text model for low-latency transcript deltas from live audio","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/o1":{"metadata":{"displayName":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-12-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/o1","displayName":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2023-09"}},"openai/o3":{"metadata":{"displayName":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/o3","displayName":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"openai/o3-fast":{"metadata":{"displayName":"o3 (Fast)","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","lifecycle":"active","contextWindow":200000,"inputLimit":100000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/o3-fast","displayName":"o3 (Fast)","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"inputLimit":100000,"defaultContextWindow":200000,"defaultInputLimit":100000,"knowledgeCutoff":"2024-05"}},"openai/o3-mini":{"metadata":{"displayName":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-01-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/o3-mini","displayName":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"openai/o3-pro":{"metadata":{"displayName":"o3 Pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","lifecycle":"active","contextWindow":200000,"inputLimit":100000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-10","structuredOutput":true,"lastUpdated":"2025-06-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/o3-pro","displayName":"o3 Pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"inputLimit":100000,"defaultContextWindow":200000,"defaultInputLimit":100000,"knowledgeCutoff":"2024-10"}},"openai/o4-mini":{"metadata":{"displayName":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openai/o4-mini","displayName":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"openai/o4-mini-fast":{"metadata":{"displayName":"o4-mini (Fast)","description":"Fast o-series model for compact reasoning, coding, and tool use","lifecycle":"active","contextWindow":200000,"inputLimit":100000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/o4-mini-fast","displayName":"o4-mini (Fast)","description":"Fast o-series model for compact reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"inputLimit":100000,"defaultContextWindow":200000,"defaultInputLimit":100000,"knowledgeCutoff":"2024-05"}},"openai/text-embedding-3-large":{"metadata":{"displayName":"text-embedding-3-large","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8192,"inputLimit":6656,"maxOutputTokens":1536,"lastUpdated":"2024-01-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/text-embedding-3-large","displayName":"text-embedding-3-large","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"inputLimit":6656,"defaultContextWindow":8192,"defaultInputLimit":6656}},"openai/text-embedding-3-small":{"metadata":{"displayName":"text-embedding-3-small","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8192,"inputLimit":6656,"maxOutputTokens":1536,"lastUpdated":"2024-01-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/text-embedding-3-small","displayName":"text-embedding-3-small","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"inputLimit":6656,"defaultContextWindow":8192,"defaultInputLimit":6656}},"openai/text-embedding-ada-002":{"metadata":{"displayName":"text-embedding-ada-002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8192,"inputLimit":6656,"maxOutputTokens":1536,"lastUpdated":"2022-12-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/text-embedding-ada-002","displayName":"text-embedding-ada-002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"inputLimit":6656,"defaultContextWindow":8192,"defaultInputLimit":6656}},"openai/tts-1":{"metadata":{"displayName":"TTS-1","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2023-11-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"openai/tts-1","displayName":"TTS-1","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/tts-1-hd":{"metadata":{"displayName":"TTS-1 HD","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2023-11-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"openai/tts-1-hd","displayName":"TTS-1 HD","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/whisper-1":{"metadata":{"displayName":"Whisper","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2022-09-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"openai/whisper-1","displayName":"Whisper","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"perplexity/pplx-embed-v1-0.6b":{"metadata":{"displayName":"Embed v1 0.6b","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":32000,"lastUpdated":"2026-02-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"perplexity/pplx-embed-v1-0.6b","displayName":"Embed v1 0.6b","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"perplexity/pplx-embed-v1-4b":{"metadata":{"displayName":"Embed v1 4b","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":32000,"lastUpdated":"2026-02-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"perplexity/pplx-embed-v1-4b","displayName":"Embed v1 4b","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"perplexity/sonar":{"metadata":{"displayName":"Sonar","description":"Sonar search model for current answers, retrieval, and citation-backed chat","lifecycle":"active","contextWindow":127000,"maxOutputTokens":8000,"knowledgeCutoff":"2025-02","lastUpdated":"2025-02-19","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"perplexity/sonar","displayName":"Sonar","description":"Sonar search model for current answers, retrieval, and citation-backed chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":127000,"defaultContextWindow":127000,"knowledgeCutoff":"2025-02"}},"perplexity/sonar-pro":{"metadata":{"displayName":"Sonar Pro","description":"Advanced Sonar search model for deeper research and cited synthesis","lifecycle":"active","contextWindow":200000,"maxOutputTokens":8000,"knowledgeCutoff":"2025-09","lastUpdated":"2025-02-19","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"perplexity/sonar-pro","displayName":"Sonar Pro","description":"Advanced Sonar search model for deeper research and cited synthesis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-09"}},"perplexity/sonar-reasoning-pro":{"metadata":{"displayName":"Sonar Reasoning Pro","description":"Web-grounded reasoning model for multi-step research and cited answers","lifecycle":"active","contextWindow":127000,"maxOutputTokens":8000,"knowledgeCutoff":"2025-09","lastUpdated":"2025-02-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"perplexity/sonar-reasoning-pro","displayName":"Sonar Reasoning Pro","description":"Web-grounded reasoning model for multi-step research and cited answers","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":127000,"defaultContextWindow":127000,"knowledgeCutoff":"2025-09"}},"poolside/laguna-s-2.1":{"metadata":{"displayName":"Laguna S 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":false,"lastUpdated":"2026-07-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"poolside/laguna-s-2.1","displayName":"Laguna S 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"poolside/laguna-s-2.1-free":{"metadata":{"displayName":"Laguna S 2.1 Free","description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-07-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"poolside/laguna-s-2.1-free","displayName":"Laguna S 2.1 Free","description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"prodia/flux-fast-schnell":{"metadata":{"displayName":"Flux Schnell","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":512,"lastUpdated":"2026-06-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"prodia/flux-fast-schnell","displayName":"Flux Schnell","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":512,"defaultContextWindow":512}},"quiverai/arrow-1.1":{"metadata":{"displayName":"Arrow 1.1","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"lastUpdated":"2026-04-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"quiverai/arrow-1.1","displayName":"Arrow 1.1","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"recraft/recraft-v2":{"metadata":{"displayName":"Recraft V2","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":512,"lastUpdated":"2024-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"recraft/recraft-v2","displayName":"Recraft V2","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":512,"defaultContextWindow":512}},"recraft/recraft-v3":{"metadata":{"displayName":"Recraft V3","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":512,"lastUpdated":"2024-10","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"recraft/recraft-v3","displayName":"Recraft V3","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":512,"defaultContextWindow":512}},"recraft/recraft-v4":{"metadata":{"displayName":"Recraft V4","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-02-17","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"recraft/recraft-v4","displayName":"Recraft V4","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"recraft/recraft-v4-pro":{"metadata":{"displayName":"Recraft V4 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-02-17","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"recraft/recraft-v4-pro","displayName":"Recraft V4 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"recraft/recraft-v4.1":{"metadata":{"displayName":"Recraft V4.1","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-05-14","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"recraft/recraft-v4.1","displayName":"Recraft V4.1","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"recraft/recraft-v4.1-pro":{"metadata":{"displayName":"Recraft V4.1 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-05-14","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"recraft/recraft-v4.1-pro","displayName":"Recraft V4.1 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"recraft/recraft-v4.1-utility":{"metadata":{"displayName":"Recraft V4.1 Utility","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-05-14","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"recraft/recraft-v4.1-utility","displayName":"Recraft V4.1 Utility","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"recraft/recraft-v4.1-utility-pro":{"metadata":{"displayName":"Recraft V4.1 Utility Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-05-14","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"recraft/recraft-v4.1-utility-pro","displayName":"Recraft V4.1 Utility Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"sakana/fugu-max":{"metadata":{"displayName":"Fugu Max","description":"Multi-agent model for routing expert agents across complex analytical tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":1000000,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"sakana/fugu-max","displayName":"Fugu Max","description":"Multi-agent model for routing expert agents across complex analytical tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"sakana/fugu-ultra":{"metadata":{"displayName":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":1000000,"structuredOutput":true,"lastUpdated":"2026-06-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"sakana/fugu-ultra","displayName":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"sakana/fugu-ultra-v2":{"metadata":{"displayName":"Fugu Ultra v2","description":"Quality-first multi-agent model for hard research, analysis, and competitions","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":1000000,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"sakana/fugu-ultra-v2","displayName":"Fugu Ultra v2","description":"Quality-first multi-agent model for hard research, analysis, and competitions","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"sakana/namazu":{"metadata":{"displayName":"Sakana Namazu","description":"Multi-agent model for routing expert agents across complex analytical tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"lastUpdated":"2026-08-03","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"sakana/namazu","displayName":"Sakana Namazu","description":"Multi-agent model for routing expert agents across complex analytical tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"spacexai/grok-4.1-fast-non-reasoning":{"metadata":{"displayName":"Grok 4.1 Fast Non-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":1000000,"lastUpdated":"2025-11-19","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"spacexai/grok-4.1-fast-non-reasoning","displayName":"Grok 4.1 Fast Non-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"spacexai/grok-4.1-fast-reasoning":{"metadata":{"displayName":"Grok 4.1 Fast Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":1000000,"structuredOutput":true,"lastUpdated":"2025-11-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"spacexai/grok-4.1-fast-reasoning","displayName":"Grok 4.1 Fast Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"spacexai/grok-4.20-multi-agent":{"metadata":{"displayName":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":2000000,"lastUpdated":"2026-03-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"spacexai/grok-4.20-multi-agent","displayName":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000}},"spacexai/grok-4.20-multi-agent-beta":{"metadata":{"displayName":"Grok 4.20 Multi Agent Beta","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":2000000,"lastUpdated":"2026-03-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"spacexai/grok-4.20-multi-agent-beta","displayName":"Grok 4.20 Multi Agent Beta","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000}},"spacexai/grok-4.20-non-reasoning":{"metadata":{"displayName":"Grok 4.20 Non-Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":2000000,"lastUpdated":"2026-03-10","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"spacexai/grok-4.20-non-reasoning","displayName":"Grok 4.20 Non-Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000}},"spacexai/grok-4.20-non-reasoning-beta":{"metadata":{"displayName":"Grok 4.20 Beta Non-Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":2000000,"lastUpdated":"2026-03-11","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"spacexai/grok-4.20-non-reasoning-beta","displayName":"Grok 4.20 Beta Non-Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000}},"spacexai/grok-4.20-reasoning":{"metadata":{"displayName":"Grok 4.20 Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":2000000,"lastUpdated":"2026-03-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"spacexai/grok-4.20-reasoning","displayName":"Grok 4.20 Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000}},"spacexai/grok-4.20-reasoning-beta":{"metadata":{"displayName":"Grok 4.20 Beta Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":2000000,"lastUpdated":"2026-03-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"spacexai/grok-4.20-reasoning-beta","displayName":"Grok 4.20 Beta Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000}},"spacexai/grok-4.3":{"metadata":{"displayName":"Grok 4.3","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":1000000,"structuredOutput":true,"lastUpdated":"2026-04-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"spacexai/grok-4.3","displayName":"Grok 4.3","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000}},"spacexai/grok-4.5":{"metadata":{"displayName":"Grok 4.5","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":500000,"maxOutputTokens":500000,"structuredOutput":true,"lastUpdated":"2026-07-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"spacexai/grok-4.5","displayName":"Grok 4.5","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":500000,"defaultContextWindow":500000}},"spacexai/grok-4.6":{"metadata":{"displayName":"Grok 4.6","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":500000,"maxOutputTokens":500000,"knowledgeCutoff":"2026-02-01","structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"spacexai/grok-4.6","displayName":"Grok 4.6","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":500000,"defaultContextWindow":500000,"knowledgeCutoff":"2026-02-01"}},"spacexai/grok-build-0.1":{"metadata":{"displayName":"Grok Build 0.1","description":"Grok coding model for agentic engineering, edits, and codebase workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"structuredOutput":true,"lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"spacexai/grok-build-0.1","displayName":"Grok Build 0.1","description":"Grok coding model for agentic engineering, edits, and codebase workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"spacexai/grok-imagine-image":{"metadata":{"displayName":"Grok Imagine Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-01-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"spacexai/grok-imagine-image","displayName":"Grok Imagine Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"spacexai/grok-imagine-image-2.0":{"metadata":{"displayName":"Grok Imagine Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-08-07","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"spacexai/grok-imagine-image-2.0","displayName":"Grok Imagine Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"spacexai/grok-imagine-video":{"metadata":{"displayName":"Grok Imagine","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-01-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"spacexai/grok-imagine-video","displayName":"Grok Imagine","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"spacexai/grok-imagine-video-1.5":{"metadata":{"displayName":"Grok Imagine Video 1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-05-30","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"spacexai/grok-imagine-video-1.5","displayName":"Grok Imagine Video 1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"spacexai/grok-stt":{"metadata":{"displayName":"Grok STT","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2026-03-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"spacexai/grok-stt","displayName":"Grok STT","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"spacexai/grok-tts":{"metadata":{"displayName":"Grok TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-03-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"spacexai/grok-tts","displayName":"Grok TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"spacexai/grok-voice-think-fast-1.0":{"metadata":{"displayName":"Grok Voice Think Fast 1.0","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-04-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","audio"],"output":["text","audio"]}},"entry":{"id":"spacexai/grok-voice-think-fast-1.0","displayName":"Grok Voice Think Fast 1.0","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"spacexai/grok-voice-think-fast-2.0":{"metadata":{"displayName":"Grok Voice Think Fast 2.0","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-07-29","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","audio"],"output":["text","audio"]}},"entry":{"id":"spacexai/grok-voice-think-fast-2.0","displayName":"Grok Voice Think Fast 2.0","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"stepfun/step-3.5-flash":{"metadata":{"displayName":"StepFun 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","lifecycle":"active","contextWindow":262114,"maxOutputTokens":262114,"knowledgeCutoff":"2025-01","lastUpdated":"2026-02-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"stepfun/step-3.5-flash","displayName":"StepFun 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":262114,"defaultContextWindow":262114,"knowledgeCutoff":"2025-01"}},"stepfun/step-3.7-flash":{"metadata":{"displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2026-03-01","lastUpdated":"2026-05-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"stepfun/step-3.7-flash","displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2026-03-01"}},"tencent/hy-mt2-lite":{"metadata":{"displayName":"Tencent Hy-MT2-Lite","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":8000,"maxOutputTokens":4000,"lastUpdated":"2026-06-12","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy-mt2-lite","displayName":"Tencent Hy-MT2-Lite","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8000,"defaultContextWindow":8000}},"tencent/hy-mt2-plus":{"metadata":{"displayName":"Tencent Hy-MT2-Plus","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":8000,"maxOutputTokens":4000,"lastUpdated":"2026-06-12","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy-mt2-plus","displayName":"Tencent Hy-MT2-Plus","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8000,"defaultContextWindow":8000}},"tencent/hy-mt2-pro":{"metadata":{"displayName":"Tencent Hy-MT2-Pro","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":8000,"maxOutputTokens":4000,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy-mt2-pro","displayName":"Tencent Hy-MT2-Pro","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8000,"defaultContextWindow":8000}},"tencent/hy3":{"metadata":{"displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"lastUpdated":"2026-07-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy3","displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","high"],"contextWindow":262144,"defaultContextWindow":262144}},"tencent/hy4-preview":{"metadata":{"displayName":"Tencent Hy4 Preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":64000,"lastUpdated":"2026-08-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy4-preview","displayName":"Tencent Hy4 Preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high"],"contextWindow":1024000,"defaultContextWindow":1024000}},"thinkingmachines/inkling":{"metadata":{"displayName":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"lastUpdated":"2026-07-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","minimal","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"thinkingmachines/inkling","displayName":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","minimal","low","medium","high","xhigh","max"],"contextWindow":256000,"defaultContextWindow":256000}},"thinkingmachines/inkling-small":{"metadata":{"displayName":"Inkling Small","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":1000000,"lastUpdated":"2026-07-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","minimal","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"thinkingmachines/inkling-small","displayName":"Inkling Small","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","minimal","low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"voyage/rerank-2.5":{"metadata":{"displayName":"Voyage Rerank 2.5","description":"Reranking model for improving retrieval quality in search and recommendation systems","lifecycle":"active","contextWindow":32000,"maxOutputTokens":32000,"lastUpdated":"2025-08-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/rerank-2.5","displayName":"Voyage Rerank 2.5","description":"Reranking model for improving retrieval quality in search and recommendation systems","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"voyage/rerank-2.5-lite":{"metadata":{"displayName":"Voyage Rerank 2.5 Lite","description":"Reranking model for improving retrieval quality in search and recommendation systems","lifecycle":"active","contextWindow":32000,"maxOutputTokens":32000,"lastUpdated":"2025-08-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/rerank-2.5-lite","displayName":"Voyage Rerank 2.5 Lite","description":"Reranking model for improving retrieval quality in search and recommendation systems","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"voyage/voyage-3-large":{"metadata":{"displayName":"voyage-3-large","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/voyage-3-large","displayName":"voyage-3-large","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"voyage/voyage-3.5":{"metadata":{"displayName":"voyage-3.5","description":"General-purpose chat model for instruction following, writing, and analysis","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2025-05-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/voyage-3.5","displayName":"voyage-3.5","description":"General-purpose chat model for instruction following, writing, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"voyage/voyage-3.5-lite":{"metadata":{"displayName":"voyage-3.5-lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2025-05-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/voyage-3.5-lite","displayName":"voyage-3.5-lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"voyage/voyage-4":{"metadata":{"displayName":"voyage-4","description":"General-purpose chat model for instruction following, writing, and analysis","lifecycle":"active","contextWindow":32000,"lastUpdated":"2026-03-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/voyage-4","displayName":"voyage-4","description":"General-purpose chat model for instruction following, writing, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"voyage/voyage-4-large":{"metadata":{"displayName":"voyage-4-large","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":32000,"lastUpdated":"2026-03-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/voyage-4-large","displayName":"voyage-4-large","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"voyage/voyage-4-lite":{"metadata":{"displayName":"voyage-4-lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":32000,"lastUpdated":"2026-03-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/voyage-4-lite","displayName":"voyage-4-lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"voyage/voyage-code-2":{"metadata":{"displayName":"voyage-code-2","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2024-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/voyage-code-2","displayName":"voyage-code-2","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"voyage/voyage-code-3":{"metadata":{"displayName":"voyage-code-3","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/voyage-code-3","displayName":"voyage-code-3","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"voyage/voyage-finance-2":{"metadata":{"displayName":"voyage-finance-2","description":"General-purpose chat model for instruction following, writing, and analysis","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2024-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/voyage-finance-2","displayName":"voyage-finance-2","description":"General-purpose chat model for instruction following, writing, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"voyage/voyage-law-2":{"metadata":{"displayName":"voyage-law-2","description":"General-purpose chat model for instruction following, writing, and analysis","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"lastUpdated":"2024-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"voyage/voyage-law-2","displayName":"voyage-law-2","description":"General-purpose chat model for instruction following, writing, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"xiaomi/mimo-v2.5":{"metadata":{"displayName":"MiMo M2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":131100,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"xiaomi/mimo-v2.5","displayName":"MiMo M2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2024-12"}},"xiaomi/mimo-v2.5-pro":{"metadata":{"displayName":"MiMo V2.5 Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":131000,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"xiaomi/mimo-v2.5-pro","displayName":"MiMo V2.5 Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2024-12"}},"zai/glm-4.5":{"metadata":{"displayName":"GLM 4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","lifecycle":"active","contextWindow":128000,"maxOutputTokens":96000,"knowledgeCutoff":"2025-07","lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-4.5","displayName":"GLM 4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-07"}},"zai/glm-4.5-air":{"metadata":{"displayName":"GLM 4.5 Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","lifecycle":"active","contextWindow":128000,"maxOutputTokens":96000,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-4.5-air","displayName":"GLM 4.5 Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-04"}},"zai/glm-4.5v":{"metadata":{"displayName":"GLM 4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":66000,"maxOutputTokens":16000,"knowledgeCutoff":"2025-08","lastUpdated":"2025-08-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"zai/glm-4.5v","displayName":"GLM 4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":66000,"defaultContextWindow":66000,"knowledgeCutoff":"2025-08"}},"zai/glm-4.6":{"metadata":{"displayName":"GLM 4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","lifecycle":"active","contextWindow":200000,"maxOutputTokens":96000,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-4.6","displayName":"GLM 4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-04"}},"zai/glm-4.7":{"metadata":{"displayName":"GLM 4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","lifecycle":"active","contextWindow":200000,"maxOutputTokens":120000,"knowledgeCutoff":"2025-04","lastUpdated":"2025-12-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-4.7","displayName":"GLM 4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-04"}},"zai/glm-4.7-flash":{"metadata":{"displayName":"GLM 4.7 Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","lifecycle":"active","contextWindow":200000,"maxOutputTokens":131000,"knowledgeCutoff":"2025-04","lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-4.7-flash","displayName":"GLM 4.7 Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-04"}},"zai/glm-4.7-flashx":{"metadata":{"displayName":"GLM 4.7 FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":200000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-4.7-flashx","displayName":"GLM 4.7 FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01"}},"zai/glm-5":{"metadata":{"displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","lifecycle":"active","contextWindow":202800,"maxOutputTokens":131100,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-5","displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202800,"defaultContextWindow":202800}},"zai/glm-5-turbo":{"metadata":{"displayName":"GLM 5 Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","lifecycle":"active","contextWindow":202800,"maxOutputTokens":131100,"structuredOutput":true,"lastUpdated":"2026-03-16","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-5-turbo","displayName":"GLM 5 Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202800,"defaultContextWindow":202800}},"zai/glm-5.1":{"metadata":{"displayName":"GLM 5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","lifecycle":"active","contextWindow":202800,"maxOutputTokens":64000,"structuredOutput":true,"lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-5.1","displayName":"GLM 5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202800,"defaultContextWindow":202800}},"zai/glm-5.2":{"metadata":{"displayName":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-5.2","displayName":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"zai/glm-5.2-fast":{"metadata":{"displayName":"GLM 5.2 Fast","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-5.2-fast","displayName":"GLM 5.2 Fast","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"zai/glm-5.3":{"metadata":{"displayName":"GLM 5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":1000000,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-5.3","displayName":"GLM 5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"zai/glm-5.3-fast":{"metadata":{"displayName":"GLM 5.3 Fast","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai/glm-5.3-fast","displayName":"GLM 5.3 Fast","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"zai/glm-5.3-flash":{"metadata":{"displayName":"GLM 5.3 Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131000,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"zai/glm-5.3-flash","displayName":"GLM 5.3 Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"zai/glm-5v-turbo":{"metadata":{"displayName":"GLM 5V Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","lifecycle":"active","contextWindow":200000,"maxOutputTokens":128000,"lastUpdated":"2026-04-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"zai/glm-5v-turbo","displayName":"GLM 5V Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}}}},"xai":{"baseUrl":"https://api.x.ai/v1","label":"xAI","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["grok-4.5","grok-4.20-0309-non-reasoning","grok-4.20-0309-reasoning","grok-4.3","grok-4.6","grok-build-0.1"],"models":{"grok-4.20-0309-non-reasoning":{"metadata":{"displayName":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":30000,"structuredOutput":true,"lastUpdated":"2026-03-09","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.20-0309-non-reasoning","displayName":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"grok-4.20-0309-reasoning":{"metadata":{"displayName":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":30000,"structuredOutput":true,"lastUpdated":"2026-03-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.20-0309-reasoning","displayName":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"grok-4.20-multi-agent-0309":{"metadata":{"displayName":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":30000,"structuredOutput":true,"lastUpdated":"2026-03-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.20-multi-agent-0309","displayName":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"grok-4.3":{"metadata":{"displayName":"Grok 4.3","description":"xAI's Grok for chat, coding, agentic tools, and lower hallucination risk","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":30000,"structuredOutput":true,"lastUpdated":"2026-04-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.3","displayName":"Grok 4.3","description":"xAI's Grok for chat, coding, agentic tools, and lower hallucination risk","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000}},"grok-4.5":{"metadata":{"displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","lifecycle":"active","contextWindow":500000,"maxOutputTokens":500000,"structuredOutput":true,"lastUpdated":"2026-07-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.5","displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":500000,"defaultContextWindow":500000}},"grok-4.6":{"metadata":{"displayName":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","lifecycle":"active","contextWindow":500000,"maxOutputTokens":500000,"knowledgeCutoff":"2026-02-01","structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.6","displayName":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":500000,"defaultContextWindow":500000,"knowledgeCutoff":"2026-02-01"}},"grok-build-0.1":{"metadata":{"displayName":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"structuredOutput":true,"lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-build-0.1","displayName":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"grok-imagine-image":{"metadata":{"displayName":"Grok Imagine Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":16000,"lastUpdated":"2026-01-28","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","pdf"],"output":["image","pdf"]}},"entry":{"id":"grok-imagine-image","displayName":"Grok Imagine Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":16000,"defaultContextWindow":16000}},"grok-imagine-image-2.0":{"metadata":{"displayName":"Grok Imagine Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":64000,"lastUpdated":"2026-08-07","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","pdf"],"output":["image","pdf"]}},"entry":{"id":"grok-imagine-image-2.0","displayName":"Grok Imagine Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":64000,"defaultContextWindow":64000}},"grok-imagine-image-quality":{"metadata":{"displayName":"Grok Imagine Image Quality","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":16000,"lastUpdated":"2026-04-03","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","pdf"],"output":["image","pdf"]}},"entry":{"id":"grok-imagine-image-quality","displayName":"Grok Imagine Image Quality","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":16000,"defaultContextWindow":16000}},"grok-imagine-video":{"metadata":{"displayName":"Grok Imagine Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":1024,"lastUpdated":"2026-01-28","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","video","pdf"],"output":["video"]}},"entry":{"id":"grok-imagine-video","displayName":"Grok Imagine Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1024,"defaultContextWindow":1024}},"grok-imagine-video-1.5":{"metadata":{"displayName":"Grok Imagine Video 1.5","description":"Video model for image-to-video generation, editing, and extension workflows","lifecycle":"active","contextWindow":1024,"lastUpdated":"2026-05-30","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","audio","pdf"],"output":["video"]}},"entry":{"id":"grok-imagine-video-1.5","displayName":"Grok Imagine Video 1.5","description":"Video model for image-to-video generation, editing, and extension workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1024,"defaultContextWindow":1024}}}},"xai-oauth":{"baseUrl":"https://api.x.ai/v1","label":"xAI OAuth (SuperGrok / X Premium)","authKind":"oauth_token","runtimeAdapter":{"kind":"openai-compatible","name":"provider","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol","auth":"oauth-bearer"},"fallbackModels":["grok-4.5","grok-4.20-0309-non-reasoning","grok-4.20-0309-reasoning","grok-4.3","grok-4.6","grok-build-0.1"],"models":{"grok-4.20-0309-non-reasoning":{"metadata":{"displayName":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":30000,"structuredOutput":true,"lastUpdated":"2026-03-09","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.20-0309-non-reasoning","displayName":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"grok-4.20-0309-reasoning":{"metadata":{"displayName":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":30000,"structuredOutput":true,"lastUpdated":"2026-03-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.20-0309-reasoning","displayName":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"grok-4.20-multi-agent-0309":{"metadata":{"displayName":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":30000,"structuredOutput":true,"lastUpdated":"2026-03-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.20-multi-agent-0309","displayName":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"grok-4.3":{"metadata":{"displayName":"Grok 4.3","description":"xAI's Grok for chat, coding, agentic tools, and lower hallucination risk","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":30000,"structuredOutput":true,"lastUpdated":"2026-04-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.3","displayName":"Grok 4.3","description":"xAI's Grok for chat, coding, agentic tools, and lower hallucination risk","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000}},"grok-4.5":{"metadata":{"displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","lifecycle":"active","contextWindow":500000,"maxOutputTokens":500000,"structuredOutput":true,"lastUpdated":"2026-07-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.5","displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":500000,"defaultContextWindow":500000}},"grok-4.6":{"metadata":{"displayName":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","lifecycle":"active","contextWindow":500000,"maxOutputTokens":500000,"knowledgeCutoff":"2026-02-01","structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-4.6","displayName":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":500000,"defaultContextWindow":500000,"knowledgeCutoff":"2026-02-01"}},"grok-build-0.1":{"metadata":{"displayName":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"structuredOutput":true,"lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"grok-build-0.1","displayName":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"grok-imagine-image":{"metadata":{"displayName":"Grok Imagine Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":16000,"lastUpdated":"2026-01-28","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","pdf"],"output":["image","pdf"]}},"entry":{"id":"grok-imagine-image","displayName":"Grok Imagine Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":16000,"defaultContextWindow":16000}},"grok-imagine-image-2.0":{"metadata":{"displayName":"Grok Imagine Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":64000,"lastUpdated":"2026-08-07","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","pdf"],"output":["image","pdf"]}},"entry":{"id":"grok-imagine-image-2.0","displayName":"Grok Imagine Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":64000,"defaultContextWindow":64000}},"grok-imagine-image-quality":{"metadata":{"displayName":"Grok Imagine Image Quality","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":16000,"lastUpdated":"2026-04-03","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","pdf"],"output":["image","pdf"]}},"entry":{"id":"grok-imagine-image-quality","displayName":"Grok Imagine Image Quality","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":16000,"defaultContextWindow":16000}},"grok-imagine-video":{"metadata":{"displayName":"Grok Imagine Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":1024,"lastUpdated":"2026-01-28","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","video","pdf"],"output":["video"]}},"entry":{"id":"grok-imagine-video","displayName":"Grok Imagine Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1024,"defaultContextWindow":1024}},"grok-imagine-video-1.5":{"metadata":{"displayName":"Grok Imagine Video 1.5","description":"Video model for image-to-video generation, editing, and extension workflows","lifecycle":"active","contextWindow":1024,"lastUpdated":"2026-05-30","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","audio","pdf"],"output":["video"]}},"entry":{"id":"grok-imagine-video-1.5","displayName":"Grok Imagine Video 1.5","description":"Video model for image-to-video generation, editing, and extension workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1024,"defaultContextWindow":1024}}}},"zai":{"baseUrl":"https://api.z.ai/api/paas/v4","label":"Z.AI","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["glm-5.2","glm-4.5","glm-4.5-air","glm-4.5-flash","glm-4.5v","glm-4.6","glm-4.6v","glm-4.7","glm-4.7-flash","glm-4.7-flashx","glm-5","glm-5-turbo","glm-5.1","glm-5.3","glm-5.3-flash","glm-5v-turbo"],"models":{"glm-4.5":{"metadata":{"displayName":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","lifecycle":"active","contextWindow":131072,"maxOutputTokens":98304,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.5","displayName":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"glm-4.5-air":{"metadata":{"displayName":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":98304,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.5-air","displayName":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"glm-4.5-flash":{"metadata":{"displayName":"GLM-4.5-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":98304,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.5-flash","displayName":"GLM-4.5-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"glm-4.5v":{"metadata":{"displayName":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":64000,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","lastUpdated":"2025-08-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"glm-4.5v","displayName":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":64000,"defaultContextWindow":64000,"knowledgeCutoff":"2025-04"}},"glm-4.6":{"metadata":{"displayName":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.6","displayName":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"glm-4.6v":{"metadata":{"displayName":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":128000,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-12-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"glm-4.6v","displayName":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-04"}},"glm-4.7":{"metadata":{"displayName":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2025-12-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.7","displayName":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"glm-4.7-flash":{"metadata":{"displayName":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","lifecycle":"active","contextWindow":200000,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.7-flash","displayName":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-04"}},"glm-4.7-flashx":{"metadata":{"displayName":"GLM-4.7-FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":200000,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.7-flashx","displayName":"GLM-4.7-FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-04"}},"glm-5":{"metadata":{"displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5","displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"glm-5-turbo":{"metadata":{"displayName":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","lifecycle":"active","contextWindow":200000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-03-16","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5-turbo","displayName":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}},"glm-5.1":{"metadata":{"displayName":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","lifecycle":"active","contextWindow":200000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.1","displayName":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}},"glm-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5.3":{"metadata":{"displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.3","displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5.3-flash":{"metadata":{"displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"glm-5.3-flash","displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5v-turbo":{"metadata":{"displayName":"GLM-5V-Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","lifecycle":"active","contextWindow":200000,"maxOutputTokens":131072,"lastUpdated":"2026-04-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"glm-5v-turbo","displayName":"GLM-5V-Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}}}},"xiaomi":{"baseUrl":"https://api.xiaomimimo.com/v1","label":"Xiaomi","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["mimo-v2.5","mimo-v2.5-pro","mimo-v2.5-pro-ultraspeed"],"models":{"mimo-v2-flash":{"metadata":{"displayName":"MiMo-V2-Flash","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2024-12-01","lastUpdated":"2026-06-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2-flash","displayName":"MiMo-V2-Flash","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-12-01"}},"mimo-v2-omni":{"metadata":{"displayName":"MiMo-V2-Omni","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-06-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]}},"entry":{"id":"mimo-v2-omni","displayName":"MiMo-V2-Omni","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-12"}},"mimo-v2-pro":{"metadata":{"displayName":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","lifecycle":"deprecated","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-06-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2-pro","displayName":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2.5":{"metadata":{"displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-06-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]}},"entry":{"id":"mimo-v2.5","displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2.5-pro":{"metadata":{"displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-06-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2.5-pro","displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2.5-pro-ultraspeed":{"metadata":{"displayName":"MiMo-V2.5-Pro-UltraSpeed","description":"MiMo pro model for strong multimodal reasoning and agent execution","lifecycle":"beta","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-06-09","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2.5-pro-ultraspeed","displayName":"MiMo-V2.5-Pro-UltraSpeed","description":"MiMo pro model for strong multimodal reasoning and agent execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}}}},"xiaomi-token-plan-cn":{"baseUrl":"https://token-plan-cn.xiaomimimo.com/v1","label":"Xiaomi Token Plan (China)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["mimo-v2.5-pro","mimo-v2.5"],"models":{"mimo-v2-pro":{"metadata":{"displayName":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","lifecycle":"deprecated","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2-pro","displayName":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2-tts":{"metadata":{"displayName":"MiMo-V2-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2-tts","displayName":"MiMo-V2-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"mimo-v2.5":{"metadata":{"displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]}},"entry":{"id":"mimo-v2.5","displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2.5-pro":{"metadata":{"displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2.5-pro","displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2.5-tts":{"metadata":{"displayName":"MiMo-V2.5-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2.5-tts","displayName":"MiMo-V2.5-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"mimo-v2.5-tts-voiceclone":{"metadata":{"displayName":"MiMo-V2.5-TTS-VoiceClone","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2.5-tts-voiceclone","displayName":"MiMo-V2.5-TTS-VoiceClone","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"mimo-v2.5-tts-voicedesign":{"metadata":{"displayName":"MiMo-V2.5-TTS-VoiceDesign","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2.5-tts-voicedesign","displayName":"MiMo-V2.5-TTS-VoiceDesign","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}}}},"xiaomi-token-plan-sgp":{"baseUrl":"https://token-plan-sgp.xiaomimimo.com/v1","label":"Xiaomi Token Plan (Singapore)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["mimo-v2.5-pro","mimo-v2.5"],"models":{"mimo-v2-pro":{"metadata":{"displayName":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","lifecycle":"deprecated","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2-pro","displayName":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2-tts":{"metadata":{"displayName":"MiMo-V2-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2-tts","displayName":"MiMo-V2-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"mimo-v2.5":{"metadata":{"displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]}},"entry":{"id":"mimo-v2.5","displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2.5-pro":{"metadata":{"displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2.5-pro","displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2.5-tts":{"metadata":{"displayName":"MiMo-V2.5-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2.5-tts","displayName":"MiMo-V2.5-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"mimo-v2.5-tts-voiceclone":{"metadata":{"displayName":"MiMo-V2.5-TTS-VoiceClone","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2.5-tts-voiceclone","displayName":"MiMo-V2.5-TTS-VoiceClone","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"mimo-v2.5-tts-voicedesign":{"metadata":{"displayName":"MiMo-V2.5-TTS-VoiceDesign","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2.5-tts-voicedesign","displayName":"MiMo-V2.5-TTS-VoiceDesign","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}}}},"xiaomi-token-plan-ams":{"baseUrl":"https://token-plan-ams.xiaomimimo.com/v1","label":"Xiaomi Token Plan (Europe)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["mimo-v2.5-pro","mimo-v2.5"],"models":{"mimo-v2-pro":{"metadata":{"displayName":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","lifecycle":"deprecated","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2-pro","displayName":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2-tts":{"metadata":{"displayName":"MiMo-V2-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2-tts","displayName":"MiMo-V2-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"mimo-v2.5":{"metadata":{"displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]}},"entry":{"id":"mimo-v2.5","displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2.5-pro":{"metadata":{"displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2.5-pro","displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2.5-tts":{"metadata":{"displayName":"MiMo-V2.5-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2.5-tts","displayName":"MiMo-V2.5-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"mimo-v2.5-tts-voiceclone":{"metadata":{"displayName":"MiMo-V2.5-TTS-VoiceClone","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2.5-tts-voiceclone","displayName":"MiMo-V2.5-TTS-VoiceClone","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"mimo-v2.5-tts-voicedesign":{"metadata":{"displayName":"MiMo-V2.5-TTS-VoiceDesign","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"mimo-v2.5-tts-voicedesign","displayName":"MiMo-V2.5-TTS-VoiceDesign","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}}}},"cerebras":{"baseUrl":"https://api.cerebras.ai/v1","label":"Cerebras","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["gpt-oss-120b","qwen-3.8-27b"],"models":{"gpt-oss-120b":{"metadata":{"displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":40960,"structuredOutput":true,"lastUpdated":"2026-06-10","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"gpt-oss-120b","displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"qwen-3.8-27b":{"metadata":{"displayName":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","lifecycle":"active","contextWindow":65536,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-09-03","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen-3.8-27b","displayName":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":65536,"defaultContextWindow":65536}}}},"mistral":{"baseUrl":"https://api.mistral.ai/v1","label":"Mistral","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol","responseShape":"array-or-data"},"fallbackModels":["mistral-large-latest","codestral-latest","magistral-medium-latest","magistral-small","ministral-3b-latest","ministral-8b-latest","mistral-large-2411","mistral-large-2512","mistral-medium-2505","mistral-medium-2508","mistral-medium-2604","mistral-medium-latest","mistral-nemo","mistral-small-2506","mistral-small-2603","mistral-small-latest","open-mistral-7b","open-mixtral-8x22b","open-mixtral-8x7b","pixtral-12b","pixtral-large-latest","voxtral-small-latest","zai-glm-5-2"],"models":{"codestral-latest":{"metadata":{"displayName":"Codestral (latest)","description":"Mistral code model for completions, refactors, and developer IDE workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":4096,"knowledgeCutoff":"2024-10","lastUpdated":"2025-01-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"codestral-latest","displayName":"Codestral (latest)","description":"Mistral code model for completions, refactors, and developer IDE workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-10"}},"devstral-2512":{"metadata":{"displayName":"Devstral 2","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-12","lastUpdated":"2025-12-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"devstral-2512","displayName":"Devstral 2","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-12"}},"devstral-latest":{"metadata":{"displayName":"Devstral 2","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-12","lastUpdated":"2025-12-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"devstral-latest","displayName":"Devstral 2","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-12"}},"devstral-medium-2507":{"metadata":{"displayName":"Devstral Medium","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-05","lastUpdated":"2025-07-10","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"devstral-medium-2507","displayName":"Devstral Medium","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-05"}},"devstral-medium-latest":{"metadata":{"displayName":"Devstral 2 (latest)","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-12","lastUpdated":"2025-12-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"devstral-medium-latest","displayName":"Devstral 2 (latest)","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-12"}},"devstral-small-2505":{"metadata":{"displayName":"Devstral Small 2505","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-05","lastUpdated":"2025-05-07","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"devstral-small-2505","displayName":"Devstral Small 2505","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-05"}},"devstral-small-2507":{"metadata":{"displayName":"Devstral Small","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-05","lastUpdated":"2025-07-10","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"devstral-small-2507","displayName":"Devstral Small","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-05"}},"labs-devstral-small-2512":{"metadata":{"displayName":"Devstral Small 2","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-12","lastUpdated":"2025-12-09","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"labs-devstral-small-2512","displayName":"Devstral Small 2","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-12"}},"magistral-medium-latest":{"metadata":{"displayName":"Magistral Medium (latest)","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2025-06","lastUpdated":"2025-03-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"magistral-medium-latest","displayName":"Magistral Medium (latest)","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-06"}},"magistral-small":{"metadata":{"displayName":"Magistral Small","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-06","lastUpdated":"2025-03-17","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"magistral-small","displayName":"Magistral Small","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-06"}},"ministral-3b-latest":{"metadata":{"displayName":"Ministral 3B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-10","lastUpdated":"2024-10-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"ministral-3b-latest","displayName":"Ministral 3B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-10"}},"ministral-8b-latest":{"metadata":{"displayName":"Ministral 8B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-10","lastUpdated":"2024-10-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"ministral-8b-latest","displayName":"Ministral 8B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-10"}},"mistral-embed":{"metadata":{"displayName":"Mistral Embed","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8000,"maxOutputTokens":3072,"lastUpdated":"2023-12-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistral-embed","displayName":"Mistral Embed","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8000,"defaultContextWindow":8000}},"mistral-large-2411":{"metadata":{"displayName":"Mistral Large 2.1","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2024-11","lastUpdated":"2024-11-18","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistral-large-2411","displayName":"Mistral Large 2.1","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-11"}},"mistral-large-2512":{"metadata":{"displayName":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2024-11","lastUpdated":"2025-12-02","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral-large-2512","displayName":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-11"}},"mistral-large-latest":{"metadata":{"displayName":"Mistral Large (latest)","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2024-11","lastUpdated":"2025-12-02","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral-large-latest","displayName":"Mistral Large (latest)","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-11"}},"mistral-medium-2505":{"metadata":{"displayName":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2025-05","lastUpdated":"2025-05-07","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral-medium-2505","displayName":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-05"}},"mistral-medium-2508":{"metadata":{"displayName":"Mistral Medium 3.1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-05","lastUpdated":"2025-08-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral-medium-2508","displayName":"Mistral Medium 3.1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-05"}},"mistral-medium-2604":{"metadata":{"displayName":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-04-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral-medium-2604","displayName":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","high"],"contextWindow":262144,"defaultContextWindow":262144}},"mistral-medium-latest":{"metadata":{"displayName":"Mistral Medium (latest)","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-04-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral-medium-latest","displayName":"Mistral Medium (latest)","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","high"],"contextWindow":262144,"defaultContextWindow":262144}},"mistral-nemo":{"metadata":{"displayName":"Mistral Nemo","description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-07","lastUpdated":"2024-07-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistral-nemo","displayName":"Mistral Nemo","description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-07"}},"mistral-small-2506":{"metadata":{"displayName":"Mistral Small 3.2","description":"Efficient Mistral model for fast chat, extraction, and production assistants","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2025-03","lastUpdated":"2025-06-20","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral-small-2506","displayName":"Mistral Small 3.2","description":"Efficient Mistral model for fast chat, extraction, and production assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-03"}},"mistral-small-2603":{"metadata":{"displayName":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-06","lastUpdated":"2026-03-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral-small-2603","displayName":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","high"],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-06"}},"mistral-small-latest":{"metadata":{"displayName":"Mistral Small (latest)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-06","lastUpdated":"2026-03-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral-small-latest","displayName":"Mistral Small (latest)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","high"],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-06"}},"open-mistral-7b":{"metadata":{"displayName":"Mistral 7B","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":8000,"maxOutputTokens":8000,"knowledgeCutoff":"2023-12","lastUpdated":"2023-09-27","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"open-mistral-7b","displayName":"Mistral 7B","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8000,"defaultContextWindow":8000,"knowledgeCutoff":"2023-12"}},"open-mistral-nemo":{"metadata":{"displayName":"Open Mistral Nemo","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-07","lastUpdated":"2024-07-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"open-mistral-nemo","displayName":"Open Mistral Nemo","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-07"}},"open-mixtral-8x22b":{"metadata":{"displayName":"Mixtral 8x22B","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":64000,"maxOutputTokens":64000,"knowledgeCutoff":"2024-04","lastUpdated":"2024-04-17","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"open-mixtral-8x22b","displayName":"Mixtral 8x22B","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":64000,"defaultContextWindow":64000,"knowledgeCutoff":"2024-04"}},"open-mixtral-8x7b":{"metadata":{"displayName":"Mixtral 8x7B","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":32000,"maxOutputTokens":32000,"knowledgeCutoff":"2024-01","lastUpdated":"2023-12-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"open-mixtral-8x7b","displayName":"Mixtral 8x7B","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000,"knowledgeCutoff":"2024-01"}},"pixtral-12b":{"metadata":{"displayName":"Pixtral 12B","description":"Mistral vision-language model for image understanding and multimodal chat","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09","lastUpdated":"2024-09-01","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"pixtral-12b","displayName":"Pixtral 12B","description":"Mistral vision-language model for image understanding and multimodal chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-09"}},"pixtral-large-latest":{"metadata":{"displayName":"Pixtral Large (latest)","description":"Mistral's larger vision model for document-heavy image understanding and chat","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-11","lastUpdated":"2024-11-04","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"pixtral-large-latest","displayName":"Pixtral Large (latest)","description":"Mistral's larger vision model for document-heavy image understanding and chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-11"}},"voxtral-mini-latest":{"metadata":{"displayName":"Voxtral Mini (latest)","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2026-02-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"voxtral-mini-latest","displayName":"Voxtral Mini (latest)","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"voxtral-mini-tts-latest":{"metadata":{"displayName":"Voxtral Mini TTS (latest)","description":"Multilingual text-to-speech model with zero-shot voice cloning","lifecycle":"active","lastUpdated":"2026-03-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"voxtral-mini-tts-latest","displayName":"Voxtral Mini TTS (latest)","description":"Multilingual text-to-speech model with zero-shot voice cloning","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"voxtral-small-latest":{"metadata":{"displayName":"Voxtral Small (latest)","description":"Instruct model with native audio input for speech understanding and tool use","lifecycle":"active","contextWindow":32000,"maxOutputTokens":32000,"lastUpdated":"2025-07-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","audio"],"output":["text"]}},"entry":{"id":"voxtral-small-latest","displayName":"Voxtral Small (latest)","description":"Instruct model with native audio input for speech understanding and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"zai-glm-5-2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"beta","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-glm-5-2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}}}},"cohere":{"baseUrl":"https://api.cohere.com/v2","label":"Cohere","authKind":"api_key","runtimeAdapter":{"kind":"cohere"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"cohere"},"fallbackModels":["command-a-plus-05-2026","command-a-03-2025","command-a-reasoning-08-2025","command-a-translate-08-2025","command-r-08-2024","command-r-plus-08-2024","command-r7b-12-2024","command-r7b-arabic-02-2025","north-mini-code-1-0"],"models":{"c4ai-aya-expanse-32b":{"metadata":{"displayName":"Aya Expanse 32B","description":"Open multilingual model optimized for generation across 23 languages","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4000,"lastUpdated":"2024-10-24","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"c4ai-aya-expanse-32b","displayName":"Aya Expanse 32B","description":"Open multilingual model optimized for generation across 23 languages","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"c4ai-aya-expanse-8b":{"metadata":{"displayName":"Aya Expanse 8B","description":"Compact open multilingual model optimized for generation across 23 languages","lifecycle":"active","contextWindow":8000,"maxOutputTokens":4000,"lastUpdated":"2024-10-24","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"c4ai-aya-expanse-8b","displayName":"Aya Expanse 8B","description":"Compact open multilingual model optimized for generation across 23 languages","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8000,"defaultContextWindow":8000}},"c4ai-aya-vision-32b":{"metadata":{"displayName":"Aya Vision 32B","description":"Open multilingual vision model for OCR, visual reasoning, and image question answering","lifecycle":"active","contextWindow":16000,"maxOutputTokens":4000,"lastUpdated":"2025-05-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"c4ai-aya-vision-32b","displayName":"Aya Vision 32B","description":"Open multilingual vision model for OCR, visual reasoning, and image question answering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":16000,"defaultContextWindow":16000}},"c4ai-aya-vision-8b":{"metadata":{"displayName":"Aya Vision 8B","description":"Compact open multilingual vision model for OCR and visual question answering","lifecycle":"active","contextWindow":16000,"maxOutputTokens":4000,"lastUpdated":"2025-05-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"c4ai-aya-vision-8b","displayName":"Aya Vision 8B","description":"Compact open multilingual vision model for OCR and visual question answering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":16000,"defaultContextWindow":16000}},"command-a-03-2025":{"metadata":{"displayName":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","lifecycle":"active","contextWindow":256000,"maxOutputTokens":8000,"knowledgeCutoff":"2024-06-01","lastUpdated":"2025-03-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"command-a-03-2025","displayName":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-06-01"}},"command-a-plus-05-2026":{"metadata":{"displayName":"Command A Plus","description":"Cohere's stronger command model for multilingual agents and enterprise workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-04-01","structuredOutput":true,"lastUpdated":"2026-06-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true,"offBehavior":"cohere-thinking-disabled"},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"command-a-plus-05-2026","displayName":"Command A Plus","description":"Cohere's stronger command model for multilingual agents and enterprise workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-04-01"}},"command-a-reasoning-08-2025":{"metadata":{"displayName":"Command A Reasoning","description":"Cohere reasoning model for multilingual enterprise agents, tools, and complex workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"knowledgeCutoff":"2024-06-01","lastUpdated":"2025-08-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true,"offBehavior":"cohere-thinking-disabled"},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"command-a-reasoning-08-2025","displayName":"Command A Reasoning","description":"Cohere reasoning model for multilingual enterprise agents, tools, and complex workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off"],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-06-01"}},"command-a-translate-08-2025":{"metadata":{"displayName":"Command A Translate","description":"Translation model for multilingual conversion, localization, and cross-language workflows","lifecycle":"active","contextWindow":8000,"maxOutputTokens":8000,"knowledgeCutoff":"2024-06-01","lastUpdated":"2025-08-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"command-a-translate-08-2025","displayName":"Command A Translate","description":"Translation model for multilingual conversion, localization, and cross-language workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8000,"defaultContextWindow":8000,"knowledgeCutoff":"2024-06-01"}},"command-a-vision-07-2025":{"metadata":{"displayName":"Command A Vision","description":"Cohere vision model for multilingual document analysis, OCR, and image understanding","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8000,"knowledgeCutoff":"2024-06-01","lastUpdated":"2025-07-31","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"command-a-vision-07-2025","displayName":"Command A Vision","description":"Cohere vision model for multilingual document analysis, OCR, and image understanding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-06-01"}},"command-r-08-2024":{"metadata":{"displayName":"Command R","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4000,"knowledgeCutoff":"2024-06-01","lastUpdated":"2024-08-30","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"command-r-08-2024","displayName":"Command R","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-06-01"}},"command-r-plus-08-2024":{"metadata":{"displayName":"Command R+","description":"Cohere's RAG workhorse for long-context enterprise search and tool use","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4000,"knowledgeCutoff":"2024-06-01","lastUpdated":"2024-08-30","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"command-r-plus-08-2024","displayName":"Command R+","description":"Cohere's RAG workhorse for long-context enterprise search and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-06-01"}},"command-r7b-12-2024":{"metadata":{"displayName":"Command R7B","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4000,"knowledgeCutoff":"2024-06-01","lastUpdated":"2024-12-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"command-r7b-12-2024","displayName":"Command R7B","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-06-01"}},"command-r7b-arabic-02-2025":{"metadata":{"displayName":"Command R7B Arabic","description":"Open Command R model optimized for Arabic enterprise chat, RAG, and cultural knowledge","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4000,"knowledgeCutoff":"2024-06-01","lastUpdated":"2025-02-27","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"command-r7b-arabic-02-2025","displayName":"Command R7B Arabic","description":"Open Command R model optimized for Arabic enterprise chat, RAG, and cultural knowledge","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-06-01"}},"north-mini-code-1-0":{"metadata":{"displayName":"North Mini Code","description":"Cohere coding model for practical software engineering and agentic edits","lifecycle":"active","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-09-23","structuredOutput":true,"lastUpdated":"2026-06-09","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai-compatible","name":"provider"},"baseUrl":"https://api.cohere.ai/compatibility/v1"},"entry":{"id":"north-mini-code-1-0","displayName":"North Mini Code","description":"Cohere coding model for practical software engineering and agentic edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high"],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-09-23"}}}},"huggingface":{"baseUrl":"https://router.huggingface.co/v1","label":"Hugging Face","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol","filter":"tool-capable"},"fallbackModels":["openai/gpt-oss-120b","meta-llama/Llama-3.3-70B-Instruct","deepseek-ai/DeepSeek-R1","deepseek-ai/DeepSeek-R1-0528","deepseek-ai/DeepSeek-V3","deepseek-ai/DeepSeek-V3-0324","deepseek-ai/DeepSeek-V3.1","deepseek-ai/DeepSeek-V3.2","deepseek-ai/DeepSeek-V4-Flash","deepseek-ai/DeepSeek-V4-Flash-0731","deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","deepseek-ai/DeepSeek-V4-Pro","deepseek-ai/DeepSeek-V4-Pro-0813","deepseek-ai/DeepSeek-V4.1-Flash","google/gemma-3-12b-it","google/gemma-3-27b-it","google/gemma-3-4b-it","google/gemma-4-26B-A4B-it","google/gemma-4-31B-it","meta-llama/Llama-3.1-8B-Instruct","MiniMaxAI/MiniMax-M2","MiniMaxAI/MiniMax-M2.1","MiniMaxAI/MiniMax-M2.5","MiniMaxAI/MiniMax-M2.7","MiniMaxAI/MiniMax-M3","moonshotai/Kimi-K2-Instruct","moonshotai/Kimi-K2-Instruct-0905","moonshotai/Kimi-K2-Thinking","moonshotai/Kimi-K2.5","moonshotai/Kimi-K2.6","moonshotai/Kimi-K2.7-Code","moonshotai/Kimi-K3","openai/gpt-oss-20b","Qwen/Qwen2.5-Coder-32B-Instruct","Qwen/Qwen3-235B-A22B","Qwen/Qwen3-235B-A22B-Instruct-2507","Qwen/Qwen3-235B-A22B-Thinking-2507","Qwen/Qwen3-30B-A3B","Qwen/Qwen3-32B","Qwen/Qwen3-Coder-30B-A3B-Instruct","Qwen/Qwen3-Coder-480B-A35B-Instruct","Qwen/Qwen3-Coder-Next","Qwen/Qwen3-Next-80B-A3B-Instruct","Qwen/Qwen3-Next-80B-A3B-Thinking","Qwen/Qwen3-VL-235B-A22B-Instruct","Qwen/Qwen3-VL-235B-A22B-Thinking","Qwen/Qwen3.5-122B-A10B","Qwen/Qwen3.5-27B","Qwen/Qwen3.5-35B-A3B","Qwen/Qwen3.5-397B-A17B","Qwen/Qwen3.5-9B","Qwen/Qwen3.6-27B","Qwen/Qwen3.6-35B-A3B","Qwen/Qwen3.8-2.4T-A95B","Qwen/Qwen3.8-27B","stepfun-ai/Step-3.5-Flash","stepfun-ai/Step-3.7-Flash","tencent/Hy3","thinkingmachines/Inkling","thinkingmachines/Inkling-Small","XiaomiMiMo/MiMo-V2-Flash","XiaomiMiMo/MiMo-V2.5","XiaomiMiMo/MiMo-V2.5-Pro","zai-org/GLM-4.5","zai-org/GLM-4.5-Air","zai-org/GLM-4.5V","zai-org/GLM-4.6","zai-org/GLM-4.6V-Flash","zai-org/GLM-4.7","zai-org/GLM-4.7-Flash","zai-org/GLM-5","zai-org/GLM-5.1","zai-org/GLM-5.2","zai-org/GLM-5.3","zai-org/GLM-5.3-Flash"],"models":{"deepseek-ai/DeepSeek-R1":{"metadata":{"displayName":"DeepSeek-R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","lifecycle":"active","contextWindow":64000,"maxOutputTokens":32768,"knowledgeCutoff":"2024-07","structuredOutput":true,"lastUpdated":"2025-05-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-R1","displayName":"DeepSeek-R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":64000,"defaultContextWindow":64000,"knowledgeCutoff":"2024-07"}},"deepseek-ai/DeepSeek-R1-0528":{"metadata":{"displayName":"DeepSeek-R1-0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","lifecycle":"active","contextWindow":163840,"maxOutputTokens":163840,"knowledgeCutoff":"2025-05","lastUpdated":"2025-05-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-R1-0528","displayName":"DeepSeek-R1-0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2025-05"}},"deepseek-ai/DeepSeek-V3":{"metadata":{"displayName":"DeepSeek-V3","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":64000,"maxOutputTokens":8192,"structuredOutput":true,"lastUpdated":"2024-12-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3","displayName":"DeepSeek-V3","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":64000,"defaultContextWindow":64000}},"deepseek-ai/DeepSeek-V3-0324":{"metadata":{"displayName":"DeepSeek V3 0324","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":163840,"structuredOutput":true,"lastUpdated":"2025-03-24","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3-0324","displayName":"DeepSeek V3 0324","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840}},"deepseek-ai/DeepSeek-V3.1":{"metadata":{"displayName":"DeepSeek-V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"structuredOutput":true,"lastUpdated":"2025-08-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3.1","displayName":"DeepSeek-V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"deepseek-ai/DeepSeek-V3.2":{"metadata":{"displayName":"DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":65536,"knowledgeCutoff":"2024-07","lastUpdated":"2025-12-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3.2","displayName":"DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2024-07"}},"deepseek-ai/DeepSeek-V4-Flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Flash","displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"deepseek-ai/DeepSeek-V4-Flash-0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp":{"metadata":{"displayName":"DeepSeek V4 Flash Vision Exp","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","displayName":"DeepSeek V4 Flash Vision Exp","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"deepseek-ai/DeepSeek-V4-Pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":393216,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Pro","displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"deepseek-ai/DeepSeek-V4-Pro-0813":{"metadata":{"displayName":"DeepSeek V4 Pro 0813","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","displayName":"DeepSeek V4 Pro 0813","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"deepseek-ai/DeepSeek-V4.1-Flash":{"metadata":{"displayName":"DeepSeek V4.1 Flash","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","high","xhigh","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4.1-Flash","displayName":"DeepSeek V4.1 Flash","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","high","xhigh","max"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"google/gemma-3-12b-it":{"metadata":{"displayName":"Gemma 3 12B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2024-08","structuredOutput":true,"lastUpdated":"2025-03-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3-12b-it","displayName":"Gemma 3 12B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-08"}},"google/gemma-3-27b-it":{"metadata":{"displayName":"Gemma 3 27B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2024-08","structuredOutput":true,"lastUpdated":"2025-03-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3-27b-it","displayName":"Gemma 3 27B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-08"}},"google/gemma-3-4b-it":{"metadata":{"displayName":"Gemma 3 4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2024-08","structuredOutput":true,"lastUpdated":"2025-03-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3-4b-it","displayName":"Gemma 3 4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-08"}},"google/gemma-4-26B-A4B-it":{"metadata":{"displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-4-26B-A4B-it","displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"google/gemma-4-31B-it":{"metadata":{"displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-4-31B-it","displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"meta-llama/Llama-3.1-8B-Instruct":{"metadata":{"displayName":"Llama-3.1-8B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":4096,"knowledgeCutoff":"2023-12","structuredOutput":true,"lastUpdated":"2024-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/Llama-3.1-8B-Instruct","displayName":"Llama-3.1-8B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12"}},"meta-llama/Llama-3.3-70B-Instruct":{"metadata":{"displayName":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","lifecycle":"active","contextWindow":131072,"maxOutputTokens":4096,"knowledgeCutoff":"2023-12","structuredOutput":true,"lastUpdated":"2024-12-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/Llama-3.3-70B-Instruct","displayName":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12"}},"MiniMaxAI/MiniMax-M2":{"metadata":{"displayName":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2025-10-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M2","displayName":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMaxAI/MiniMax-M2.1":{"metadata":{"displayName":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-10","lastUpdated":"2025-12-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M2.1","displayName":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-10"}},"MiniMaxAI/MiniMax-M2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M2.5","displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMaxAI/MiniMax-M2.7":{"metadata":{"displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M2.7","displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMaxAI/MiniMax-M3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","lifecycle":"active","contextWindow":524288,"maxOutputTokens":512000,"structuredOutput":true,"lastUpdated":"2026-06-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M3","displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":524288,"defaultContextWindow":524288}},"moonshotai/Kimi-K2-Instruct":{"metadata":{"displayName":"Kimi-K2-Instruct","description":"Kimi model for long-context chat, coding, and agentic reasoning","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2024-10","lastUpdated":"2025-07-14","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2-Instruct","displayName":"Kimi-K2-Instruct","description":"Kimi model for long-context chat, coding, and agentic reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-10"}},"moonshotai/Kimi-K2-Instruct-0905":{"metadata":{"displayName":"Kimi-K2-Instruct-0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"knowledgeCutoff":"2024-10","lastUpdated":"2025-09-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2-Instruct-0905","displayName":"Kimi-K2-Instruct-0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-10"}},"moonshotai/Kimi-K2-Thinking":{"metadata":{"displayName":"Kimi-K2-Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2024-08","lastUpdated":"2025-11-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2-Thinking","displayName":"Kimi-K2-Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-08"}},"moonshotai/Kimi-K2.5":{"metadata":{"displayName":"Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","lastUpdated":"2026-01-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2.5","displayName":"Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/Kimi-K2.6":{"metadata":{"displayName":"Kimi-K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","lastUpdated":"2026-04-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2.6","displayName":"Kimi-K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/Kimi-K2.7-Code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2.7-Code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/Kimi-K3":{"metadata":{"displayName":"Kimi K3","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K3","displayName":"Kimi K3","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"openai/gpt-oss-120b":{"metadata":{"displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-120b","displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"openai/gpt-oss-20b":{"metadata":{"displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-20b","displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"Qwen/Qwen2.5-Coder-32B-Instruct":{"metadata":{"displayName":"Qwen2.5-Coder-32B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"structuredOutput":true,"lastUpdated":"2024-11-12","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen2.5-Coder-32B-Instruct","displayName":"Qwen2.5-Coder-32B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"Qwen/Qwen3-235B-A22B":{"metadata":{"displayName":"Qwen3 235B-A22B","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","lifecycle":"active","contextWindow":40960,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-235B-A22B","displayName":"Qwen3 235B-A22B","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":40960,"defaultContextWindow":40960,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-235B-A22B-Instruct-2507":{"metadata":{"displayName":"Qwen3 235B-A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-07-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","displayName":"Qwen3 235B-A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3-235B-A22B-Thinking-2507":{"metadata":{"displayName":"Qwen3-235B-A22B-Thinking-2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","displayName":"Qwen3-235B-A22B-Thinking-2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-30B-A3B":{"metadata":{"displayName":"Qwen3 30B A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":40960,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-04-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-30B-A3B","displayName":"Qwen3 30B A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":40960,"defaultContextWindow":40960}},"Qwen/Qwen3-32B":{"metadata":{"displayName":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-32B","displayName":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-Coder-30B-A3B-Instruct":{"metadata":{"displayName":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","displayName":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-Coder-480B-A35B-Instruct":{"metadata":{"displayName":"Qwen3-Coder-480B-A35B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":66536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","displayName":"Qwen3-Coder-480B-A35B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-Coder-Next":{"metadata":{"displayName":"Qwen3-Coder-Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Coder-Next","displayName":"Qwen3-Coder-Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-Embedding-4B":{"metadata":{"displayName":"Qwen 3 Embedding 4B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":32000,"maxOutputTokens":2048,"knowledgeCutoff":"2024-12","lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Embedding-4B","displayName":"Qwen 3 Embedding 4B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000,"knowledgeCutoff":"2024-12"}},"Qwen/Qwen3-Embedding-8B":{"metadata":{"displayName":"Qwen 3 Embedding 8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":32000,"maxOutputTokens":4096,"knowledgeCutoff":"2024-12","lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Embedding-8B","displayName":"Qwen 3 Embedding 8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000,"knowledgeCutoff":"2024-12"}},"Qwen/Qwen3-Next-80B-A3B-Instruct":{"metadata":{"displayName":"Qwen3-Next-80B-A3B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":66536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Next-80B-A3B-Instruct","displayName":"Qwen3-Next-80B-A3B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-Next-80B-A3B-Thinking":{"metadata":{"displayName":"Qwen3-Next-80B-A3B-Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Next-80B-A3B-Thinking","displayName":"Qwen3-Next-80B-A3B-Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-VL-235B-A22B-Instruct":{"metadata":{"displayName":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-09-23","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-VL-235B-A22B-Instruct","displayName":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-03-31"}},"Qwen/Qwen3-VL-235B-A22B-Thinking":{"metadata":{"displayName":"Qwen3 VL 235B A22B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-09-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-VL-235B-A22B-Thinking","displayName":"Qwen3 VL 235B A22B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-03-31"}},"Qwen/Qwen3.5-122B-A10B":{"metadata":{"displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-122B-A10B","displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.5-27B":{"metadata":{"displayName":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-27B","displayName":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.5-35B-A3B":{"metadata":{"displayName":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-35B-A3B","displayName":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.5-397B-A17B":{"metadata":{"displayName":"Qwen3.5-397B-A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-397B-A17B","displayName":"Qwen3.5-397B-A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3.5-9B":{"metadata":{"displayName":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-9B","displayName":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.6-27B":{"metadata":{"displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.6-27B","displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.6-35B-A3B":{"metadata":{"displayName":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.6-35B-A3B","displayName":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.8-2.4T-A95B":{"metadata":{"displayName":"Qwen3.8 2.4T A95B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.8-2.4T-A95B","displayName":"Qwen3.8 2.4T A95B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","xhigh"],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.8-27B":{"metadata":{"displayName":"Qwen3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.8-27B","displayName":"Qwen3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":262144,"defaultContextWindow":262144}},"stepfun-ai/Step-3.5-Flash":{"metadata":{"displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","lifecycle":"active","contextWindow":262144,"maxOutputTokens":256000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"stepfun-ai/Step-3.5-Flash","displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"stepfun-ai/Step-3.7-Flash":{"metadata":{"displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","lifecycle":"active","contextWindow":262144,"maxOutputTokens":256000,"knowledgeCutoff":"2026-03-01","lastUpdated":"2026-05-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"stepfun-ai/Step-3.7-Flash","displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2026-03-01"}},"tencent/Hy3":{"metadata":{"displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":262144,"inputLimit":192000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-07-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/Hy3","displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","high"],"contextWindow":262144,"inputLimit":192000,"defaultContextWindow":262144,"defaultInputLimit":192000}},"thinkingmachines/Inkling":{"metadata":{"displayName":"Inkling","description":"Multimodal model for analyzing text, images, documents, and rich media","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"structuredOutput":true,"lastUpdated":"2026-07-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"thinkingmachines/Inkling","displayName":"Inkling","description":"Multimodal model for analyzing text, images, documents, and rich media","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576}},"thinkingmachines/Inkling-Small":{"metadata":{"displayName":"Inkling Small","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":524288,"maxOutputTokens":1048576,"lastUpdated":"2026-07-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"thinkingmachines/Inkling-Small","displayName":"Inkling Small","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":524288,"defaultContextWindow":524288}},"XiaomiMiMo/MiMo-V2-Flash":{"metadata":{"displayName":"MiMo-V2-Flash","description":"MiMo flash model for fast multimodal assistance and agent workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":4096,"knowledgeCutoff":"2024-12","lastUpdated":"2025-12-16","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"XiaomiMiMo/MiMo-V2-Flash","displayName":"MiMo-V2-Flash","description":"MiMo flash model for fast multimodal assistance and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-12"}},"XiaomiMiMo/MiMo-V2.5":{"metadata":{"displayName":"MiMo-V2.5","description":"MiMo model for long-context reasoning, perception, and agentic tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"XiaomiMiMo/MiMo-V2.5","displayName":"MiMo-V2.5","description":"MiMo model for long-context reasoning, perception, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-12"}},"XiaomiMiMo/MiMo-V2.5-Pro":{"metadata":{"displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"XiaomiMiMo/MiMo-V2.5-Pro","displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"zai-org/GLM-4.5":{"metadata":{"displayName":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","lifecycle":"active","contextWindow":131072,"maxOutputTokens":98304,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-4.5","displayName":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"zai-org/GLM-4.5-Air":{"metadata":{"displayName":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":98304,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-4.5-Air","displayName":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"zai-org/GLM-4.5V":{"metadata":{"displayName":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":65536,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","lastUpdated":"2025-08-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"zai-org/GLM-4.5V","displayName":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-04"}},"zai-org/GLM-4.6":{"metadata":{"displayName":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-4.6","displayName":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"zai-org/GLM-4.6V-Flash":{"metadata":{"displayName":"GLM-4.6V-Flash","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"lastUpdated":"2025-12-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"zai-org/GLM-4.6V-Flash","displayName":"GLM-4.6V-Flash","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"zai-org/GLM-4.7":{"metadata":{"displayName":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2025-12-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-4.7","displayName":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"zai-org/GLM-4.7-Flash":{"metadata":{"displayName":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":200000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-04","lastUpdated":"2025-08-08","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-4.7-Flash","displayName":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-04"}},"zai-org/GLM-5":{"metadata":{"displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":131072,"lastUpdated":"2026-02-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5","displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"zai-org/GLM-5.1":{"metadata":{"displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":131072,"lastUpdated":"2026-04-03","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.1","displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"zai-org/GLM-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"zai-org/GLM-5.3":{"metadata":{"displayName":"GLM-5.3","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.3","displayName":"GLM-5.3","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"zai-org/GLM-5.3-Flash":{"metadata":{"displayName":"GLM-5.3-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.3-Flash","displayName":"GLM-5.3-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}}}},"zenmux":{"baseUrl":"https://zenmux.ai/api/v1","label":"ZenMux","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider","replayAssistantReasoningAs":"reasoning","replayAssistantReasoningDetails":true},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol","auth":"none"},"fallbackModels":["moonshotai/kimi-k2.5","baidu/ernie-5.0-thinking-preview","deepseek/deepseek-v3.2","deepseek/deepseek-v3.2-exp","deepseek/deepseek-v4-flash","deepseek/deepseek-v4-pro","google/gemini-2.5-flash","google/gemini-2.5-flash-lite","google/gemini-2.5-pro","google/gemini-3-flash-preview","google/gemini-3.1-flash-lite","google/gemini-3.1-flash-lite-preview","google/gemini-3.1-pro-preview","google/gemini-3.5-flash","inclusionai/ring-2.6-1t","kuaishou/kat-coder-pro-v2","moonshotai/kimi-k2.6","moonshotai/kimi-k2.7-code","moonshotai/kimi-k2.7-code-free","moonshotai/kimi-k3","moonshotai/kimi-k3-free","openai/gpt-5.5","openai/gpt-5.5-instant","openai/gpt-5.5-pro","openai/gpt-5.6-luna","openai/gpt-5.6-sol","openai/gpt-5.6-terra","qwen/qwen3-coder-plus","qwen/qwen3-max","qwen/qwen3.5-flash","qwen/qwen3.5-plus","qwen/qwen3.6-plus","qwen/qwen3.7-max","qwen/qwen3.7-plus","sapiens-ai/agnes-1.5-lite","sapiens-ai/agnes-1.5-pro","stepfun/step-3.5-flash","stepfun/step-3.7-flash","stepfun/step-3.7-flash-free","tencent/hy3-preview","volcengine/doubao-seed-1.8","volcengine/doubao-seed-2.0-code","volcengine/doubao-seed-2.0-lite","volcengine/doubao-seed-2.0-mini","volcengine/doubao-seed-2.0-pro","x-ai/grok-4.2-fast","x-ai/grok-4.2-fast-non-reasoning","x-ai/grok-4.3","x-ai/grok-4.5","x-ai/grok-build-0.1","xiaomi/mimo-v2-flash","xiaomi/mimo-v2-omni","xiaomi/mimo-v2-pro","xiaomi/mimo-v2.5","xiaomi/mimo-v2.5-pro","z-ai/glm-4.5","z-ai/glm-4.5-air","z-ai/glm-4.6","z-ai/glm-4.6v","z-ai/glm-4.6v-flash","z-ai/glm-4.6v-flash-free","z-ai/glm-4.7","z-ai/glm-4.7-flash-free","z-ai/glm-4.7-flashx","z-ai/glm-5","z-ai/glm-5-turbo","z-ai/glm-5.1","z-ai/glm-5.2","z-ai/glm-5.2-free","z-ai/glm-5v-turbo"],"models":{"anthropic/claude-3.5-haiku":{"metadata":{"displayName":"Claude 3.5 Haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2024-11-04","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-3.5-haiku","displayName":"Claude 3.5 Haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"anthropic/claude-3.7-sonnet":{"metadata":{"displayName":"Claude 3.7 Sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-02-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-3.7-sonnet","displayName":"Claude 3.7 Sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"anthropic/claude-fable-5":{"metadata":{"displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-06-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-fable-5","displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"anthropic/claude-haiku-4.5":{"metadata":{"displayName":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-10-15","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["image","text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-haiku-4.5","displayName":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"anthropic/claude-opus-4":{"metadata":{"displayName":"Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-05-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-opus-4","displayName":"Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"anthropic/claude-opus-4.1":{"metadata":{"displayName":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-08-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-opus-4.1","displayName":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"anthropic/claude-opus-4.5":{"metadata":{"displayName":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-11-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-opus-4.5","displayName":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"anthropic/claude-opus-4.6":{"metadata":{"displayName":"Claude Opus 4.6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-05-31","lastUpdated":"2026-02-06","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["image","text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-opus-4.6","displayName":"Claude Opus 4.6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05-31"}},"anthropic/claude-opus-4.7":{"metadata":{"displayName":"Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-opus-4.7","displayName":"Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"anthropic/claude-opus-4.8":{"metadata":{"displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01","lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-opus-4.8","displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01"}},"anthropic/claude-sonnet-4":{"metadata":{"displayName":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-05-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-sonnet-4","displayName":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-01-01"}},"anthropic/claude-sonnet-4.5":{"metadata":{"displayName":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-09-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-sonnet-4.5","displayName":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-01-01"}},"anthropic/claude-sonnet-4.6":{"metadata":{"displayName":"Claude Sonnet 4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-02-18","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-sonnet-4.6","displayName":"Claude Sonnet 4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-08-31"}},"anthropic/claude-sonnet-5":{"metadata":{"displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-sonnet-5","displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"anthropic/claude-sonnet-5-free":{"metadata":{"displayName":"Claude Sonnet 5 (Free)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"anthropic/claude-sonnet-5-free","displayName":"Claude Sonnet 5 (Free)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"baidu/ernie-5.0-thinking-preview":{"metadata":{"displayName":"ERNIE 5.0","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-01-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"baidu/ernie-5.0-thinking-preview","displayName":"ERNIE 5.0","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-01-01"}},"deepseek/deepseek-chat":{"metadata":{"displayName":"DeepSeek-V3.2 (Non-thinking Mode)","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-12-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-chat","displayName":"DeepSeek-V3.2 (Non-thinking Mode)","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-01-01"}},"deepseek/deepseek-v3.2":{"metadata":{"displayName":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-12-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v3.2","displayName":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-01-01"}},"deepseek/deepseek-v3.2-exp":{"metadata":{"displayName":"DeepSeek-V3.2-Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-09-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v3.2-exp","displayName":"DeepSeek-V3.2-Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163000,"defaultContextWindow":163000,"knowledgeCutoff":"2025-01-01"}},"deepseek/deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-flash","displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek/deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-pro","displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"google/gemini-2.5-flash":{"metadata":{"displayName":"Gemini 2.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-06-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["pdf","image","text","audio"],"output":["text"]}},"entry":{"id":"google/gemini-2.5-flash","displayName":"Gemini 2.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048000,"defaultContextWindow":1048000,"knowledgeCutoff":"2025-01-01"}},"google/gemini-2.5-flash-lite":{"metadata":{"displayName":"Gemini 2.5 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","lifecycle":"active","contextWindow":1048000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-07-22","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["pdf","image","text","audio"],"output":["text"]}},"entry":{"id":"google/gemini-2.5-flash-lite","displayName":"Gemini 2.5 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048000,"defaultContextWindow":1048000,"knowledgeCutoff":"2025-01-01"}},"google/gemini-2.5-pro":{"metadata":{"displayName":"Gemini 2.5 Pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","lifecycle":"active","contextWindow":1048000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-06-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["pdf","image","text","audio","video"],"output":["text"]}},"entry":{"id":"google/gemini-2.5-pro","displayName":"Gemini 2.5 Pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048000,"defaultContextWindow":1048000,"knowledgeCutoff":"2025-01-01"}},"google/gemini-3-flash-preview":{"metadata":{"displayName":"Gemini 3 Flash Preview","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-12-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf","audio"],"output":["text"]}},"entry":{"id":"google/gemini-3-flash-preview","displayName":"Gemini 3 Flash Preview","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048000,"defaultContextWindow":1048000,"knowledgeCutoff":"2025-01-01"}},"google/gemini-3.1-flash-lite":{"metadata":{"displayName":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.1-flash-lite","displayName":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-flash-lite-preview":{"metadata":{"displayName":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":65530,"lastUpdated":"2025-03-20","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]}},"entry":{"id":"google/gemini-3.1-flash-lite-preview","displayName":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1050000,"defaultContextWindow":1050000}},"google/gemini-3.1-pro-preview":{"metadata":{"displayName":"Gemini 3.1 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","lifecycle":"active","contextWindow":1048000,"maxOutputTokens":64000,"knowledgeCutoff":"2026-02-19","lastUpdated":"2026-02-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf","audio","video"],"output":["text"]}},"entry":{"id":"google/gemini-3.1-pro-preview","displayName":"Gemini 3.1 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048000,"defaultContextWindow":1048000,"knowledgeCutoff":"2026-02-19"}},"google/gemini-3.5-flash":{"metadata":{"displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.5-flash","displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"inclusionai/ling-1t":{"metadata":{"displayName":"Ling-1T","description":"Tool-capable chat model for instruction following and agentic application workflows","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-10-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ling-1t","displayName":"Ling-1T","description":"Tool-capable chat model for instruction following and agentic application workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-01-01"}},"inclusionai/ring-1t":{"metadata":{"displayName":"Ring-1T","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-10-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ring-1t","displayName":"Ring-1T","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-01-01"}},"inclusionai/ring-2.6-1t":{"metadata":{"displayName":"inclusionAI: Ring-2.6-1T","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":262000,"maxOutputTokens":65000,"knowledgeCutoff":"2025-12-31","lastUpdated":"2026-05-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ring-2.6-1t","displayName":"inclusionAI: Ring-2.6-1T","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000,"knowledgeCutoff":"2025-12-31"}},"kuaishou/kat-coder-pro-v2":{"metadata":{"displayName":"KAT-Coder-Pro-V2","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":80000,"lastUpdated":"2026-03-30","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"kuaishou/kat-coder-pro-v2","displayName":"KAT-Coder-Pro-V2","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"minimax/minimax-m2":{"metadata":{"displayName":"MiniMax M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-10-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"minimax/minimax-m2","displayName":"MiniMax M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204000,"defaultContextWindow":204000,"knowledgeCutoff":"2025-01-01"}},"minimax/minimax-m2.1":{"metadata":{"displayName":"MiniMax M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-12-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"minimax/minimax-m2.1","displayName":"MiniMax M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204000,"defaultContextWindow":204000,"knowledgeCutoff":"2025-01-01"}},"minimax/minimax-m2.5":{"metadata":{"displayName":"MiniMax M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"minimax/minimax-m2.5","displayName":"MiniMax M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01-01"}},"minimax/minimax-m2.5-lightning":{"metadata":{"displayName":"MiniMax M2.5 highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"minimax/minimax-m2.5-lightning","displayName":"MiniMax M2.5 highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01-01"}},"minimax/minimax-m2.7":{"metadata":{"displayName":"MiniMax M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131070,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-03-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"minimax/minimax-m2.7","displayName":"MiniMax M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01-01"}},"minimax/minimax-m2.7-highspeed":{"metadata":{"displayName":"MiniMax M2.7 highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131070,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-03-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"minimax/minimax-m2.7-highspeed","displayName":"MiniMax M2.7 highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01-01"}},"minimax/minimax-m3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":512000,"lastUpdated":"2026-06-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"baseUrl":"https://zenmux.ai/api/anthropic/v1"},"entry":{"id":"minimax/minimax-m3","displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}},"moonshotai/kimi-k2-0905":{"metadata":{"displayName":"Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","lifecycle":"deprecated","contextWindow":262000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-09-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2-0905","displayName":"Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000,"knowledgeCutoff":"2025-01-01"}},"moonshotai/kimi-k2-thinking":{"metadata":{"displayName":"Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","lifecycle":"deprecated","contextWindow":262000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-11-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2-thinking","displayName":"Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000,"knowledgeCutoff":"2025-01-01"}},"moonshotai/kimi-k2-thinking-turbo":{"metadata":{"displayName":"Kimi K2 Thinking Turbo","description":"Kimi reasoning model for long-horizon research, planning, and tool use","lifecycle":"deprecated","contextWindow":262000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-11-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2-thinking-turbo","displayName":"Kimi K2 Thinking Turbo","description":"Kimi reasoning model for long-horizon research, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000,"knowledgeCutoff":"2025-01-01"}},"moonshotai/kimi-k2.5":{"metadata":{"displayName":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.5","displayName":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000,"knowledgeCutoff":"2025-01-01"}},"moonshotai/kimi-k2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262140,"maxOutputTokens":262140,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-04-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.6","displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262140,"defaultContextWindow":262140,"knowledgeCutoff":"2025-01-01"}},"moonshotai/kimi-k2.7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.7-code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/kimi-k2.7-code-free":{"metadata":{"displayName":"Kimi K2.7 Code (Free)","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.7-code-free","displayName":"Kimi K2.7 Code (Free)","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/kimi-k3":{"metadata":{"displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["max"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k3","displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"moonshotai/kimi-k3-free":{"metadata":{"displayName":"Kimi K3 (Free)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["max"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k3-free","displayName":"Kimi K3 (Free)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"openai/gpt-5":{"metadata":{"displayName":"GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":400000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5","displayName":"GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-01-01"}},"openai/gpt-5-codex":{"metadata":{"displayName":"GPT-5 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-09-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5-codex","displayName":"GPT-5 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-01-01"}},"openai/gpt-5.1":{"metadata":{"displayName":"GPT-5.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":400000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.1","displayName":"GPT-5.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-01-01"}},"openai/gpt-5.1-chat":{"metadata":{"displayName":"GPT-5.1 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.1-chat","displayName":"GPT-5.1 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-01-01"}},"openai/gpt-5.1-codex":{"metadata":{"displayName":"GPT-5.1-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.1-codex","displayName":"GPT-5.1-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-01-01"}},"openai/gpt-5.1-codex-mini":{"metadata":{"displayName":"GPT-5.1-Codex-Mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["image","text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.1-codex-mini","displayName":"GPT-5.1-Codex-Mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-01-01"}},"openai/gpt-5.2":{"metadata":{"displayName":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":400000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.2","displayName":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-01-01"}},"openai/gpt-5.2-codex":{"metadata":{"displayName":"GPT-5.2-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-01-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.2-codex","displayName":"GPT-5.2-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-01-01"}},"openai/gpt-5.2-pro":{"metadata":{"displayName":"GPT-5.2-Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.2-pro","displayName":"GPT-5.2-Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.3-chat":{"metadata":{"displayName":"GPT-5.3 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16380,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-03-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.3-chat","displayName":"GPT-5.3 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.3-codex":{"metadata":{"displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-03-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.3-codex","displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4":{"metadata":{"displayName":"GPT-5.4","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-03-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.4","displayName":"GPT-5.4","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4-mini":{"metadata":{"displayName":"GPT-5.4 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-03-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.4-mini","displayName":"GPT-5.4 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4-nano":{"metadata":{"displayName":"GPT-5.4 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-03-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.4-nano","displayName":"GPT-5.4 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4-pro":{"metadata":{"displayName":"GPT-5.4 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-03-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"none"}},"baseUrl":"https://zenmux.ai/api/v1"},"entry":{"id":"openai/gpt-5.4-pro","displayName":"GPT-5.4 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.5":{"metadata":{"displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.5","displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-12-01"}},"openai/gpt-5.5-instant":{"metadata":{"displayName":"GPT-5.5 Instant","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":400000,"inputLimit":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.5-instant","displayName":"GPT-5.5 Instant","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"inputLimit":400000,"defaultContextWindow":400000,"defaultInputLimit":400000,"knowledgeCutoff":"2025-12-01"}},"openai/gpt-5.5-pro":{"metadata":{"displayName":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.5-pro","displayName":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-12-01"}},"openai/gpt-5.6-luna":{"metadata":{"displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-luna","displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-sol":{"metadata":{"displayName":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-sol","displayName":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-terra":{"metadata":{"displayName":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-terra","displayName":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"qwen/qwen3-coder-plus":{"metadata":{"displayName":"Qwen3-Coder-Plus","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-coder-plus","displayName":"Qwen3-Coder-Plus","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-01-01"}},"qwen/qwen3-max":{"metadata":{"displayName":"Qwen3-Max-Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-01-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-max","displayName":"Qwen3-Max-Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-01-01"}},"qwen/qwen3.5-flash":{"metadata":{"displayName":"Qwen3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1020000,"maxOutputTokens":1020000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-03-20","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-flash","displayName":"Qwen3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1020000,"defaultContextWindow":1020000,"knowledgeCutoff":"2025-01-01"}},"qwen/qwen3.5-plus":{"metadata":{"displayName":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-03-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-plus","displayName":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-01-01"}},"qwen/qwen3.6-plus":{"metadata":{"displayName":"Qwen3.6-Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"lastUpdated":"2026-03-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3.6-plus","displayName":"Qwen3.6-Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen/qwen3.7-max":{"metadata":{"displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3.7-max","displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen/qwen3.7-plus":{"metadata":{"displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-04","lastUpdated":"2026-06-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.7-plus","displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"sapiens-ai/agnes-1.5-lite":{"metadata":{"displayName":"Agnes 1.5 Lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"lastUpdated":"2026-03-26","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"sapiens-ai/agnes-1.5-lite","displayName":"Agnes 1.5 Lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"sapiens-ai/agnes-1.5-pro":{"metadata":{"displayName":"Agnes 1.5 Pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"lastUpdated":"2026-03-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"sapiens-ai/agnes-1.5-pro","displayName":"Agnes 1.5 Pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"stepfun/step-3":{"metadata":{"displayName":"Step-3","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"deprecated","contextWindow":65536,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-07-31","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["image","text"],"output":["text"]}},"entry":{"id":"stepfun/step-3","displayName":"Step-3","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-01-01"}},"stepfun/step-3.5-flash":{"metadata":{"displayName":"Step 3.5 Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-02-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"stepfun/step-3.5-flash","displayName":"Step 3.5 Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-01-01"}},"stepfun/step-3.7-flash":{"metadata":{"displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2026-03-01","lastUpdated":"2026-05-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"stepfun/step-3.7-flash","displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2026-03-01"}},"stepfun/step-3.7-flash-free":{"metadata":{"displayName":"Step 3.7 Flash (Free)","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2026-03-01","lastUpdated":"2026-05-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"stepfun/step-3.7-flash-free","displayName":"Step 3.7 Flash (Free)","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2026-03-01"}},"tencent/hy3-preview":{"metadata":{"displayName":"Hy3 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":64000,"lastUpdated":"2026-04-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy3-preview","displayName":"Hy3 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","high"],"contextWindow":256000,"defaultContextWindow":256000}},"volcengine/doubao-seed-1.8":{"metadata":{"displayName":"Doubao-Seed-1.8","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-12-18","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"volcengine/doubao-seed-1.8","displayName":"Doubao-Seed-1.8","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-01-01"}},"volcengine/doubao-seed-2.0-code":{"metadata":{"displayName":"Doubao Seed 2.0 Code","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-03-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"volcengine/doubao-seed-2.0-code","displayName":"Doubao Seed 2.0 Code","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-01-01"}},"volcengine/doubao-seed-2.0-lite":{"metadata":{"displayName":"Doubao-Seed-2.0-lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2026-02-14","lastUpdated":"2026-02-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"volcengine/doubao-seed-2.0-lite","displayName":"Doubao-Seed-2.0-lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2026-02-14"}},"volcengine/doubao-seed-2.0-mini":{"metadata":{"displayName":"Doubao-Seed-2.0-mini","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2026-02-14","lastUpdated":"2026-02-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"volcengine/doubao-seed-2.0-mini","displayName":"Doubao-Seed-2.0-mini","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2026-02-14"}},"volcengine/doubao-seed-2.0-pro":{"metadata":{"displayName":"Doubao-Seed-2.0-pro","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2026-02-14","lastUpdated":"2026-02-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"volcengine/doubao-seed-2.0-pro","displayName":"Doubao-Seed-2.0-pro","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2026-02-14"}},"volcengine/doubao-seed-code":{"metadata":{"displayName":"Doubao-Seed-Code","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"deprecated","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-11-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"volcengine/doubao-seed-code","displayName":"Doubao-Seed-Code","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-01-01"}},"x-ai/grok-4":{"metadata":{"displayName":"Grok 4","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"deprecated","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["image","text"],"output":["text"]}},"entry":{"id":"x-ai/grok-4","displayName":"Grok 4","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-01-01"}},"x-ai/grok-4-fast":{"metadata":{"displayName":"Grok 4 Fast","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","lifecycle":"deprecated","contextWindow":2000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-09-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"x-ai/grok-4-fast","displayName":"Grok 4 Fast","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000,"knowledgeCutoff":"2025-01-01"}},"x-ai/grok-4.1-fast":{"metadata":{"displayName":"Grok 4.1 Fast","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","lifecycle":"deprecated","contextWindow":2000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-11-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"x-ai/grok-4.1-fast","displayName":"Grok 4.1 Fast","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000,"knowledgeCutoff":"2025-01-01"}},"x-ai/grok-4.1-fast-non-reasoning":{"metadata":{"displayName":"Grok 4.1 Fast Non Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","lifecycle":"deprecated","contextWindow":2000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-11-20","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"x-ai/grok-4.1-fast-non-reasoning","displayName":"Grok 4.1 Fast Non Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000,"knowledgeCutoff":"2025-01-01"}},"x-ai/grok-4.2-fast":{"metadata":{"displayName":"Grok 4.2 Fast","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":30000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-03-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"x-ai/grok-4.2-fast","displayName":"Grok 4.2 Fast","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000,"knowledgeCutoff":"2025-08-31"}},"x-ai/grok-4.2-fast-non-reasoning":{"metadata":{"displayName":"Grok 4.2 Fast Non Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":30000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-03-20","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"x-ai/grok-4.2-fast-non-reasoning","displayName":"Grok 4.2 Fast Non Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000,"knowledgeCutoff":"2025-08-31"}},"x-ai/grok-4.3":{"metadata":{"displayName":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":1000000,"structuredOutput":true,"lastUpdated":"2026-04-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"x-ai/grok-4.3","displayName":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000}},"x-ai/grok-4.5":{"metadata":{"displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","lifecycle":"active","contextWindow":500000,"maxOutputTokens":500000,"structuredOutput":true,"lastUpdated":"2026-07-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"x-ai/grok-4.5","displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":500000,"defaultContextWindow":500000}},"x-ai/grok-build-0.1":{"metadata":{"displayName":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"structuredOutput":true,"lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"x-ai/grok-build-0.1","displayName":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"x-ai/grok-code-fast-1":{"metadata":{"displayName":"Grok Code Fast 1","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","lifecycle":"deprecated","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-08-26","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"x-ai/grok-code-fast-1","displayName":"Grok Code Fast 1","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-01-01"}},"xiaomi/mimo-v2-flash":{"metadata":{"displayName":"MiMo-V2-Flash","description":"MiMo flash model for fast multimodal assistance and agent workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2024-12-01","lastUpdated":"2026-02-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"xiaomi/mimo-v2-flash","displayName":"MiMo-V2-Flash","description":"MiMo flash model for fast multimodal assistance and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-12-01"}},"xiaomi/mimo-v2-omni":{"metadata":{"displayName":"MiMo V2 Omni","description":"MiMo omni model for text, image, video, audio, and agents","lifecycle":"active","contextWindow":265000,"maxOutputTokens":265000,"knowledgeCutoff":"2024-12","lastUpdated":"2026-03-18","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]}},"entry":{"id":"xiaomi/mimo-v2-omni","displayName":"MiMo V2 Omni","description":"MiMo omni model for text, image, video, audio, and agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":265000,"defaultContextWindow":265000,"knowledgeCutoff":"2024-12"}},"xiaomi/mimo-v2-pro":{"metadata":{"displayName":"MiMo V2 Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":256000,"knowledgeCutoff":"2024-12","lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"xiaomi/mimo-v2-pro","displayName":"MiMo V2 Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-12"}},"xiaomi/mimo-v2.5":{"metadata":{"displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]}},"entry":{"id":"xiaomi/mimo-v2.5","displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"xiaomi/mimo-v2.5-pro":{"metadata":{"displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"xiaomi/mimo-v2.5-pro","displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"z-ai/glm-4.5":{"metadata":{"displayName":"GLM 4.5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-07-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.5","displayName":"GLM 4.5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-01-01"}},"z-ai/glm-4.5-air":{"metadata":{"displayName":"GLM 4.5 Air","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-07-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.5-air","displayName":"GLM 4.5 Air","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-01-01"}},"z-ai/glm-4.6":{"metadata":{"displayName":"GLM 4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-09-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.6","displayName":"GLM 4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"z-ai/glm-4.6v":{"metadata":{"displayName":"GLM 4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-12-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.6v","displayName":"GLM 4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"z-ai/glm-4.6v-flash":{"metadata":{"displayName":"GLM 4.6V FlashX","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-12-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.6v-flash","displayName":"GLM 4.6V FlashX","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"z-ai/glm-4.6v-flash-free":{"metadata":{"displayName":"GLM 4.6V Flash (Free)","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-12-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.6v-flash-free","displayName":"GLM 4.6V Flash (Free)","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"z-ai/glm-4.7":{"metadata":{"displayName":"GLM 4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2025-12-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.7","displayName":"GLM 4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"z-ai/glm-4.7-flash-free":{"metadata":{"displayName":"GLM 4.7 Flash (Free)","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.7-flash-free","displayName":"GLM 4.7 Flash (Free)","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"z-ai/glm-4.7-flashx":{"metadata":{"displayName":"GLM 4.7 FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.7-flashx","displayName":"GLM 4.7 FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"z-ai/glm-5":{"metadata":{"displayName":"GLM 5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":200000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-5","displayName":"GLM 5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"z-ai/glm-5-turbo":{"metadata":{"displayName":"GLM 5 Turbo","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":200000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-01-01","lastUpdated":"2026-03-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-5-turbo","displayName":"GLM 5 Turbo","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-01"}},"z-ai/glm-5.1":{"metadata":{"displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":200000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-04-03","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-5.1","displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}},"z-ai/glm-5.2":{"metadata":{"displayName":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-5.2","displayName":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"z-ai/glm-5.2-free":{"metadata":{"displayName":"GLM 5.2 (Free)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-5.2-free","displayName":"GLM 5.2 (Free)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"z-ai/glm-5v-turbo":{"metadata":{"displayName":"GLM 5V Turbo","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":128000,"lastUpdated":"2026-04-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"z-ai/glm-5v-turbo","displayName":"GLM 5V Turbo","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}}}},"opencode":{"baseUrl":"https://opencode.ai/zen/v1","label":"OpenCode Zen","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{"anthropic-messages":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"openai-responses":{"kind":"openai","apiProtocol":"openai-responses","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["gpt-5.5","big-pickle","claude-fable-5","claude-fable-5-1","claude-haiku-4-5","claude-opus-4-5","claude-opus-4-6","claude-opus-4-7","claude-opus-4-8","claude-opus-5","claude-sonnet-4","claude-sonnet-4-5","claude-sonnet-4-6","claude-sonnet-5","deepseek-v4-flash","deepseek-v4-flash-vision-exp","deepseek-v4-pro","gemini-3-flash","gemini-3.1-pro","gemini-3.5-flash","gemini-3.5-flash-lite","gemini-3.6-flash","gemini-3.7-flash","gemini-3.8-flash","glm-5","glm-5.1","glm-5.2","glm-5.3","glm-5.3-flash","gpt-5","gpt-5-codex","gpt-5-nano","gpt-5.1","gpt-5.1-codex","gpt-5.1-codex-max","gpt-5.1-codex-mini","gpt-5.2","gpt-5.2-codex","gpt-5.3-codex","gpt-5.3-codex-spark","gpt-5.4","gpt-5.4-mini","gpt-5.4-nano","gpt-5.4-pro","gpt-5.5-pro","gpt-5.6-luna","gpt-5.6-sol","gpt-5.6-terra","gpt-6-astra","grok-4.5","grok-4.6","grok-build-0.1","kimi-k2.5","kimi-k2.6","kimi-k2.7-code","kimi-k3","ling-3.0-flash-fin-free","mimo-v2.5-free","minimax-m2.5","minimax-m2.7","minimax-m3","muse-spark-1.2","muse-spark-1.2-contributor-free","muse-spark-1.3","muse-spark-1.3-contributor-free","nemotron-3-ultra-free","nemotron-3.5-lightning-free","qwen3.5-plus","qwen3.6-plus"],"models":{"big-pickle":{"metadata":{"displayName":"Big Pickle","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":200000,"inputLimit":160000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-10-17","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"big-pickle","displayName":"Big Pickle","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"inputLimit":160000,"defaultContextWindow":200000,"defaultInputLimit":160000,"knowledgeCutoff":"2025-01"}},"claude-3-5-haiku":{"metadata":{"displayName":"Claude Haiku 3.5","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":8192,"knowledgeCutoff":"2024-07-31","lastUpdated":"2024-10-22","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-3-5-haiku","displayName":"Claude Haiku 3.5","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-07-31"}},"claude-fable-5":{"metadata":{"displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-06-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-fable-5","displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"claude-fable-5-1":{"metadata":{"displayName":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-06","lastUpdated":"2026-09-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-fable-5-1","displayName":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-06"}},"claude-haiku-4-5":{"metadata":{"displayName":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-02-28","lastUpdated":"2025-10-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-haiku-4-5","displayName":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-02-28"}},"claude-opus-4-1":{"metadata":{"displayName":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-03-31","lastUpdated":"2025-08-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-opus-4-1","displayName":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-03-31"}},"claude-opus-4-5":{"metadata":{"displayName":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-03-31","lastUpdated":"2025-11-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-opus-4-5","displayName":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-03-31"}},"claude-opus-4-6":{"metadata":{"displayName":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-05-31","lastUpdated":"2026-03-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-opus-4-6","displayName":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05-31"}},"claude-opus-4-7":{"metadata":{"displayName":"Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-opus-4-7","displayName":"Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"claude-opus-4-8":{"metadata":{"displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01","lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-opus-4-8","displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01"}},"claude-opus-5":{"metadata":{"displayName":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-05","lastUpdated":"2026-07-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-opus-5","displayName":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-05"}},"claude-sonnet-4":{"metadata":{"displayName":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-03-31","lastUpdated":"2025-05-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-sonnet-4","displayName":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-03-31"}},"claude-sonnet-4-5":{"metadata":{"displayName":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-07-31","lastUpdated":"2025-09-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-sonnet-4-5","displayName":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-07-31"}},"claude-sonnet-4-6":{"metadata":{"displayName":"Claude Sonnet 4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-02-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-sonnet-4-6","displayName":"Claude Sonnet 4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-08-31"}},"claude-sonnet-5":{"metadata":{"displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"claude-sonnet-5","displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash","displayName":"DeepSeek V4 Flash","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-flash-free":{"metadata":{"displayName":"DeepSeek V4 Flash Free","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash-free","displayName":"DeepSeek V4 Flash Free","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-flash-vision-exp":{"metadata":{"displayName":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash-vision-exp","displayName":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-pro","displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"gemini-3-flash":{"metadata":{"displayName":"Gemini 3 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-12-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"google","normalizeBaseUrl":false}},"entry":{"id":"gemini-3-flash","displayName":"Gemini 3 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-3-pro":{"metadata":{"displayName":"Gemini 3 Pro","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-11-18","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"google","normalizeBaseUrl":false}},"entry":{"id":"gemini-3-pro","displayName":"Gemini 3 Pro","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-3.1-pro":{"metadata":{"displayName":"Gemini 3.1 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-02-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"google","normalizeBaseUrl":false}},"entry":{"id":"gemini-3.1-pro","displayName":"Gemini 3.1 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-3.5-flash":{"metadata":{"displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"google","normalizeBaseUrl":false}},"entry":{"id":"gemini-3.5-flash","displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"gemini-3.5-flash-lite":{"metadata":{"displayName":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-07-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"google","normalizeBaseUrl":false}},"entry":{"id":"gemini-3.5-flash-lite","displayName":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2026-03"}},"gemini-3.6-flash":{"metadata":{"displayName":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-07-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"google","normalizeBaseUrl":false}},"entry":{"id":"gemini-3.6-flash","displayName":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2026-03"}},"gemini-3.7-flash":{"metadata":{"displayName":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-08-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"google","normalizeBaseUrl":false}},"entry":{"id":"gemini-3.7-flash","displayName":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2026-03"}},"gemini-3.8-flash":{"metadata":{"displayName":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"google","normalizeBaseUrl":false}},"entry":{"id":"gemini-3.8-flash","displayName":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576}},"glm-4.6":{"metadata":{"displayName":"GLM-4.6","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.6","displayName":"GLM-4.6","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"glm-4.7":{"metadata":{"displayName":"GLM-4.7","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2025-12-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.7","displayName":"GLM-4.7","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"glm-4.7-free":{"metadata":{"displayName":"GLM-4.7 Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2025-12-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.7-free","displayName":"GLM-4.7 Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"glm-5":{"metadata":{"displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5","displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"glm-5-free":{"metadata":{"displayName":"GLM-5 Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5-free","displayName":"GLM-5 Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"glm-5.1":{"metadata":{"displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.1","displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"glm-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5.3":{"metadata":{"displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.3","displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5.3-flash":{"metadata":{"displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"glm-5.3-flash","displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"gpt-5":{"metadata":{"displayName":"GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5","displayName":"GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"gpt-5-codex":{"metadata":{"displayName":"GPT-5 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-09-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5-codex","displayName":"GPT-5 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"gpt-5-nano":{"metadata":{"displayName":"GPT-5 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-05-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5-nano","displayName":"GPT-5 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-05-30"}},"gpt-5.1":{"metadata":{"displayName":"GPT-5.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.1","displayName":"GPT-5.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"gpt-5.1-codex":{"metadata":{"displayName":"GPT-5.1 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.1-codex","displayName":"GPT-5.1 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"gpt-5.1-codex-max":{"metadata":{"displayName":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.1-codex-max","displayName":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"gpt-5.1-codex-mini":{"metadata":{"displayName":"GPT-5.1 Codex Mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.1-codex-mini","displayName":"GPT-5.1 Codex Mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"gpt-5.2":{"metadata":{"displayName":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.2","displayName":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.2-codex":{"metadata":{"displayName":"GPT-5.2 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-01-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.2-codex","displayName":"GPT-5.2 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.3-codex":{"metadata":{"displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-02-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.3-codex","displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.3-codex-spark":{"metadata":{"displayName":"GPT-5.3 Codex Spark","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":128000,"inputLimit":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.3-codex-spark","displayName":"GPT-5.3 Codex Spark","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":128000,"inputLimit":128000,"defaultContextWindow":128000,"defaultInputLimit":128000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4":{"metadata":{"displayName":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.4","displayName":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4-mini":{"metadata":{"displayName":"GPT-5.4 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.4-mini","displayName":"GPT-5.4 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4-nano":{"metadata":{"displayName":"GPT-5.4 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.4-nano","displayName":"GPT-5.4 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4-pro":{"metadata":{"displayName":"GPT-5.4 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":false,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.4-pro","displayName":"GPT-5.4 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.5":{"metadata":{"displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.5","displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-12-01"}},"gpt-5.5-pro":{"metadata":{"displayName":"GPT-5.5 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":false,"lastUpdated":"2026-04-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.5-pro","displayName":"GPT-5.5 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-12-01"}},"gpt-5.6-luna":{"metadata":{"displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.6-luna","displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"gpt-5.6-sol":{"metadata":{"displayName":"GPT-5.6 Sol (50% Off)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.6-sol","displayName":"GPT-5.6 Sol (50% Off)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"gpt-5.6-terra":{"metadata":{"displayName":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.6-terra","displayName":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"gpt-6-astra":{"metadata":{"displayName":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-04-30","structuredOutput":true,"lastUpdated":"2026-09-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-6-astra","displayName":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-04-30"}},"grok-4.5":{"metadata":{"displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","lifecycle":"active","contextWindow":500000,"maxOutputTokens":500000,"structuredOutput":true,"lastUpdated":"2026-07-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"grok-4.5","displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":500000,"defaultContextWindow":500000}},"grok-4.6":{"metadata":{"displayName":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","lifecycle":"active","contextWindow":500000,"maxOutputTokens":500000,"knowledgeCutoff":"2026-02-01","structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"grok-4.6","displayName":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":500000,"defaultContextWindow":500000,"knowledgeCutoff":"2026-02-01"}},"grok-build-0.1":{"metadata":{"displayName":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"structuredOutput":true,"lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"grok-build-0.1","displayName":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"grok-code":{"metadata":{"displayName":"Grok Code Fast 1","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":256000,"maxOutputTokens":256000,"lastUpdated":"2025-08-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"grok-code","displayName":"Grok Code Fast 1","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"hy3-free":{"metadata":{"displayName":"Hy3 Free","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"deprecated","contextWindow":190000,"inputLimit":192000,"maxOutputTokens":64000,"structuredOutput":true,"lastUpdated":"2026-07-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hy3-free","displayName":"Hy3 Free","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":190000,"inputLimit":192000,"defaultContextWindow":190000,"defaultInputLimit":192000}},"hy3-preview-free":{"metadata":{"displayName":"Hy3 preview Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-06","lastUpdated":"2026-04-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hy3-preview-free","displayName":"Hy3 preview Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-06"}},"kimi-k2":{"metadata":{"displayName":"Kimi K2","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2024-10","lastUpdated":"2025-09-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"kimi-k2","displayName":"Kimi K2","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-10"}},"kimi-k2-thinking":{"metadata":{"displayName":"Kimi K2 Thinking","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2024-10","lastUpdated":"2025-09-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"kimi-k2-thinking","displayName":"Kimi K2 Thinking","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-10"}},"kimi-k2.5":{"metadata":{"displayName":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2024-10","lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.5","displayName":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-10"}},"kimi-k2.5-free":{"metadata":{"displayName":"Kimi K2.5 Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2024-10","lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.5-free","displayName":"Kimi K2.5 Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-10"}},"kimi-k2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2024-10","lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.6","displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-10"}},"kimi-k2.7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.7-code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k3":{"metadata":{"displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["max"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k3","displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"laguna-s-2.1-free":{"metadata":{"displayName":"Laguna S 2.1 Free","description":"Agentic coding model from Poolside in the XS size class for local deployment","lifecycle":"deprecated","contextWindow":256000,"maxOutputTokens":32000,"structuredOutput":false,"lastUpdated":"2026-07-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"laguna-s-2.1-free","displayName":"Laguna S 2.1 Free","description":"Agentic coding model from Poolside in the XS size class for local deployment","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000}},"ling-2.6-flash-free":{"metadata":{"displayName":"Ling 2.6 Flash Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262100,"maxOutputTokens":32800,"knowledgeCutoff":"2025-06","lastUpdated":"2026-04-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"ling-2.6-flash-free","displayName":"Ling 2.6 Flash Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262100,"defaultContextWindow":262100,"knowledgeCutoff":"2025-06"}},"ling-3.0-flash-fin-free":{"metadata":{"displayName":"Ling 3.0 Flash Fin Free","description":"Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-08-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"ling-3.0-flash-fin-free","displayName":"Ling 3.0 Flash Fin Free","description":"Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"ling-3.0-flash-free":{"metadata":{"displayName":"Ling-3.0-flash Free","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-07-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"ling-3.0-flash-free","displayName":"Ling-3.0-flash Free","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":262144,"defaultContextWindow":262144}},"ling-3.0-tiny-free":{"metadata":{"displayName":"Ling-3.0-tiny Free","description":"Compact MoE model for responsive agents, instruction following, and multi-turn conversations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-08-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"ling-3.0-tiny-free","displayName":"Ling-3.0-tiny Free","description":"Compact MoE model for responsive agents, instruction following, and multi-turn conversations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"longcat-2.0-free":{"metadata":{"displayName":"LongCat-2.0 Free","description":"Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window","lifecycle":"deprecated","contextWindow":1000000,"maxOutputTokens":131072,"lastUpdated":"2026-06-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"longcat-2.0-free","displayName":"LongCat-2.0 Free","description":"Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"mimo-v2-flash-free":{"metadata":{"displayName":"MiMo V2 Flash Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2024-12","lastUpdated":"2025-12-16","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2-flash-free","displayName":"MiMo V2 Flash Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-12"}},"mimo-v2-omni-free":{"metadata":{"displayName":"MiMo V2 Omni Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":64000,"knowledgeCutoff":"2024-12","lastUpdated":"2026-03-18","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio","pdf"],"output":["text"]}},"entry":{"id":"mimo-v2-omni-free","displayName":"MiMo V2 Omni Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-12"}},"mimo-v2-pro-free":{"metadata":{"displayName":"MiMo V2 Pro Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":1048576,"maxOutputTokens":64000,"knowledgeCutoff":"2024-12","lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2-pro-free","displayName":"MiMo V2 Pro Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2.5-free":{"metadata":{"displayName":"MiMo V2.5 Free","description":"MiMo omni model for text, image, video, audio, and agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":32000,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]}},"entry":{"id":"mimo-v2.5-free","displayName":"MiMo V2.5 Free","description":"MiMo omni model for text, image, video, audio, and agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-12"}},"minimax-m2.1":{"metadata":{"displayName":"MiniMax-M2.1","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01","lastUpdated":"2025-12-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax-m2.1","displayName":"MiniMax-M2.1","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01"}},"minimax-m2.1-free":{"metadata":{"displayName":"MiniMax-M2.1 Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01","lastUpdated":"2025-12-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"minimax-m2.1-free","displayName":"MiniMax-M2.1 Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01"}},"minimax-m2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01","lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax-m2.5","displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01"}},"minimax-m2.5-free":{"metadata":{"displayName":"MiniMax-M2.5 Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01","lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"minimax-m2.5-free","displayName":"MiniMax-M2.5 Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01"}},"minimax-m2.7":{"metadata":{"displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01","lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax-m2.7","displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01"}},"minimax-m3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","lifecycle":"active","contextWindow":512000,"maxOutputTokens":128000,"lastUpdated":"2026-06-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"minimax-m3","displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":512000,"defaultContextWindow":512000}},"minimax-m3-free":{"metadata":{"displayName":"MiniMax-M3 Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-05-31","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"minimax-m3-free","displayName":"MiniMax-M3 Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01"}},"muse-spark-1.2":{"metadata":{"displayName":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"muse-spark-1.2","displayName":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"muse-spark-1.2-contributor-free":{"metadata":{"displayName":"Muse Spark 1.2 Free","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"muse-spark-1.2-contributor-free","displayName":"Muse Spark 1.2 Free","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"muse-spark-1.3":{"metadata":{"displayName":"Muse Spark 1.3","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"muse-spark-1.3","displayName":"Muse Spark 1.3","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"muse-spark-1.3-contributor-free":{"metadata":{"displayName":"Muse Spark 1.3 Free","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for coding and agentic workflows.","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"muse-spark-1.3-contributor-free","displayName":"Muse Spark 1.3 Free","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for coding and agentic workflows.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"nemotron-3-super-free":{"metadata":{"displayName":"Nemotron 3 Super Free","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","lifecycle":"deprecated","contextWindow":204800,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02","lastUpdated":"2026-03-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nemotron-3-super-free","displayName":"Nemotron 3 Super Free","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2026-02"}},"nemotron-3-ultra-free":{"metadata":{"displayName":"Nemotron 3 Ultra Free","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02","lastUpdated":"2026-06-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nemotron-3-ultra-free","displayName":"Nemotron 3 Ultra Free","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-02"}},"nemotron-3.5-lightning-free":{"metadata":{"displayName":"Nemotron 3.5 Lightning Free","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-08-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nemotron-3.5-lightning-free","displayName":"Nemotron 3.5 Lightning Free","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"north-mini-code-free":{"metadata":{"displayName":"North Mini Code Free","description":"Cohere coding model for practical software engineering and agentic edits","lifecycle":"deprecated","contextWindow":256000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-09-23","structuredOutput":true,"lastUpdated":"2026-06-09","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"north-mini-code-free","displayName":"North Mini Code Free","description":"Cohere coding model for practical software engineering and agentic edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high"],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-09-23"}},"qwen3-coder":{"metadata":{"displayName":"Qwen3 Coder","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder","displayName":"Qwen3 Coder","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3.5-plus":{"metadata":{"displayName":"Qwen3.5 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"qwen3.5-plus","displayName":"Qwen3.5 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3.6-plus":{"metadata":{"displayName":"Qwen3.6 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"qwen3.6-plus","displayName":"Qwen3.6 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3.6-plus-free":{"metadata":{"displayName":"Qwen3.6 Plus Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"qwen3.6-plus-free","displayName":"Qwen3.6 Plus Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"ring-2.6-1t-free":{"metadata":{"displayName":"Ring 2.6 1T Free","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262000,"maxOutputTokens":66000,"knowledgeCutoff":"2025-06","lastUpdated":"2026-05-08","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"ring-2.6-1t-free","displayName":"Ring 2.6 1T Free","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000,"knowledgeCutoff":"2025-06"}},"trinity-large-preview-free":{"metadata":{"displayName":"Trinity Large Preview","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2025-06","lastUpdated":"2026-01-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"trinity-large-preview-free","displayName":"Trinity Large Preview","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-06"}},"x-preview-f-free":{"metadata":{"displayName":"Ox Alpha Free (Unlimited)","description":"Stealth reasoning model for coding, agentic tasks, and tool use","lifecycle":"deprecated","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"x-preview-f-free","displayName":"Ox Alpha Free (Unlimited)","description":"Stealth reasoning model for coding, agentic tasks, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}}}},"opencode-go":{"baseUrl":"https://opencode.ai/zen/go/v1","label":"OpenCode Go","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{"anthropic-messages":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"openai-responses":{"kind":"openai","apiProtocol":"openai-responses","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["minimax-m3","deepseek-v4-flash","deepseek-v4-flash-vision-exp","deepseek-v4-pro","deepseek-v4.1-flash","glm-5.1","glm-5.2","glm-5.3","glm-5.3-flash","gpt-5.6-luna","grok-4.6","hy3","hy4-preview","kimi-k2.6","kimi-k2.7-code","kimi-k3","longcat-2.0","mimo-v2.5","mimo-v2.5-pro","minimax-m2.7","muse-spark-1.2-contributor","muse-spark-1.3-contributor","qwen3.6-plus","qwen3.7-max","qwen3.7-plus","qwen3.8-flash","qwen3.8-max"],"models":{"deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash","displayName":"DeepSeek V4 Flash","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-flash-vision-exp":{"metadata":{"displayName":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash-vision-exp","displayName":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek V4 Pro (New)","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-pro","displayName":"DeepSeek V4 Pro (New)","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4.1-flash":{"metadata":{"displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-v4.1-flash","displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"glm-5":{"metadata":{"displayName":"GLM-5","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":202752,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5","displayName":"GLM-5","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752,"knowledgeCutoff":"2025-04"}},"glm-5.1":{"metadata":{"displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.1","displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752,"knowledgeCutoff":"2025-04"}},"glm-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5.3":{"metadata":{"displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.3","displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5.3-flash":{"metadata":{"displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"glm-5.3-flash","displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"gpt-5.6-luna":{"metadata":{"displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"gpt-5.6-luna","displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"grok-4.5":{"metadata":{"displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","lifecycle":"deprecated","contextWindow":500000,"maxOutputTokens":500000,"structuredOutput":true,"lastUpdated":"2026-07-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"grok-4.5","displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":500000,"defaultContextWindow":500000}},"grok-4.6":{"metadata":{"displayName":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","lifecycle":"active","contextWindow":500000,"maxOutputTokens":500000,"knowledgeCutoff":"2026-02-01","structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"grok-4.6","displayName":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":500000,"defaultContextWindow":500000,"knowledgeCutoff":"2026-02-01"}},"hy3":{"metadata":{"displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":256000,"inputLimit":192000,"maxOutputTokens":128000,"lastUpdated":"2026-07-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hy3","displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","high"],"contextWindow":256000,"inputLimit":192000,"defaultContextWindow":256000,"defaultInputLimit":192000}},"hy4-preview":{"metadata":{"displayName":"Hy4 preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":64000,"lastUpdated":"2026-08-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hy4-preview","displayName":"Hy4 preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high"],"contextWindow":1024000,"defaultContextWindow":1024000}},"kimi-k2.5":{"metadata":{"displayName":"Kimi K2.5","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2024-10","lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.5","displayName":"Kimi K2.5","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-10"}},"kimi-k2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2024-10","lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.6","displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-10"}},"kimi-k2.7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.7-code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k3":{"metadata":{"displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["max"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k3","displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"longcat-2.0":{"metadata":{"displayName":"LongCat-2.0","description":"Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"lastUpdated":"2026-06-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"longcat-2.0","displayName":"LongCat-2.0","description":"Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"mimo-v2-omni":{"metadata":{"displayName":"MiMo V2 Omni","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":128000,"knowledgeCutoff":"2024-12","lastUpdated":"2026-03-18","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio","pdf"],"output":["text"]}},"entry":{"id":"mimo-v2-omni","displayName":"MiMo V2 Omni","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-12"}},"mimo-v2-pro":{"metadata":{"displayName":"MiMo V2 Pro","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":1048576,"maxOutputTokens":128000,"knowledgeCutoff":"2024-12","lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2-pro","displayName":"MiMo V2 Pro","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"mimo-v2.5":{"metadata":{"displayName":"MiMo V2.5","description":"MiMo omni model for text, image, video, audio, and agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]}},"entry":{"id":"mimo-v2.5","displayName":"MiMo V2.5","description":"MiMo omni model for text, image, video, audio, and agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-12"}},"mimo-v2.5-pro":{"metadata":{"displayName":"MiMo V2.5 Pro","description":"MiMo pro model for strong multimodal reasoning and agent execution","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":128000,"knowledgeCutoff":"2024-12","lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mimo-v2.5-pro","displayName":"MiMo V2.5 Pro","description":"MiMo pro model for strong multimodal reasoning and agent execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"minimax-m2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":204800,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"minimax-m2.5","displayName":"MiniMax-M2.5","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01"}},"minimax-m2.7":{"metadata":{"displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01","lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"minimax-m2.7","displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01"}},"minimax-m3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01","lastUpdated":"2026-05-31","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"minimax-m3","displayName":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-01"}},"muse-spark-1.2-contributor":{"metadata":{"displayName":"Muse Spark 1.2 Contributor","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"muse-spark-1.2-contributor","displayName":"Muse Spark 1.2 Contributor","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"muse-spark-1.3-contributor":{"metadata":{"displayName":"Muse Spark 1.3 Contributor","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for coding and agentic workflows.","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"openai","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"entry":{"id":"muse-spark-1.3-contributor","displayName":"Muse Spark 1.3 Contributor","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for coding and agentic workflows.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"omen-alpha":{"metadata":{"displayName":"Omen Alpha","description":"oH man anothEr aLPha ModEl","lifecycle":"deprecated","contextWindow":500000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-09-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"omen-alpha","displayName":"Omen Alpha","description":"oH man anothEr aLPha ModEl","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high"],"contextWindow":500000,"defaultContextWindow":500000}},"ox-alpha-free":{"metadata":{"displayName":"Ox Alpha Free (Unlimited)","description":"Stealth reasoning model for coding, agentic tasks, and tool use","lifecycle":"deprecated","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"ox-alpha-free","displayName":"Ox Alpha Free (Unlimited)","description":"Stealth reasoning model for coding, agentic tasks, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.5-plus":{"metadata":{"displayName":"Qwen3.5 Plus","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.5-plus","displayName":"Qwen3.5 Plus","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3.6-plus":{"metadata":{"displayName":"Qwen3.6 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-plus","displayName":"Qwen3.6 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.7-max":{"metadata":{"displayName":"Qwen3.7 Max","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3.7-max","displayName":"Qwen3.7 Max","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.7-plus":{"metadata":{"displayName":"Qwen3.7 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"lastUpdated":"2026-06-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.7-plus","displayName":"Qwen3.7 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.8-flash":{"metadata":{"displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"runtimeOverride":{"adapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true}},"entry":{"id":"qwen3.8-flash","displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.8-max":{"metadata":{"displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter multimodal flagship for coding, professional work, and long-horizon agentic workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-03","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.8-max","displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter multimodal flagship for coding, professional work, and long-horizon agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}}}},"togetherai":{"baseUrl":"https://api.together.ai/v1","label":"Together AI","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["MiniMaxAI/MiniMax-M3","deepseek-ai/DeepSeek-V4-Flash-0731","deepseek-ai/DeepSeek-V4-Pro","deepseek-ai/DeepSeek-V4-Pro-0813","deepseek-ai/DeepSeek-V4.1-Flash","google/gemma-4-31B-it","meta-llama/Llama-3.3-70B-Instruct-Turbo","MiniMaxAI/MiniMax-M2.7","moonshotai/Kimi-K2.6","moonshotai/Kimi-K2.7-Code","moonshotai/Kimi-K3","nvidia/nemotron-3-ultra-550b-a55b","openai/gpt-oss-120b","openai/gpt-oss-20b","Qwen/Qwen2.5-7B-Instruct-Turbo","Qwen/Qwen3.5-9B","Qwen/Qwen3.6-Plus","Qwen/Qwen3.7-Max","thinkingmachines/Inkling","zai-org/GLM-5.2","zai-org/GLM-5.3","zai-org/GLM-5.3-Flash"],"models":{"deepcogito/cogito-v2-1-671b":{"metadata":{"displayName":"Cogito v2.1 671B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":163840,"maxOutputTokens":163840,"lastUpdated":"2025-11-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepcogito/cogito-v2-1-671b","displayName":"Cogito v2.1 671B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840}},"deepseek-ai/DeepSeek-R1":{"metadata":{"displayName":"DeepSeek-R1","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":163839,"maxOutputTokens":163839,"knowledgeCutoff":"2024-07","lastUpdated":"2025-03-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-R1","displayName":"DeepSeek-R1","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163839,"defaultContextWindow":163839,"knowledgeCutoff":"2024-07"}},"deepseek-ai/DeepSeek-V3":{"metadata":{"displayName":"DeepSeek-V3","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2024-07","lastUpdated":"2025-05-29","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3","displayName":"DeepSeek-V3","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-07"}},"deepseek-ai/DeepSeek-V3-1":{"metadata":{"displayName":"DeepSeek V3.1","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2025-08","lastUpdated":"2025-08-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3-1","displayName":"DeepSeek V3.1","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-08"}},"deepseek-ai/DeepSeek-V4-Flash-0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-ai/DeepSeek-V4-Pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","lifecycle":"active","contextWindow":512000,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Pro","displayName":"DeepSeek V4 Pro","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":512000,"defaultContextWindow":512000}},"deepseek-ai/DeepSeek-V4-Pro-0813":{"metadata":{"displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"deepseek-ai/DeepSeek-V4.1-Flash":{"metadata":{"displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4.1-Flash","displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"essentialai/Rnj-1-Instruct":{"metadata":{"displayName":"Rnj-1 Instruct","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","lifecycle":"deprecated","contextWindow":32768,"maxOutputTokens":32768,"knowledgeCutoff":"2024-10","lastUpdated":"2025-12-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"essentialai/Rnj-1-Instruct","displayName":"Rnj-1 Instruct","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-10"}},"google/gemma-3n-E4B-it":{"metadata":{"displayName":"Gemma 3N E4B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":32768,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2025-05-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"google/gemma-3n-E4B-it","displayName":"Gemma 3N E4B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"google/gemma-4-31B-it":{"metadata":{"displayName":"Gemma 4 31B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-4-31B-it","displayName":"Gemma 4 31B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"LiquidAI/LFM2-24B-A2B":{"metadata":{"displayName":"LFM2-24B-A2B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","lifecycle":"active","contextWindow":32768,"maxOutputTokens":32768,"lastUpdated":"2026-02-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"LiquidAI/LFM2-24B-A2B","displayName":"LFM2-24B-A2B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"meta-llama/Llama-3.3-70B-Instruct-Turbo":{"metadata":{"displayName":"Llama 3.3 70B","description":"Compact Llama instruction model for fast chat and local deployment","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2023-12","lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","displayName":"Llama 3.3 70B","description":"Compact Llama instruction model for fast chat and local deployment","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12"}},"meta-llama/Meta-Llama-3-8B-Instruct-Lite":{"metadata":{"displayName":"Meta Llama 3 8B Instruct Lite","description":"Compact Llama instruction model for fast chat and local deployment","lifecycle":"active","contextWindow":8192,"maxOutputTokens":8192,"lastUpdated":"2024-04-18","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/Meta-Llama-3-8B-Instruct-Lite","displayName":"Meta Llama 3 8B Instruct Lite","description":"Compact Llama instruction model for fast chat and local deployment","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"MiniMaxAI/MiniMax-M2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M2.5","displayName":"MiniMax-M2.5","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMaxAI/MiniMax-M2.7":{"metadata":{"displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":202752,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M2.7","displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"MiniMaxAI/MiniMax-M3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","lifecycle":"active","contextWindow":524288,"maxOutputTokens":250000,"structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M3","displayName":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":524288,"defaultContextWindow":524288}},"moonshotai/Kimi-K2.5":{"metadata":{"displayName":"Kimi K2.5","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2026-01","lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2.5","displayName":"Kimi K2.5","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2026-01"}},"moonshotai/Kimi-K2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131000,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2.6","displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/Kimi-K2.7-Code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Kimi coding model for software agents, refactors, and repository reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2.7-Code","displayName":"Kimi K2.7 Code","description":"Kimi coding model for software agents, refactors, and repository reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"moonshotai/Kimi-K3":{"metadata":{"displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K3","displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"nvidia/nemotron-3-ultra-550b-a55b":{"metadata":{"displayName":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","lifecycle":"active","contextWindow":512300,"maxOutputTokens":512300,"structuredOutput":true,"lastUpdated":"2026-06-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-ultra-550b-a55b","displayName":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":512300,"defaultContextWindow":512300}},"openai/gpt-oss-120b":{"metadata":{"displayName":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2025-08","lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-120b","displayName":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-08"}},"openai/gpt-oss-20b":{"metadata":{"displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-20b","displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"pearl-ai/gemma-4-31b-it":{"metadata":{"displayName":"Pearl AI Gemma 4 31B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":32000,"maxOutputTokens":32000,"lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"pearl-ai/gemma-4-31b-it","displayName":"Pearl AI Gemma 4 31B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000}},"Qwen/Qwen2.5-7B-Instruct-Turbo":{"metadata":{"displayName":"Qwen 2.5 7B Instruct Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","lifecycle":"active","contextWindow":32768,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2024-09-19","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen2.5-7B-Instruct-Turbo","displayName":"Qwen 2.5 7B Instruct Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"Qwen/Qwen3-235B-A22B-Instruct-2507-tput":{"metadata":{"displayName":"Qwen3 235B A22B Instruct 2507 FP8","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-07","lastUpdated":"2025-07-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507-tput","displayName":"Qwen3 235B A22B Instruct 2507 FP8","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-07"}},"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8":{"metadata":{"displayName":"Qwen3 Coder 480B A35B Instruct","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","displayName":"Qwen3 Coder 480B A35B Instruct","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-Coder-Next-FP8":{"metadata":{"displayName":"Qwen3 Coder Next FP8","description":"Legacy model retained for compatibility with older integrations","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2026-02-03","lastUpdated":"2026-02-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Coder-Next-FP8","displayName":"Qwen3 Coder Next FP8","description":"Legacy model retained for compatibility with older integrations","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2026-02-03"}},"Qwen/Qwen3.5-397B-A17B":{"metadata":{"displayName":"Qwen3.5 397B A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":130000,"lastUpdated":"2026-06-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-397B-A17B","displayName":"Qwen3.5 397B A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.5-9B":{"metadata":{"displayName":"Qwen3.5 9B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-03-03","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-9B","displayName":"Qwen3.5 9B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.6-Plus":{"metadata":{"displayName":"Qwen3.6 Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":500000,"lastUpdated":"2026-04-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.6-Plus","displayName":"Qwen3.6 Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"Qwen/Qwen3.7-Max":{"metadata":{"displayName":"Qwen3.7 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":500000,"lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.7-Max","displayName":"Qwen3.7 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"thinkingmachines/Inkling":{"metadata":{"displayName":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","lifecycle":"active","contextWindow":524288,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["max","xhigh","high","medium","low","none"]},"modalities":{"input":["text","image","audio"],"output":["text"]}},"entry":{"id":"thinkingmachines/Inkling","displayName":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":524288,"defaultContextWindow":524288}},"zai-org/GLM-5":{"metadata":{"displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","lifecycle":"deprecated","contextWindow":202752,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-02-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5","displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"zai-org/GLM-5.1":{"metadata":{"displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"deprecated","contextWindow":202752,"maxOutputTokens":131072,"knowledgeCutoff":"2025-11","structuredOutput":true,"lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.1","displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752,"knowledgeCutoff":"2025-11"}},"zai-org/GLM-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":512000,"maxOutputTokens":164000,"structuredOutput":true,"lastUpdated":"2026-06-16","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":512000,"defaultContextWindow":512000}},"zai-org/GLM-5.3":{"metadata":{"displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.3","displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"zai-org/GLM-5.3-Flash":{"metadata":{"displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","lifecycle":"active","contextWindow":1048575,"maxOutputTokens":400000,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.3-Flash","displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048575,"defaultContextWindow":1048575}}}},"fireworks-ai":{"baseUrl":"https://api.fireworks.ai/inference/v1/","label":"Fireworks AI","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"fireworks","accountsPath":"/v1/accounts","publicAccount":"accounts/fireworks","query":{"filter":"supports_serverless=true","pageSize":"200"}},"fallbackModels":["accounts/fireworks/models/kimi-k2p6","accounts/fireworks/models/deepseek-v4-flash-0731","accounts/fireworks/models/deepseek-v4-flash-vision-exp","accounts/fireworks/models/deepseek-v4-pro-0813","accounts/fireworks/models/deepseek-v4p1-flash","accounts/fireworks/models/glm-5p2","accounts/fireworks/models/glm-5p3","accounts/fireworks/models/glm-5p3-flash","accounts/fireworks/models/gpt-oss-120b","accounts/fireworks/models/inkling","accounts/fireworks/models/kimi-k2p7-code","accounts/fireworks/models/kimi-k3","accounts/fireworks/models/minimax-m3","accounts/fireworks/models/mistral-large-3-fp8","accounts/fireworks/models/muse-glimmer-30b","accounts/fireworks/models/nemotron-3-ultra-nvfp4","accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b","accounts/fireworks/models/qwen3p7-plus","accounts/fireworks/models/qwen3p8-2p4t-a95b","accounts/fireworks/models/qwen3p8-max","accounts/fireworks/routers/glm-5p2-fast","accounts/fireworks/routers/glm-5p3-fast","accounts/fireworks/routers/kimi-k3-fast"],"models":{"accounts/fireworks/models/deepseek-v4-flash-0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/deepseek-v4-flash-0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"accounts/fireworks/models/deepseek-v4-flash-vision-exp":{"metadata":{"displayName":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/deepseek-v4-flash-vision-exp","displayName":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"accounts/fireworks/models/deepseek-v4-pro-0813":{"metadata":{"displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/deepseek-v4-pro-0813","displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"accounts/fireworks/models/deepseek-v4p1-flash":{"metadata":{"displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/deepseek-v4p1-flash","displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"accounts/fireworks/models/glm-5p2":{"metadata":{"displayName":"GLM 5.2","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":1048575,"maxOutputTokens":131072,"lastUpdated":"2026-06-16","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/glm-5p2","displayName":"GLM 5.2","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1048575,"defaultContextWindow":1048575}},"accounts/fireworks/models/glm-5p3":{"metadata":{"displayName":"GLM 5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1048573,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-09-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/glm-5p3","displayName":"GLM 5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1048573,"defaultContextWindow":1048573}},"accounts/fireworks/models/glm-5p3-flash":{"metadata":{"displayName":"GLM 5.3 Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","lifecycle":"active","contextWindow":1048573,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-09-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/glm-5p3-flash","displayName":"GLM 5.3 Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048573,"defaultContextWindow":1048573}},"accounts/fireworks/models/gpt-oss-120b":{"metadata":{"displayName":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"lastUpdated":"2026-06-16","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/gpt-oss-120b","displayName":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"accounts/fireworks/models/inkling":{"metadata":{"displayName":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"lastUpdated":"2026-07-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/inkling","displayName":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}},"accounts/fireworks/models/kimi-k2p6":{"metadata":{"displayName":"Kimi K2.6","description":"Kimi reasoning model for long-horizon research, planning, and tool use","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"lastUpdated":"2026-04-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/kimi-k2p6","displayName":"Kimi K2.6","description":"Kimi reasoning model for long-horizon research, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"accounts/fireworks/models/kimi-k2p7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Kimi coding model for software agents, refactors, and repository reasoning","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"lastUpdated":"2026-06-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/kimi-k2p7-code","displayName":"Kimi K2.7 Code","description":"Kimi coding model for software agents, refactors, and repository reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"accounts/fireworks/models/kimi-k3":{"metadata":{"displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/kimi-k3","displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"accounts/fireworks/models/minimax-m3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","lifecycle":"active","contextWindow":512000,"maxOutputTokens":512000,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/minimax-m3","displayName":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":512000,"defaultContextWindow":512000}},"accounts/fireworks/models/mistral-large-3-fp8":{"metadata":{"displayName":"Mistral Large 3 675B Instruct 2512","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2024-11","lastUpdated":"2025-12-02","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/mistral-large-3-fp8","displayName":"Mistral Large 3 675B Instruct 2512","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-11"}},"accounts/fireworks/models/muse-glimmer-30b":{"metadata":{"displayName":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2026-01-04","structuredOutput":true,"lastUpdated":"2026-08-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/muse-glimmer-30b","displayName":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2026-01-04"}},"accounts/fireworks/models/nemotron-3-ultra-nvfp4":{"metadata":{"displayName":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","lifecycle":"active","contextWindow":262144,"maxOutputTokens":128000,"lastUpdated":"2026-06-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/nemotron-3-ultra-nvfp4","displayName":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b":{"metadata":{"displayName":"Nemotron 3.5 Lightning 30B A3B","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-08-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b","displayName":"Nemotron 3.5 Lightning 30B A3B","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"accounts/fireworks/models/qwen3p7-plus":{"metadata":{"displayName":"Qwen 3.7 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/qwen3p7-plus","displayName":"Qwen 3.7 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":262144,"defaultContextWindow":262144}},"accounts/fireworks/models/qwen3p8-2p4t-a95b":{"metadata":{"displayName":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/qwen3p8-2p4t-a95b","displayName":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","xhigh"],"contextWindow":262144,"defaultContextWindow":262144}},"accounts/fireworks/models/qwen3p8-max":{"metadata":{"displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"lastUpdated":"2026-08-03","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"accounts/fireworks/models/qwen3p8-max","displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"accounts/fireworks/routers/glm-5p2-fast":{"metadata":{"displayName":"GLM 5.2 Fast","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":1048575,"maxOutputTokens":131072,"lastUpdated":"2026-06-26","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"accounts/fireworks/routers/glm-5p2-fast","displayName":"GLM 5.2 Fast","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1048575,"defaultContextWindow":1048575}},"accounts/fireworks/routers/glm-5p3-fast":{"metadata":{"displayName":"GLM 5.3 Fast","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1048572,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-09-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"accounts/fireworks/routers/glm-5p3-fast","displayName":"GLM 5.3 Fast","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1048572,"defaultContextWindow":1048572}},"accounts/fireworks/routers/kimi-k3-fast":{"metadata":{"displayName":"Kimi K3 Fast","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"accounts/fireworks/routers/kimi-k3-fast","displayName":"Kimi K3 Fast","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}}}},"nvidia":{"baseUrl":"https://integrate.api.nvidia.com/v1","label":"NVIDIA","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["nvidia/nemotron-3-super-120b-a12b","abacusai/dracarys-llama-3.1-70b-instruct","bytedance/seed-oss-36b-instruct","deepseek-ai/deepseek-v4-flash","deepseek-ai/deepseek-v4-flash-0731","deepseek-ai/deepseek-v4-pro","deepseek-ai/deepseek-v4-pro-0813","google/gemma-2-2b-it","google/gemma-3-12b-it","google/gemma-3-4b-it","google/gemma-3n-e2b-it","google/gemma-3n-e4b-it","google/gemma-4-31b-it","meta/llama-3.1-70b-instruct","meta/llama-3.1-8b-instruct","meta/llama-3.2-11b-vision-instruct","meta/llama-3.2-1b-instruct","meta/llama-3.2-90b-vision-instruct","meta/llama-3.3-70b-instruct","meta/llama-4-maverick-17b-128e-instruct","meta/muse-glimmer-30b","microsoft/phi-4-mini-instruct","minimaxai/minimax-m2.7","minimaxai/minimax-m3","mistralai/ministral-14b-instruct-2512","mistralai/mistral-7b-instruct-v0.3","mistralai/mistral-large-3-675b-instruct-2512","mistralai/mistral-medium-3.5-128b","mistralai/mistral-nemotron","mistralai/mistral-small-4-119b-2603","mistralai/mixtral-8x22b-instruct","mistralai/mixtral-8x7b-instruct","moonshotai/kimi-k3","nvidia/cosmos-reason2-8b","nvidia/llama-3.1-nemotron-70b-instruct","nvidia/llama-3.1-nemotron-nano-8b-v1","nvidia/llama-3.1-nemotron-nano-vl-8b-v1","nvidia/llama-3.1-nemotron-ultra-253b-v1","nvidia/llama-3.3-nemotron-super-49b-v1","nvidia/llama-3.3-nemotron-super-49b-v1.5","nvidia/nemotron-3-nano-30b-a3b","nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","nvidia/nemotron-3-ultra-550b-a55b","nvidia/nemotron-3.5-lightning-30b-a3b","nvidia/nemotron-mini-4b-instruct","nvidia/nemotron-nano-12b-v2-vl","nvidia/nemotron-voicechat","nvidia/nvidia-nemotron-nano-9b-v2","openai/gpt-oss-120b","openai/gpt-oss-20b","poolside/laguna-xs-2.1","qwen/qwen2.5-coder-32b-instruct","qwen/qwen3-coder-480b-a35b-instruct","qwen/qwen3-next-80b-a3b-instruct","qwen/qwen3.5-122b-a10b","qwen/qwen3.5-397b-a17b","sarvamai/sarvam-m","stepfun-ai/step-3.5-flash","stepfun-ai/step-3.7-flash","thinkingmachines/inkling","upstage/solar-10.7b-instruct","z-ai/glm-5.2","z-ai/glm-5.3-flash"],"models":{"abacusai/dracarys-llama-3.1-70b-instruct":{"metadata":{"displayName":"dracarys-llama-3.1-70b-instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2025-05-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"abacusai/dracarys-llama-3.1-70b-instruct","displayName":"dracarys-llama-3.1-70b-instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"baai/bge-m3":{"metadata":{"displayName":"BGE M3","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1024,"lastUpdated":"2026-04-30","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"baai/bge-m3","displayName":"BGE M3","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"black-forest-labs/flux_1-kontext-dev":{"metadata":{"displayName":"FLUX.1-Kontext-dev","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":40960,"maxOutputTokens":40960,"lastUpdated":"2025-08-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["image"]}},"entry":{"id":"black-forest-labs/flux_1-kontext-dev","displayName":"FLUX.1-Kontext-dev","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":40960,"defaultContextWindow":40960}},"black-forest-labs/flux_1-schnell":{"metadata":{"displayName":"FLUX.1-schnell","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":77,"inputLimit":77,"knowledgeCutoff":"2024-07","structuredOutput":false,"lastUpdated":"2026-02-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"black-forest-labs/flux_1-schnell","displayName":"FLUX.1-schnell","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":77,"inputLimit":77,"defaultContextWindow":77,"defaultInputLimit":77,"knowledgeCutoff":"2024-07"}},"black-forest-labs/flux_2-klein-4b":{"metadata":{"displayName":"FLUX.2 Klein 4B","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":40960,"maxOutputTokens":40960,"knowledgeCutoff":"2025-06","lastUpdated":"2026-01-31","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["image","text"],"output":["image"]}},"entry":{"id":"black-forest-labs/flux_2-klein-4b","displayName":"FLUX.2 Klein 4B","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":40960,"defaultContextWindow":40960,"knowledgeCutoff":"2025-06"}},"black-forest-labs/flux.1-dev":{"metadata":{"displayName":"FLUX.1-dev","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":4096,"knowledgeCutoff":"2024-08","lastUpdated":"2025-09-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"black-forest-labs/flux.1-dev","displayName":"FLUX.1-dev","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":4096,"defaultContextWindow":4096,"knowledgeCutoff":"2024-08"}},"bytedance/seed-oss-36b-instruct":{"metadata":{"displayName":"ByteDance-Seed/Seed-OSS-36B-Instruct","description":"Tool-capable chat model for instruction following and agentic application workflows","lifecycle":"active","contextWindow":262000,"maxOutputTokens":262000,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"bytedance/seed-oss-36b-instruct","displayName":"ByteDance-Seed/Seed-OSS-36B-Instruct","description":"Tool-capable chat model for instruction following and agentic application workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262000,"defaultContextWindow":262000}},"deepseek-ai/deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":393216,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/deepseek-v4-flash","displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"deepseek-ai/deepseek-v4-flash-0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/deepseek-v4-flash-0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-ai/deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":393216,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/deepseek-v4-pro","displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"deepseek-ai/deepseek-v4-pro-0813":{"metadata":{"displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/deepseek-v4-pro-0813","displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"google/gemma-2-2b-it":{"metadata":{"displayName":"Gemma 2 2b It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"structuredOutput":true,"lastUpdated":"2024-07-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"google/gemma-2-2b-it","displayName":"Gemma 2 2b It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"google/gemma-3-12b-it":{"metadata":{"displayName":"Gemma 3 12B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"lastUpdated":"2025-03-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3-12b-it","displayName":"Gemma 3 12B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"google/gemma-3-4b-it":{"metadata":{"displayName":"Gemma 3 4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"lastUpdated":"2025-03-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3-4b-it","displayName":"Gemma 3 4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"google/gemma-3n-e2b-it":{"metadata":{"displayName":"Gemma 3n E2b It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2024-06","structuredOutput":true,"lastUpdated":"2025-06-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3n-e2b-it","displayName":"Gemma 3n E2b It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-06"}},"google/gemma-3n-e4b-it":{"metadata":{"displayName":"Gemma 3n E4b It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2024-06","structuredOutput":true,"lastUpdated":"2025-06-03","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3n-e4b-it","displayName":"Gemma 3n E4b It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-06"}},"google/gemma-4-31b-it":{"metadata":{"displayName":"Gemma-4-31B-IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":256000,"maxOutputTokens":16384,"knowledgeCutoff":"2025-01","lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"google/gemma-4-31b-it","displayName":"Gemma-4-31B-IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-01"}},"google/google-paligemma":{"metadata":{"displayName":"paligemma","description":"Gemini multimodal model for text, image, audio, video, and document tasks","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2024-08-26","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/google-paligemma","displayName":"paligemma","description":"Gemini multimodal model for text, image, audio, video, and document tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"meta/esm2-650m":{"metadata":{"displayName":"esm2-650m","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2025-03-10","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta/esm2-650m","displayName":"esm2-650m","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"meta/esmfold":{"metadata":{"displayName":"esmfold","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2025-06-12","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta/esmfold","displayName":"esmfold","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"meta/llama-3.1-70b-instruct":{"metadata":{"displayName":"Llama 3.1 70b Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"structuredOutput":true,"lastUpdated":"2024-07-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta/llama-3.1-70b-instruct","displayName":"Llama 3.1 70b Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"meta/llama-3.1-8b-instruct":{"metadata":{"displayName":"Llama 3.1 8B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":16000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-12","lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta/llama-3.1-8b-instruct","displayName":"Llama 3.1 8B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16000,"defaultContextWindow":16000,"knowledgeCutoff":"2023-12"}},"meta/llama-3.2-11b-vision-instruct":{"metadata":{"displayName":"Llama 3.2 11b Vision Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-12","structuredOutput":true,"lastUpdated":"2024-09-18","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta/llama-3.2-11b-vision-instruct","displayName":"Llama 3.2 11b Vision Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-12"}},"meta/llama-3.2-1b-instruct":{"metadata":{"displayName":"Llama 3.2 1b Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-12","structuredOutput":true,"lastUpdated":"2024-09-18","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta/llama-3.2-1b-instruct","displayName":"Llama 3.2 1b Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-12"}},"meta/llama-3.2-3b-instruct":{"metadata":{"displayName":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":32768,"maxOutputTokens":32000,"structuredOutput":true,"lastUpdated":"2024-09-18","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta/llama-3.2-3b-instruct","displayName":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"meta/llama-3.2-90b-vision-instruct":{"metadata":{"displayName":"Llama-3.2-90B-Vision-Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"knowledgeCutoff":"2023-12","lastUpdated":"2024-09-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta/llama-3.2-90b-vision-instruct","displayName":"Llama-3.2-90B-Vision-Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-12"}},"meta/llama-3.3-70b-instruct":{"metadata":{"displayName":"Llama 3.3 70b Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"structuredOutput":true,"lastUpdated":"2024-11-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta/llama-3.3-70b-instruct","displayName":"Llama 3.3 70b Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"meta/llama-4-maverick-17b-128e-instruct":{"metadata":{"displayName":"Llama 4 Maverick 17b 128e Instruct","description":"Open multimodal Llama model for strong reasoning and fast responses","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2024-02","structuredOutput":true,"lastUpdated":"2025-04-01","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta/llama-4-maverick-17b-128e-instruct","displayName":"Llama 4 Maverick 17b 128e Instruct","description":"Open multimodal Llama model for strong reasoning and fast responses","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-02"}},"meta/llama-guard-4-12b":{"metadata":{"displayName":"Llama Guard 4 12B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"lastUpdated":"2026-04-30","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta/llama-guard-4-12b","displayName":"Llama Guard 4 12B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"meta/muse-glimmer-30b":{"metadata":{"displayName":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2026-01-04","structuredOutput":true,"lastUpdated":"2026-08-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","minimal","low","medium","high","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta/muse-glimmer-30b","displayName":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","minimal","low","medium","high","max"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2026-01-04"}},"microsoft/phi-4-mini-instruct":{"metadata":{"displayName":"Phi-4-Mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-12","lastUpdated":"2025-09-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"microsoft/phi-4-mini-instruct","displayName":"Phi-4-Mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-12"}},"microsoft/phi-4-multimodal-instruct":{"metadata":{"displayName":"Phi 4 Multimodal","description":"General-purpose chat model for instruction following, writing, and analysis","lifecycle":"active","contextWindow":128000,"inputLimit":128000,"maxOutputTokens":16384,"structuredOutput":false,"lastUpdated":"2025-07-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"microsoft/phi-4-multimodal-instruct","displayName":"Phi 4 Multimodal","description":"General-purpose chat model for instruction following, writing, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"inputLimit":128000,"defaultContextWindow":128000,"defaultInputLimit":128000}},"minimaxai/minimax-m2.7":{"metadata":{"displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-04-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimaxai/minimax-m2.7","displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"minimaxai/minimax-m3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":16384,"lastUpdated":"2026-06-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"minimaxai/minimax-m3","displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"mistralai/magistral-small-2506":{"metadata":{"displayName":"Magistral Small 2506","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","lifecycle":"active","contextWindow":32768,"inputLimit":32768,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2025-09-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistralai/magistral-small-2506","displayName":"Magistral Small 2506","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"inputLimit":32768,"defaultContextWindow":32768,"defaultInputLimit":32768}},"mistralai/ministral-14b-instruct-2512":{"metadata":{"displayName":"Ministral 3 14B Instruct 2512","description":"Compact Mistral VLM for chat and instruction-based workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"lastUpdated":"2025-12-02","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistralai/ministral-14b-instruct-2512","displayName":"Ministral 3 14B Instruct 2512","description":"Compact Mistral VLM for chat and instruction-based workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"mistralai/mistral-7b-instruct-v0.3":{"metadata":{"displayName":"Mistral-7B-Instruct-v0.3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":65536,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2025-04-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistralai/mistral-7b-instruct-v0.3","displayName":"Mistral-7B-Instruct-v0.3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536}},"mistralai/mistral-large-3-675b-instruct-2512":{"metadata":{"displayName":"Mistral Large 3 675B Instruct 2512","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-12-02","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistralai/mistral-large-3-675b-instruct-2512","displayName":"Mistral Large 3 675B Instruct 2512","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"mistralai/mistral-medium-3-instruct":{"metadata":{"displayName":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":131072,"inputLimit":131072,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2025-09-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistralai/mistral-medium-3-instruct","displayName":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"inputLimit":131072,"defaultContextWindow":131072,"defaultInputLimit":131072}},"mistralai/mistral-medium-3.5-128b":{"metadata":{"displayName":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-04-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistralai/mistral-medium-3.5-128b","displayName":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","high"],"contextWindow":262144,"defaultContextWindow":262144}},"mistralai/mistral-nemotron":{"metadata":{"displayName":"mistral-nemotron","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2025-06-12","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistralai/mistral-nemotron","displayName":"mistral-nemotron","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"mistralai/mistral-small-4-119b-2603":{"metadata":{"displayName":"mistral-small-4-119b-2603","description":"Efficient Mistral model for fast chat, extraction, and production assistants","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"structuredOutput":true,"lastUpdated":"2026-03-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistralai/mistral-small-4-119b-2603","displayName":"mistral-small-4-119b-2603","description":"Efficient Mistral model for fast chat, extraction, and production assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","high"],"contextWindow":128000,"defaultContextWindow":128000}},"mistralai/mixtral-8x22b-instruct":{"metadata":{"displayName":"Mistral: Mixtral 8x22B Instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":65536,"maxOutputTokens":13108,"lastUpdated":"2024-04-17","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistralai/mixtral-8x22b-instruct","displayName":"Mistral: Mixtral 8x22B Instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536}},"mistralai/mixtral-8x7b-instruct":{"metadata":{"displayName":"Mistral: Mixtral 8x7B Instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":32768,"maxOutputTokens":16384,"lastUpdated":"2026-03-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistralai/mixtral-8x7b-instruct","displayName":"Mistral: Mixtral 8x7B Instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"moonshotai/kimi-k2-instruct-0905":{"metadata":{"displayName":"Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2024-10","lastUpdated":"2025-09-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2-instruct-0905","displayName":"Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-10"}},"moonshotai/kimi-k2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","minimal","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.6","displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","minimal","low","medium","high","xhigh","max"],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/kimi-k3":{"metadata":{"displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k3","displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"nvidia/active-speaker-detection":{"metadata":{"displayName":"Active Speaker Detection","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","lifecycle":"active","maxOutputTokens":4096,"lastUpdated":"2026-04-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["video"],"output":["text"]}},"entry":{"id":"nvidia/active-speaker-detection","displayName":"Active Speaker Detection","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"nvidia/bevformer":{"metadata":{"displayName":"bevformer","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2025-07-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["video"],"output":["text"]}},"entry":{"id":"nvidia/bevformer","displayName":"bevformer","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/cosmos-predict1-5b":{"metadata":{"displayName":"cosmos-predict1-5b","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","maxOutputTokens":4096,"lastUpdated":"2025-03-18","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","video"],"output":["video"]}},"entry":{"id":"nvidia/cosmos-predict1-5b","displayName":"cosmos-predict1-5b","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"nvidia/cosmos-reason2-8b":{"metadata":{"displayName":"Cosmos Reason2 8B","description":"Vision language model for physical-world understanding with structured reasoning on video and images","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"lastUpdated":"2025-12-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"nvidia/cosmos-reason2-8b","displayName":"Cosmos Reason2 8B","description":"Vision language model for physical-world understanding with structured reasoning on video and images","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"nvidia/cosmos-transfer1-7b":{"metadata":{"displayName":"cosmos-transfer1-7b","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","maxOutputTokens":4096,"lastUpdated":"2025-06-30","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","video"],"output":["video"]}},"entry":{"id":"nvidia/cosmos-transfer1-7b","displayName":"cosmos-transfer1-7b","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"nvidia/cosmos-transfer2_5-2b":{"metadata":{"displayName":"cosmos-transfer2.5-2b","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","maxOutputTokens":4096,"lastUpdated":"2026-02-26","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","video"],"output":["video"]}},"entry":{"id":"nvidia/cosmos-transfer2_5-2b","displayName":"cosmos-transfer2.5-2b","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"nvidia/gliner-pii":{"metadata":{"displayName":"gliner-pii","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"lastUpdated":"2026-03-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/gliner-pii","displayName":"gliner-pii","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/llama-3_2-nemoretriever-300m-embed-v1":{"metadata":{"displayName":"llama-3_2-nemoretriever-300m-embed-v1","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":32768,"maxOutputTokens":2048,"lastUpdated":"2025-07-24","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/llama-3_2-nemoretriever-300m-embed-v1","displayName":"llama-3_2-nemoretriever-300m-embed-v1","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"nvidia/llama-3.1-nemotron-70b-instruct":{"metadata":{"displayName":"Llama 3.1 Nemotron 70B Instruct","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2025-04-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/llama-3.1-nemotron-70b-instruct","displayName":"Llama 3.1 Nemotron 70B Instruct","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/llama-3.1-nemotron-nano-8b-v1":{"metadata":{"displayName":"Llama 3.1 Nemotron Nano 8B v1","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"lastUpdated":"2025-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/llama-3.1-nemotron-nano-8b-v1","displayName":"Llama 3.1 Nemotron Nano 8B v1","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"nvidia/llama-3.1-nemotron-nano-vl-8b-v1":{"metadata":{"displayName":"Llama 3.1 Nemotron Nano VL 8B v1","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","lifecycle":"active","contextWindow":32768,"maxOutputTokens":16384,"lastUpdated":"2025-04-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"nvidia/llama-3.1-nemotron-nano-vl-8b-v1","displayName":"Llama 3.1 Nemotron Nano VL 8B v1","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"nvidia/llama-3.1-nemotron-safety-guard-8b-v3":{"metadata":{"displayName":"llama-3.1-nemotron-safety-guard-8b-v3","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"lastUpdated":"2025-10-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/llama-3.1-nemotron-safety-guard-8b-v3","displayName":"llama-3.1-nemotron-safety-guard-8b-v3","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/llama-3.1-nemotron-ultra-253b-v1":{"metadata":{"displayName":"Llama 3.1 Nemotron Ultra 253B","description":"Flagship Nemotron model for high-throughput reasoning and complex agents","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"lastUpdated":"2025-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/llama-3.1-nemotron-ultra-253b-v1","displayName":"Llama 3.1 Nemotron Ultra 253B","description":"Flagship Nemotron model for high-throughput reasoning and complex agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/llama-3.3-nemotron-super-49b-v1":{"metadata":{"displayName":"Llama 3.3 Nemotron Super 49B v1","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"lastUpdated":"2025-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/llama-3.3-nemotron-super-49b-v1","displayName":"Llama 3.3 Nemotron Super 49B v1","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"nvidia/llama-3.3-nemotron-super-49b-v1.5":{"metadata":{"displayName":"Llama 3.3 Nemotron Super 49B v1.5","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"lastUpdated":"2025-07-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/llama-3.3-nemotron-super-49b-v1.5","displayName":"Llama 3.3 Nemotron Super 49B v1.5","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"nvidia/llama-nemotron-embed-vl-1b-v2":{"metadata":{"displayName":"llama-nemotron-embed-vl-1b-v2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":32768,"maxOutputTokens":2048,"lastUpdated":"2026-02-10","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"nvidia/llama-nemotron-embed-vl-1b-v2","displayName":"llama-nemotron-embed-vl-1b-v2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"nvidia/llama-nemotron-rerank-vl-1b-v2":{"metadata":{"displayName":"llama-nemotron-rerank-vl-1b-v2","description":"Reranking model for improving retrieval quality in search and recommendation systems","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"lastUpdated":"2026-03-31","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"nvidia/llama-nemotron-rerank-vl-1b-v2","displayName":"llama-nemotron-rerank-vl-1b-v2","description":"Reranking model for improving retrieval quality in search and recommendation systems","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/magpie-tts-zeroshot":{"metadata":{"displayName":"magpie-tts-zeroshot","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","maxOutputTokens":4096,"lastUpdated":"2025-06-12","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","audio"],"output":["audio"]}},"entry":{"id":"nvidia/magpie-tts-zeroshot","displayName":"magpie-tts-zeroshot","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"nvidia/nemotron-3-content-safety":{"metadata":{"displayName":"nemotron-3-content-safety","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"lastUpdated":"2026-04-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-content-safety","displayName":"nemotron-3-content-safety","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/nemotron-3-nano-30b-a3b":{"metadata":{"displayName":"nemotron-3-nano-30b-a3b","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2024-09","lastUpdated":"2024-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-nano-30b-a3b","displayName":"nemotron-3-nano-30b-a3b","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-09"}},"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning":{"metadata":{"displayName":"Nemotron 3 Nano Omni","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","lifecycle":"active","contextWindow":256000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","displayName":"Nemotron 3 Nano Omni","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"nvidia/nemotron-3-super-120b-a12b":{"metadata":{"displayName":"Nemotron 3 Super","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2024-04","lastUpdated":"2026-03-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-super-120b-a12b","displayName":"Nemotron 3 Super","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-04"}},"nvidia/nemotron-3-ultra-550b-a55b":{"metadata":{"displayName":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-06-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-ultra-550b-a55b","displayName":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"nvidia/nemotron-3.5-lightning-30b-a3b":{"metadata":{"displayName":"Nemotron 3.5 Lightning 30B A3B","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-08-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3.5-lightning-30b-a3b","displayName":"Nemotron 3.5 Lightning 30B A3B","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"nvidia/nemotron-content-safety-reasoning-4b":{"metadata":{"displayName":"nemotron-content-safety-reasoning-4b","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"lastUpdated":"2026-01-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-content-safety-reasoning-4b","displayName":"nemotron-content-safety-reasoning-4b","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/nemotron-mini-4b-instruct":{"metadata":{"displayName":"nemotron-mini-4b-instruct","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2024-08-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-mini-4b-instruct","displayName":"nemotron-mini-4b-instruct","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/nemotron-nano-12b-v2-vl":{"metadata":{"displayName":"Nemotron Nano 12B v2 VL","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"lastUpdated":"2025-10-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-nano-12b-v2-vl","displayName":"Nemotron Nano 12B v2 VL","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/nemotron-voicechat":{"metadata":{"displayName":"nemotron-voicechat","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2026-03-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","audio"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-voicechat","displayName":"nemotron-voicechat","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/nv-embed-v1":{"metadata":{"displayName":"nv-embed-v1","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":32768,"maxOutputTokens":2048,"lastUpdated":"2025-07-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nv-embed-v1","displayName":"nv-embed-v1","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"nvidia/nv-embedcode-7b-v1":{"metadata":{"displayName":"nv-embedcode-7b-v1","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","contextWindow":32768,"maxOutputTokens":2048,"lastUpdated":"2025-05-29","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nv-embedcode-7b-v1","displayName":"nv-embedcode-7b-v1","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"nvidia/nvidia-nemotron-nano-9b-v2":{"metadata":{"displayName":"nvidia-nemotron-nano-9b-v2","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2024-09","lastUpdated":"2025-08-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nvidia-nemotron-nano-9b-v2","displayName":"nvidia-nemotron-nano-9b-v2","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-09"}},"nvidia/rerank-qa-mistral-4b":{"metadata":{"displayName":"rerank-qa-mistral-4b","description":"Reranking model for improving retrieval quality in search and recommendation systems","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"lastUpdated":"2025-01-17","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/rerank-qa-mistral-4b","displayName":"rerank-qa-mistral-4b","description":"Reranking model for improving retrieval quality in search and recommendation systems","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/riva-translate-4b-instruct-v1.1":{"metadata":{"displayName":"riva-translate-4b-instruct-v1_1","description":"Translation model for multilingual conversion, localization, and cross-language workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"lastUpdated":"2025-12-12","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/riva-translate-4b-instruct-v1.1","displayName":"riva-translate-4b-instruct-v1_1","description":"Translation model for multilingual conversion, localization, and cross-language workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/sparsedrive":{"metadata":{"displayName":"sparsedrive","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2025-07-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["video"],"output":["text"]}},"entry":{"id":"nvidia/sparsedrive","displayName":"sparsedrive","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/streampetr":{"metadata":{"displayName":"streampetr","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2025-11-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["video"],"output":["text"]}},"entry":{"id":"nvidia/streampetr","displayName":"streampetr","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/studiovoice":{"metadata":{"displayName":"studiovoice","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2025-06-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/studiovoice","displayName":"studiovoice","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/synthetic-video-detector":{"metadata":{"displayName":"synthetic-video-detector","description":"Video model for prompt-guided generation, editing, and motion workflows","lifecycle":"active","maxOutputTokens":4096,"lastUpdated":"2026-04-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["video"],"output":["text"]}},"entry":{"id":"nvidia/synthetic-video-detector","displayName":"synthetic-video-detector","description":"Video model for prompt-guided generation, editing, and motion workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"nvidia/usdcode":{"metadata":{"displayName":"usdcode","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"lastUpdated":"2026-01-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/usdcode","displayName":"usdcode","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/usdvalidate":{"metadata":{"displayName":"usdvalidate","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","maxOutputTokens":4096,"lastUpdated":"2025-01-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/usdvalidate","displayName":"usdvalidate","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"openai/gpt-oss-120b":{"metadata":{"displayName":"GPT-OSS-120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"knowledgeCutoff":"2025-08","structuredOutput":true,"lastUpdated":"2025-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-120b","displayName":"GPT-OSS-120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-08"}},"openai/gpt-oss-20b":{"metadata":{"displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-20b","displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"openai/whisper-large-v3":{"metadata":{"displayName":"Whisper Large v3","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","maxOutputTokens":4096,"knowledgeCutoff":"2023-09","lastUpdated":"2025-09-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"openai/whisper-large-v3","displayName":"Whisper Large v3","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"knowledgeCutoff":"2023-09"}},"poolside/laguna-xs-2.1":{"metadata":{"displayName":"Laguna XS 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"structuredOutput":false,"lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"poolside/laguna-xs-2.1","displayName":"Laguna XS 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen-image":{"metadata":{"displayName":"Qwen Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","structuredOutput":false,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["image"]}},"entry":{"id":"qwen/qwen-image","displayName":"Qwen Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"qwen/qwen-image-edit":{"metadata":{"displayName":"Qwen Image Edit","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","structuredOutput":false,"lastUpdated":"2025-08-19","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["image"]}},"entry":{"id":"qwen/qwen-image-edit","displayName":"Qwen Image Edit","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"qwen/qwen2.5-coder-32b-instruct":{"metadata":{"displayName":"Qwen2.5 Coder 32b Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"structuredOutput":true,"lastUpdated":"2024-11-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen2.5-coder-32b-instruct","displayName":"Qwen2.5 Coder 32b Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"qwen/qwen3-coder-480b-a35b-instruct":{"metadata":{"displayName":"Qwen3 Coder 480B A35B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":66536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-coder-480b-a35b-instruct","displayName":"Qwen3 Coder 480B A35B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen/qwen3-next-80b-a3b-instruct":{"metadata":{"displayName":"Qwen3-Next-80B-A3B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"knowledgeCutoff":"2024-12","lastUpdated":"2025-09-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-next-80b-a3b-instruct","displayName":"Qwen3-Next-80B-A3B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-12"}},"qwen/qwen3.5-122b-a10b":{"metadata":{"displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-122b-a10b","displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen3.5-397b-a17b":{"metadata":{"displayName":"Qwen3.5-397B-A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":8192,"knowledgeCutoff":"2026-01","structuredOutput":true,"lastUpdated":"2026-02-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-397b-a17b","displayName":"Qwen3.5-397B-A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2026-01"}},"sarvamai/sarvam-m":{"metadata":{"displayName":"sarvam-m","description":"Efficient Indian-language reasoning model for chat, coding, and multilingual work","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2025-07-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"sarvamai/sarvam-m","displayName":"sarvam-m","description":"Efficient Indian-language reasoning model for chat, coding, and multilingual work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"stepfun-ai/step-3.5-flash":{"metadata":{"displayName":"Step 3.5 Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":16384,"lastUpdated":"2026-02-02","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"stepfun-ai/step-3.5-flash","displayName":"Step 3.5 Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000}},"stepfun-ai/step-3.7-flash":{"metadata":{"displayName":"Step 3.7 Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":16384,"lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"stepfun-ai/step-3.7-flash","displayName":"Step 3.7 Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh","max"],"contextWindow":256000,"defaultContextWindow":256000}},"thinkingmachines/inkling":{"metadata":{"displayName":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":16384,"lastUpdated":"2026-07-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio"],"output":["text"]}},"entry":{"id":"thinkingmachines/inkling","displayName":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}},"upstage/solar-10.7b-instruct":{"metadata":{"displayName":"solar-10.7b-instruct","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"lastUpdated":"2025-04-10","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"upstage/solar-10.7b-instruct","displayName":"solar-10.7b-instruct","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"z-ai/glm-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"z-ai/glm-5.3-flash":{"metadata":{"displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"z-ai/glm-5.3-flash","displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}}}},"tencent-tokenhub":{"baseUrl":"https://tokenhub.tencentmaas.com/v1","label":"Tencent TokenHub","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["hy3","hy3-preview","hy4-preview"],"models":{"hy3":{"metadata":{"displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":256000,"inputLimit":192000,"maxOutputTokens":128000,"lastUpdated":"2026-07-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hy3","displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high"],"contextWindow":256000,"inputLimit":192000,"defaultContextWindow":256000,"defaultInputLimit":192000}},"hy3-preview":{"metadata":{"displayName":"Hy3 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":64000,"lastUpdated":"2026-04-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hy3-preview","displayName":"Hy3 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000}},"hy4-preview":{"metadata":{"displayName":"Hy4 preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":64000,"lastUpdated":"2026-08-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"hy4-preview","displayName":"Hy4 preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","high"],"contextWindow":1024000,"defaultContextWindow":1024000}}}},"stepfun":{"baseUrl":"https://api.stepfun.com/v1","label":"StepFun (China)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["step-3.7-flash","step-3.5-flash-2603","step-3.5-flash","step-1-32k","step-2-16k"],"models":{"step-1-32k":{"metadata":{"displayName":"Step 1 (32K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":32768,"inputLimit":32768,"maxOutputTokens":32768,"knowledgeCutoff":"2024-06","lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-1-32k","displayName":"Step 1 (32K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"inputLimit":32768,"defaultContextWindow":32768,"defaultInputLimit":32768,"knowledgeCutoff":"2024-06"}},"step-2-16k":{"metadata":{"displayName":"Step 2 (16K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":16384,"inputLimit":16384,"maxOutputTokens":8192,"knowledgeCutoff":"2024-06","lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-2-16k","displayName":"Step 2 (16K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16384,"inputLimit":16384,"defaultContextWindow":16384,"defaultInputLimit":16384,"knowledgeCutoff":"2024-06"}},"step-3.5-flash":{"metadata":{"displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-06-15","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-3.5-flash","displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2025-01"}},"step-3.5-flash-2603":{"metadata":{"displayName":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-04-02","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-3.5-flash-2603","displayName":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2025-01"}},"step-3.7-flash":{"metadata":{"displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2026-03-01","lastUpdated":"2026-06-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"step-3.7-flash","displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2026-03-01"}},"step-tts-2":{"metadata":{"displayName":"Step TTS 2","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"step-tts-2","displayName":"Step TTS 2","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"stepaudio-2.5-asr":{"metadata":{"displayName":"StepAudio 2.5 ASR","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"stepaudio-2.5-asr","displayName":"StepAudio 2.5 ASR","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"stepaudio-2.5-tts":{"metadata":{"displayName":"StepAudio 2.5 TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"stepaudio-2.5-tts","displayName":"StepAudio 2.5 TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}}}},"stepfun-step-plan":{"baseUrl":"https://api.stepfun.com/step_plan/v1","label":"StepFun Step Plan (China)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["step-3.7-flash","step-3.5-flash-2603","step-3.5-flash","step-router-v1"],"models":{"step-3.5-flash":{"metadata":{"displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-3.5-flash","displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2025-01"}},"step-3.5-flash-2603":{"metadata":{"displayName":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-04-02","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-3.5-flash-2603","displayName":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2025-01"}},"step-3.7-flash":{"metadata":{"displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2026-03-01","lastUpdated":"2026-05-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"step-3.7-flash","displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2026-03-01"}},"step-router-v1":{"metadata":{"displayName":"Step Router v1","description":"StepFun routing model that dispatches requests to the appropriate Step model.","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-05-29","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-router-v1","displayName":"Step Router v1","description":"StepFun routing model that dispatches requests to the appropriate Step model.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2025-01"}}}},"stepfun-ai-step-plan":{"baseUrl":"https://api.stepfun.ai/step_plan/v1","label":"StepFun Step Plan (Global)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["step-3.7-flash","step-3.5-flash-2603","step-3.5-flash"],"models":{"step-3.5-flash":{"metadata":{"displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-3.5-flash","displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2025-01"}},"step-3.5-flash-2603":{"metadata":{"displayName":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-04-02","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-3.5-flash-2603","displayName":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2025-01"}},"step-3.7-flash":{"metadata":{"displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2026-03-01","lastUpdated":"2026-05-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"step-3.7-flash","displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2026-03-01"}}}},"stepfun-ai":{"baseUrl":"https://api.stepfun.ai/v1","label":"StepFun (Global)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["step-3.7-flash","step-3.5-flash-2603","step-3.5-flash"],"models":{"step-1-32k":{"metadata":{"displayName":"Step 1 (32K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":32768,"inputLimit":32768,"maxOutputTokens":32768,"knowledgeCutoff":"2024-06","lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-1-32k","displayName":"Step 1 (32K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"inputLimit":32768,"defaultContextWindow":32768,"defaultInputLimit":32768,"knowledgeCutoff":"2024-06"}},"step-2-16k":{"metadata":{"displayName":"Step 2 (16K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":16384,"inputLimit":16384,"maxOutputTokens":8192,"knowledgeCutoff":"2024-06","lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-2-16k","displayName":"Step 2 (16K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16384,"inputLimit":16384,"defaultContextWindow":16384,"defaultInputLimit":16384,"knowledgeCutoff":"2024-06"}},"step-3.5-flash":{"metadata":{"displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-06-15","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-3.5-flash","displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2025-01"}},"step-3.5-flash-2603":{"metadata":{"displayName":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2025-01","lastUpdated":"2026-04-02","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"step-3.5-flash-2603","displayName":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2025-01"}},"step-3.7-flash":{"metadata":{"displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","lifecycle":"active","contextWindow":256000,"inputLimit":256000,"maxOutputTokens":256000,"knowledgeCutoff":"2026-03-01","lastUpdated":"2026-06-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"step-3.7-flash","displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"inputLimit":256000,"defaultContextWindow":256000,"defaultInputLimit":256000,"knowledgeCutoff":"2026-03-01"}},"step-tts-2":{"metadata":{"displayName":"Step TTS 2","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"step-tts-2","displayName":"Step TTS 2","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"stepaudio-2.5-asr":{"metadata":{"displayName":"StepAudio 2.5 ASR","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"stepaudio-2.5-asr","displayName":"StepAudio 2.5 ASR","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"stepaudio-2.5-tts":{"metadata":{"displayName":"StepAudio 2.5 TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"stepaudio-2.5-tts","displayName":"StepAudio 2.5 TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}}}},"volcengine-ark":{"baseUrl":"https://ark.cn-beijing.volces.com/api/v3","label":"Volcengine Ark (China)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":false,"modelDiscovery":{"kind":"fallback","reason":"Ark model discovery is a control-plane API that requires AK/SK signing; inference API keys cannot call it"},"fallbackModels":["doubao-seed-2-0-pro-260215"],"models":{"doubao-seed-2-0-pro-260215":{"metadata":{"displayName":"Doubao Seed 2.0 Pro","lifecycle":"active","capabilities":{"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"],"toggle":true,"offBehavior":"volcengine-thinking-disabled"}},"entry":{"id":"doubao-seed-2-0-pro-260215","displayName":"Doubao Seed 2.0 Pro","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","minimal","low","medium","high"]}}}},"deepinfra":{"baseUrl":"https://api.deepinfra.com/v1/openai","label":"Deep Infra","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol","path":"/v1/models"},"fallbackModels":["moonshotai/Kimi-K2.7-Code","moonshotai/Kimi-K2.6","ByteDance/Seed-2.0-code","ByteDance/Seed-2.0-mini","ByteDance/Seed-2.0-pro","deepseek-ai/DeepSeek-R1-0528","deepseek-ai/DeepSeek-V3","deepseek-ai/DeepSeek-V3-0324","deepseek-ai/DeepSeek-V3.1","deepseek-ai/DeepSeek-V3.2","deepseek-ai/DeepSeek-V4-Flash","deepseek-ai/DeepSeek-V4-Flash-0731","deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","deepseek-ai/DeepSeek-V4-Pro","deepseek-ai/DeepSeek-V4-Pro-0813","deepseek-ai/DeepSeek-V4.1-Flash","google/gemma-3-12b-it","google/gemma-3-27b-it","google/gemma-3-4b-it","google/gemma-4-26B-A4B-it","google/gemma-4-31B-it","google/gemma-4-E4B-it","meta-llama/Llama-3.3-70B-Instruct-Turbo","meta-llama/Llama-4-Scout-17B-16E-Instruct","MiniMaxAI/MiniMax-M3","moonshotai/Kimi-K3","nvidia/Nemotron-3-Nano-30B-A3B","openai/gpt-oss-120b","openai/gpt-oss-20b","Qwen/Qwen3-235B-A22B-Instruct-2507","Qwen/Qwen3-30B-A3B","Qwen/Qwen3-32B","Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","Qwen/Qwen3-Max","Qwen/Qwen3-Next-80B-A3B-Instruct","Qwen/Qwen3-VL-235B-A22B-Instruct","Qwen/Qwen3.5-122B-A10B","Qwen/Qwen3.5-27B","Qwen/Qwen3.5-35B-A3B","Qwen/Qwen3.5-397B-A17B","Qwen/Qwen3.5-9B","Qwen/Qwen3.6-27B","Qwen/Qwen3.6-35B-A3B","Qwen/Qwen3.7-Max","Qwen/Qwen3.8-2.4T-A95B","Qwen/Qwen3.8-27B","Qwen/Qwen3.8-Flash","Qwen/Qwen3.8-Max","stepfun-ai/Step-3.7-Flash","tencent/Hy3","thinkingmachines/Inkling","thinkingmachines/Inkling-Small","XiaomiMiMo/MiMo-V2.5","XiaomiMiMo/MiMo-V2.5-Pro","zai-org/GLM-4.6","zai-org/GLM-4.7","zai-org/GLM-5.1","zai-org/GLM-5.2","zai-org/GLM-5.3","zai-org/GLM-5.3-Flash"],"models":{"ByteDance/Seed-2.0-code":{"metadata":{"displayName":"Seed 2.0 Code","description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","lifecycle":"active","contextWindow":256000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-02-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"ByteDance/Seed-2.0-code","displayName":"Seed 2.0 Code","description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000}},"ByteDance/Seed-2.0-mini":{"metadata":{"displayName":"Seed 2.0 Mini","description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":32000,"structuredOutput":true,"lastUpdated":"2026-02-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"ByteDance/Seed-2.0-mini","displayName":"Seed 2.0 Mini","description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"ByteDance/Seed-2.0-pro":{"metadata":{"displayName":"Seed 2.0 Pro","description":"Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-02-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"ByteDance/Seed-2.0-pro","displayName":"Seed 2.0 Pro","description":"Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"deepseek-ai/DeepSeek-R1-0528":{"metadata":{"displayName":"DeepSeek-R1-0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","lifecycle":"active","contextWindow":163840,"maxOutputTokens":64000,"knowledgeCutoff":"2024-07","structuredOutput":true,"lastUpdated":"2025-05-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-R1-0528","displayName":"DeepSeek-R1-0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2024-07"}},"deepseek-ai/DeepSeek-V3":{"metadata":{"displayName":"DeepSeek-V3","description":"Open DeepSeek MoE chat model for coding, math, and general reasoning","lifecycle":"active","contextWindow":163840,"maxOutputTokens":8192,"structuredOutput":true,"lastUpdated":"2024-12-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3","displayName":"DeepSeek-V3","description":"Open DeepSeek MoE chat model for coding, math, and general reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840}},"deepseek-ai/DeepSeek-V3-0324":{"metadata":{"displayName":"DeepSeek V3 0324","description":"March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding","lifecycle":"active","contextWindow":163840,"maxOutputTokens":163840,"structuredOutput":true,"lastUpdated":"2025-03-24","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3-0324","displayName":"DeepSeek V3 0324","description":"March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840}},"deepseek-ai/DeepSeek-V3.1":{"metadata":{"displayName":"DeepSeek-V3.1","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes","lifecycle":"active","contextWindow":163840,"maxOutputTokens":8192,"structuredOutput":true,"lastUpdated":"2025-08-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3.1","displayName":"DeepSeek-V3.1","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840}},"deepseek-ai/DeepSeek-V3.2":{"metadata":{"displayName":"DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":64000,"knowledgeCutoff":"2024-12","structuredOutput":true,"lastUpdated":"2025-12-02","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V3.2","displayName":"DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2024-12"}},"deepseek-ai/DeepSeek-V4-Flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":16384,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Flash","displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"deepseek-ai/DeepSeek-V4-Flash-0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp":{"metadata":{"displayName":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","high","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","displayName":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"deepseek-ai/DeepSeek-V4-Pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":16384,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Pro","displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"deepseek-ai/DeepSeek-V4-Pro-0813":{"metadata":{"displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"deepseek-ai/DeepSeek-V4.1-Flash":{"metadata":{"displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","high","xhigh","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-ai/DeepSeek-V4.1-Flash","displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","high","xhigh","max"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"google/gemma-3-12b-it":{"metadata":{"displayName":"Gemma 3 12B IT","description":"Open multimodal Gemma instruction model for multilingual text generation and image understanding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2024-08","structuredOutput":true,"lastUpdated":"2025-03-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3-12b-it","displayName":"Gemma 3 12B IT","description":"Open multimodal Gemma instruction model for multilingual text generation and image understanding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-08"}},"google/gemma-3-27b-it":{"metadata":{"displayName":"Gemma 3 27B IT","description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2024-08","structuredOutput":true,"lastUpdated":"2025-03-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3-27b-it","displayName":"Gemma 3 27B IT","description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-08"}},"google/gemma-3-4b-it":{"metadata":{"displayName":"Gemma 3 4B IT","description":"Open multimodal Gemma instruction model for efficient text generation and image understanding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2024-08","structuredOutput":true,"lastUpdated":"2025-03-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3-4b-it","displayName":"Gemma 3 4B IT","description":"Open multimodal Gemma instruction model for efficient text generation and image understanding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-08"}},"google/gemma-4-26B-A4B-it":{"metadata":{"displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-4-26B-A4B-it","displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"google/gemma-4-31B-it":{"metadata":{"displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"google/gemma-4-31B-it","displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"google/gemma-4-E4B-it":{"metadata":{"displayName":"Gemma 4 E4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio"],"output":["text"]}},"entry":{"id":"google/gemma-4-E4B-it","displayName":"Gemma 4 E4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"meta-llama/Llama-3.3-70B-Instruct-Turbo":{"metadata":{"displayName":"Llama 3.3 70B Turbo","description":"Compact Llama instruction model for fast chat and local deployment","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2024-12-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","displayName":"Llama 3.3 70B Turbo","description":"Compact Llama instruction model for fast chat and local deployment","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8":{"metadata":{"displayName":"Llama 4 Maverick 17B FP8","description":"Open multimodal Llama model for strong reasoning and fast responses","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-04-05","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","displayName":"Llama 4 Maverick 17B FP8","description":"Open multimodal Llama model for strong reasoning and fast responses","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}},"meta-llama/Llama-4-Scout-17B-16E-Instruct":{"metadata":{"displayName":"Llama 4 Scout 17B","description":"Open multimodal Llama model for long-context analysis and efficient agents","lifecycle":"active","contextWindow":327680,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-04-05","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","displayName":"Llama 4 Scout 17B","description":"Open multimodal Llama model for long-context analysis and efficient agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":327680,"defaultContextWindow":327680}},"MiniMaxAI/MiniMax-M2.5":{"metadata":{"displayName":"MiniMax M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"deprecated","contextWindow":196608,"maxOutputTokens":131072,"knowledgeCutoff":"2025-06","lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M2.5","displayName":"MiniMax M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":196608,"defaultContextWindow":196608,"knowledgeCutoff":"2025-06"}},"MiniMaxAI/MiniMax-M2.7":{"metadata":{"displayName":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","lifecycle":"deprecated","contextWindow":196608,"maxOutputTokens":131072,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M2.7","displayName":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":196608,"defaultContextWindow":196608}},"MiniMaxAI/MiniMax-M3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","lifecycle":"active","contextWindow":524288,"maxOutputTokens":512000,"structuredOutput":true,"lastUpdated":"2026-06-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"MiniMaxAI/MiniMax-M3","displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":524288,"defaultContextWindow":524288}},"moonshotai/Kimi-K2.5":{"metadata":{"displayName":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2.5","displayName":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/Kimi-K2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2.6","displayName":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-04"}},"moonshotai/Kimi-K2.7-Code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K2.7-Code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/Kimi-K3":{"metadata":{"displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"moonshotai/Kimi-K3","displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"nvidia/Llama-3.3-Nemotron-Super-49B-v1.5":{"metadata":{"displayName":"Llama 3.3 Nemotron Super 49B v1.5","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"deprecated","contextWindow":131072,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2025-07-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/Llama-3.3-Nemotron-Super-49B-v1.5","displayName":"Llama 3.3 Nemotron Super 49B v1.5","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"nvidia/Nemotron-3-Nano-30B-A3B":{"metadata":{"displayName":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"lastUpdated":"2025-12-15","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/Nemotron-3-Nano-30B-A3B","displayName":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning":{"metadata":{"displayName":"Nemotron 3 Nano Omni 30B A3B Reasoning","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","lifecycle":"deprecated","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning","displayName":"Nemotron 3 Nano Omni 30B A3B Reasoning","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"openai/gpt-oss-120b":{"metadata":{"displayName":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-120b","displayName":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"openai/gpt-oss-20b":{"metadata":{"displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-20b","displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"Qwen/Qwen3-235B-A22B-Instruct-2507":{"metadata":{"displayName":"Qwen3 235B-A22B Instruct 2507","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-07-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","displayName":"Qwen3 235B-A22B Instruct 2507","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3-30B-A3B":{"metadata":{"displayName":"Qwen3 30B A3B","description":"Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning","lifecycle":"active","contextWindow":40960,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-04-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-30B-A3B","displayName":"Qwen3 30B A3B","description":"Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":40960,"defaultContextWindow":40960}},"Qwen/Qwen3-32B":{"metadata":{"displayName":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","lifecycle":"active","contextWindow":40960,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-32B","displayName":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":40960,"defaultContextWindow":40960,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo":{"metadata":{"displayName":"Qwen3 Coder 480B A35B Instruct Turbo","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":66536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","displayName":"Qwen3 Coder 480B A35B Instruct Turbo","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-Max":{"metadata":{"displayName":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","lifecycle":"active","contextWindow":256000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-09-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Max","displayName":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-Next-80B-A3B-Instruct":{"metadata":{"displayName":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-Next-80B-A3B-Instruct","displayName":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"Qwen/Qwen3-VL-235B-A22B-Instruct":{"metadata":{"displayName":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-09-23","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3-VL-235B-A22B-Instruct","displayName":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-03-31"}},"Qwen/Qwen3.5-122B-A10B":{"metadata":{"displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-122B-A10B","displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.5-27B":{"metadata":{"displayName":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-27B","displayName":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.5-35B-A3B":{"metadata":{"displayName":"Qwen 3.5 35B A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":81920,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-35B-A3B","displayName":"Qwen 3.5 35B A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"Qwen/Qwen3.5-397B-A17B":{"metadata":{"displayName":"Qwen 3.5 397B A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":81920,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-397B-A17B","displayName":"Qwen 3.5 397B A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"Qwen/Qwen3.5-9B":{"metadata":{"displayName":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.5-9B","displayName":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.6-27B":{"metadata":{"displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.6-27B","displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.6-35B-A3B":{"metadata":{"displayName":"Qwen3.6 35B A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":81920,"structuredOutput":true,"lastUpdated":"2026-04-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.6-35B-A3B","displayName":"Qwen3.6 35B A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.7-Max":{"metadata":{"displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","lifecycle":"active","contextWindow":256000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.7-Max","displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"Qwen/Qwen3.8-2.4T-A95B":{"metadata":{"displayName":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.8-2.4T-A95B","displayName":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","xhigh"],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.8-27B":{"metadata":{"displayName":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.8-27B","displayName":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":262144,"defaultContextWindow":262144}},"Qwen/Qwen3.8-Flash":{"metadata":{"displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.8-Flash","displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"Qwen/Qwen3.8-Max":{"metadata":{"displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-03","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"Qwen/Qwen3.8-Max","displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"stepfun-ai/Step-3.7-Flash":{"metadata":{"displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","lifecycle":"active","contextWindow":262144,"maxOutputTokens":256000,"knowledgeCutoff":"2026-03-01","lastUpdated":"2026-05-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"stepfun-ai/Step-3.7-Flash","displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2026-03-01"}},"tencent/Hy3":{"metadata":{"displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":262144,"inputLimit":192000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-07-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/Hy3","displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"inputLimit":192000,"defaultContextWindow":262144,"defaultInputLimit":192000}},"thinkingmachines/Inkling":{"metadata":{"displayName":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","lifecycle":"active","contextWindow":524288,"maxOutputTokens":1048576,"lastUpdated":"2026-07-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio"],"output":["text"]}},"entry":{"id":"thinkingmachines/Inkling","displayName":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":524288,"defaultContextWindow":524288}},"thinkingmachines/Inkling-Small":{"metadata":{"displayName":"Inkling Small","description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","lifecycle":"active","contextWindow":524288,"maxOutputTokens":1048576,"structuredOutput":true,"lastUpdated":"2026-07-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio"],"output":["text"]}},"entry":{"id":"thinkingmachines/Inkling-Small","displayName":"Inkling Small","description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":524288,"defaultContextWindow":524288}},"XiaomiMiMo/MiMo-V2.5":{"metadata":{"displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"knowledgeCutoff":"2024-12","structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]}},"entry":{"id":"XiaomiMiMo/MiMo-V2.5","displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-12"}},"XiaomiMiMo/MiMo-V2.5-Pro":{"metadata":{"displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":16384,"knowledgeCutoff":"2024-12","structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","audio"],"output":["text"]}},"entry":{"id":"XiaomiMiMo/MiMo-V2.5-Pro","displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-12"}},"zai-org/GLM-4.6":{"metadata":{"displayName":"GLM-4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-09-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-4.6","displayName":"GLM-4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752,"knowledgeCutoff":"2025-04"}},"zai-org/GLM-4.7":{"metadata":{"displayName":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-12-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-4.7","displayName":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752,"knowledgeCutoff":"2025-04"}},"zai-org/GLM-4.7-Flash":{"metadata":{"displayName":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"deprecated","contextWindow":202752,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-4.7-Flash","displayName":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752,"knowledgeCutoff":"2025-04"}},"zai-org/GLM-5":{"metadata":{"displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"deprecated","contextWindow":202752,"maxOutputTokens":16384,"knowledgeCutoff":"2025-12","structuredOutput":true,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5","displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752,"knowledgeCutoff":"2025-12"}},"zai-org/GLM-5.1":{"metadata":{"displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.1","displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752,"knowledgeCutoff":"2025-04"}},"zai-org/GLM-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"zai-org/GLM-5.3":{"metadata":{"displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.3","displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"zai-org/GLM-5.3-Flash":{"metadata":{"displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"zai-org/GLM-5.3-Flash","displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}}}},"groq":{"baseUrl":"https://api.groq.com/openai/v1","label":"Groq","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["llama-3.3-70b-versatile","llama-3.1-8b-instant","openai/gpt-oss-120b","openai/gpt-oss-20b","openai/gpt-oss-safeguard-20b","qwen/qwen3.6-27b","qwen/qwen3.8-27b"],"models":{"allam-2-7b":{"metadata":{"displayName":"ALLaM-2-7b","description":"ALLaM-2-7b instruction tuned model by SDAIA","lifecycle":"active","contextWindow":4096,"maxOutputTokens":4096,"lastUpdated":"2025-01-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"allam-2-7b","displayName":"ALLaM-2-7b","description":"ALLaM-2-7b instruction tuned model by SDAIA","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":4096,"defaultContextWindow":4096}},"canopylabs/orpheus-arabic-saudi":{"metadata":{"displayName":"Canopy Labs Orpheus Arabic Saudi","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"beta","contextWindow":4000,"maxOutputTokens":50000,"lastUpdated":"2025-12-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"canopylabs/orpheus-arabic-saudi","displayName":"Canopy Labs Orpheus Arabic Saudi","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":4000,"defaultContextWindow":4000}},"canopylabs/orpheus-v1-english":{"metadata":{"displayName":"Canopy Labs Orpheus V1 English","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"beta","contextWindow":4000,"maxOutputTokens":50000,"lastUpdated":"2025-12-19","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["audio"]}},"entry":{"id":"canopylabs/orpheus-v1-english","displayName":"Canopy Labs Orpheus V1 English","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":4000,"defaultContextWindow":4000}},"groq/compound":{"metadata":{"displayName":"Compound","description":"General-purpose chat model for instruction following, writing, and analysis","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"lastUpdated":"2025-09-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"groq/compound","displayName":"Compound","description":"General-purpose chat model for instruction following, writing, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"groq/compound-mini":{"metadata":{"displayName":"Compound Mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"lastUpdated":"2025-09-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"groq/compound-mini","displayName":"Compound Mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"llama-3.1-8b-instant":{"metadata":{"displayName":"Llama 3.1 8B","description":"Compact Llama instruction model for fast chat and local deployment","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2023-12","lastUpdated":"2024-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"llama-3.1-8b-instant","displayName":"Llama 3.1 8B","description":"Compact Llama instruction model for fast chat and local deployment","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12"}},"llama-3.3-70b-versatile":{"metadata":{"displayName":"Llama 3.3 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2023-12","lastUpdated":"2024-12-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"llama-3.3-70b-versatile","displayName":"Llama 3.3 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12"}},"meta-llama/llama-prompt-guard-2-22m":{"metadata":{"displayName":"Llama Prompt Guard 2 22M","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"beta","contextWindow":512,"maxOutputTokens":512,"lastUpdated":"2025-05-29","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/llama-prompt-guard-2-22m","displayName":"Llama Prompt Guard 2 22M","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":512,"defaultContextWindow":512}},"meta-llama/llama-prompt-guard-2-86m":{"metadata":{"displayName":"Prompt Guard 2 86M","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"beta","contextWindow":512,"maxOutputTokens":512,"lastUpdated":"2025-05-29","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/llama-prompt-guard-2-86m","displayName":"Prompt Guard 2 86M","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":512,"defaultContextWindow":512}},"openai/gpt-oss-120b":{"metadata":{"displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2025-10-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-120b","displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"openai/gpt-oss-20b":{"metadata":{"displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2025-09-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-20b","displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"openai/gpt-oss-safeguard-20b":{"metadata":{"displayName":"Safety GPT OSS 20B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"beta","contextWindow":131072,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-06-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-safeguard-20b","displayName":"Safety GPT OSS 20B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"qwen/qwen3.6-27b":{"metadata":{"displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","default"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen3.6-27b","displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"],"contextWindow":131072,"defaultContextWindow":131072}},"qwen/qwen3.8-27b":{"metadata":{"displayName":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","lifecycle":"active","contextWindow":131042,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","default","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen3.8-27b","displayName":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":131042,"defaultContextWindow":131042}},"whisper-large-v3":{"metadata":{"displayName":"Whisper","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2025-09-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"whisper-large-v3","displayName":"Whisper","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"whisper-large-v3-turbo":{"metadata":{"displayName":"Whisper Large V3 Turbo","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","lastUpdated":"2024-10-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"whisper-large-v3-turbo","displayName":"Whisper Large V3 Turbo","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"qwen/qwen3-32b":{"metadata":{"thinkingOptions":{"efforts":[]}},"entry":{"id":"qwen/qwen3-32b","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}}}},"openrouter":{"baseUrl":"https://openrouter.ai/api/v1","label":"OpenRouter","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["anthropic/claude-sonnet-5","openai/gpt-5.6-sol","x-ai/grok-4.5","deepseek/deepseek-v4-pro","~anthropic/claude-fable-latest","~anthropic/claude-haiku-latest","~anthropic/claude-opus-latest","~anthropic/claude-sonnet-latest","~deepseek/deepseek-flash-latest","~deepseek/deepseek-pro-latest","~deepseek/deepseek-v4-flash-latest","~google/gemini-flash-latest","~google/gemini-pro-latest","~moonshotai/kimi-latest","~openai/gpt-astra-latest","~openai/gpt-luna-latest","~openai/gpt-mini-latest","~openai/gpt-sol-latest","~openai/gpt-terra-latest","~x-ai/grok-latest","~z-ai/glm-flash-latest","~z-ai/glm-latest","aion-labs/aion-2.0","aion-labs/aion-3.0","aion-labs/aion-3.0-mini","amazon/nova-2-lite-v1","amazon/nova-lite-v1","amazon/nova-micro-v1","amazon/nova-premier-v1","amazon/nova-pro-v1","anthropic/claude-3-haiku","anthropic/claude-fable-5","anthropic/claude-fable-5.1","anthropic/claude-haiku-4.5","anthropic/claude-opus-4","anthropic/claude-opus-4.1","anthropic/claude-opus-4.5","anthropic/claude-opus-4.6","anthropic/claude-opus-4.7","anthropic/claude-opus-4.8","anthropic/claude-opus-5","anthropic/claude-sonnet-4","anthropic/claude-sonnet-4.5","anthropic/claude-sonnet-4.6","arcee-ai/trinity-large-thinking","bytedance-seed/seed-1.6","bytedance-seed/seed-1.6-flash","bytedance-seed/seed-2-1-turbo","bytedance-seed/seed-2.0-code","bytedance-seed/seed-2.0-lite","bytedance-seed/seed-2.0-mini","cohere/command-r-08-2024","cohere/command-r-plus-08-2024","cohere/north-mini-code:free","deepseek/deepseek-chat","deepseek/deepseek-chat-v3-0324","deepseek/deepseek-chat-v3.1","deepseek/deepseek-r1","deepseek/deepseek-r1-0528","deepseek/deepseek-v3.1-terminus","deepseek/deepseek-v3.2","deepseek/deepseek-v3.2-exp","deepseek/deepseek-v4-flash","deepseek/deepseek-v4-flash-0731","deepseek/deepseek-v4-flash-vision-exp","deepseek/deepseek-v4-pro-0813","deepseek/deepseek-v4.1-flash","dots-studio/dots-3-note-preview:free","google/gemini-2.5-flash","google/gemini-2.5-flash-lite","google/gemini-2.5-pro","google/gemini-2.5-pro-preview","google/gemini-3-flash-preview","google/gemini-3-pro-image","google/gemini-3.1-flash-lite","google/gemini-3.1-flash-lite-preview","google/gemini-3.1-pro-preview","google/gemini-3.1-pro-preview-customtools","google/gemini-3.5-flash","google/gemini-3.5-flash-lite","google/gemini-3.6-flash","google/gemini-3.7-flash","google/gemini-3.8-flash","google/gemma-3-12b-it","google/gemma-3-27b-it","google/gemma-4-26b-a4b-it","google/gemma-4-26b-a4b-it:free","google/gemma-4-31b-it","google/gemma-4-31b-it:free","ibm-granite/granite-4.2-8b","inception/mercury-2","inception/mercury-2.5","inclusionai/ling-3.0-flash","inclusionai/ling-3.0-flash-fin","inclusionai/ling-3.0-flash-fin:free","inclusionai/ling-3.0-flash-sante:free","inclusionai/ling-3.0-flash-vl","inclusionai/ling-3.0-flash-vl:free","kwaipilot/kat-coder-pro-v2","kwaipilot/kat-coder-pro-v2.5","liquid/lfm-2.5-2.6b:free","meituan/longcat-2.0","meta-llama/llama-3.1-70b-instruct","meta-llama/llama-3.1-8b-instruct","meta-llama/llama-3.3-70b-instruct","meta-llama/llama-4-maverick","meta-llama/llama-4-scout","meta/muse-glimmer-30b","meta/muse-spark-1.1","meta/muse-spark-1.2","meta/muse-spark-1.2-contributor","meta/muse-spark-1.3","meta/muse-spark-1.3-contributor","minimax/minimax-m1","minimax/minimax-m2","minimax/minimax-m2.1","minimax/minimax-m2.5","minimax/minimax-m2.7","minimax/minimax-m3","mistralai/codestral-2508","mistralai/devstral-2512","mistralai/ministral-14b-2512","mistralai/ministral-3b-2512","mistralai/ministral-8b-2512","mistralai/mistral-large","mistralai/mistral-large-2407","mistralai/mistral-large-2512","mistralai/mistral-medium-3","mistralai/mistral-medium-3-5","mistralai/mistral-medium-3.1","mistralai/mistral-nemo","mistralai/mistral-saba","mistralai/mistral-small-2603","mistralai/mistral-small-3.2-24b-instruct","mistralai/mixtral-8x22b-instruct","mistralai/voxtral-small-24b-2507","moonshotai/kimi-k2","moonshotai/kimi-k2-0905","moonshotai/kimi-k2-thinking","moonshotai/kimi-k2.5","moonshotai/kimi-k2.6","moonshotai/kimi-k2.7-code","moonshotai/kimi-k3","nex-agi/nex-n2.5-mini:free","nex-agi/nex-n2.5-pro:free","nvidia/nemotron-3-nano-30b-a3b","nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","nvidia/nemotron-3-super-120b-a12b","nvidia/nemotron-3-super-120b-a12b:free","nvidia/nemotron-3-ultra-550b-a55b","nvidia/nemotron-3-ultra-550b-a55b:free","nvidia/nemotron-3.5-lightning","nvidia/nemotron-3.5-lightning:free","openai/gpt-3.5-turbo","openai/gpt-3.5-turbo-0613","openai/gpt-3.5-turbo-16k","openai/gpt-4","openai/gpt-4-turbo","openai/gpt-4.1","openai/gpt-4.1-mini","openai/gpt-4.1-nano","openai/gpt-4o","openai/gpt-4o-2024-05-13","openai/gpt-4o-2024-08-06","openai/gpt-4o-2024-11-20","openai/gpt-4o-mini","openai/gpt-4o-mini-2024-07-18","openai/gpt-5","openai/gpt-5-mini","openai/gpt-5-nano","openai/gpt-5-pro","openai/gpt-5.1","openai/gpt-5.1-codex","openai/gpt-5.1-codex-max","openai/gpt-5.1-codex-mini","openai/gpt-5.2","openai/gpt-5.2-chat","openai/gpt-5.2-codex","openai/gpt-5.2-pro","openai/gpt-5.3-codex","openai/gpt-5.4","openai/gpt-5.4-mini","openai/gpt-5.4-nano","openai/gpt-5.4-pro","openai/gpt-5.5","openai/gpt-5.5-pro","openai/gpt-5.6-luna","openai/gpt-5.6-luna-pro","openai/gpt-5.6-sol-pro","openai/gpt-5.6-terra","openai/gpt-5.6-terra-pro","openai/gpt-6-astra","openai/gpt-6-astra-pro","openai/gpt-audio","openai/gpt-audio-mini","openai/gpt-chat-latest","openai/gpt-oss-120b","openai/gpt-oss-20b","openai/gpt-oss-safeguard-20b","openai/o1","openai/o3","openai/o3-mini","openai/o3-mini-high","openai/o3-pro","openai/o4-mini","openai/o4-mini-high","openrouter/auto","openrouter/free","poolside/laguna-s-2.1","poolside/laguna-s-2.1:free","poolside/laguna-xs-2.1","poolside/laguna-xs-2.1:free","qwen/qwen-2.5-72b-instruct","qwen/qwen-2.5-7b-instruct","qwen/qwen-plus","qwen/qwen-plus-2025-07-28","qwen/qwen3-14b","qwen/qwen3-235b-a22b","qwen/qwen3-235b-a22b-2507","qwen/qwen3-235b-a22b-thinking-2507","qwen/qwen3-30b-a3b","qwen/qwen3-30b-a3b-instruct-2507","qwen/qwen3-30b-a3b-thinking-2507","qwen/qwen3-32b","qwen/qwen3-8b","qwen/qwen3-coder","qwen/qwen3-coder-30b-a3b-instruct","qwen/qwen3-coder-flash","qwen/qwen3-coder-next","qwen/qwen3-coder-plus","qwen/qwen3-max","qwen/qwen3-max-thinking","qwen/qwen3-next-80b-a3b-instruct","qwen/qwen3-next-80b-a3b-thinking","qwen/qwen3-vl-235b-a22b-instruct","qwen/qwen3-vl-235b-a22b-thinking","qwen/qwen3-vl-30b-a3b-instruct","qwen/qwen3-vl-30b-a3b-thinking","qwen/qwen3-vl-32b-instruct","qwen/qwen3-vl-8b-instruct","qwen/qwen3-vl-8b-thinking","qwen/qwen3.5-122b-a10b","qwen/qwen3.5-27b","qwen/qwen3.5-35b-a3b","qwen/qwen3.5-397b-a17b","qwen/qwen3.5-9b","qwen/qwen3.5-flash-02-23","qwen/qwen3.5-plus-02-15","qwen/qwen3.5-plus-20260420","qwen/qwen3.6-27b","qwen/qwen3.6-35b-a3b","qwen/qwen3.6-flash","qwen/qwen3.6-max-preview","qwen/qwen3.6-plus","qwen/qwen3.7-flash","qwen/qwen3.7-max","qwen/qwen3.7-plus","qwen/qwen3.8-2.4t-a95b","qwen/qwen3.8-27b","qwen/qwen3.8-flash","qwen/qwen3.8-max-0902","rekaai/reka-edge","relace/relace-search","sakana/fugu-max","sakana/fugu-ultra","sakana/fugu-ultra-v2","sakana/sakana-namazu","sao10k/l3.1-euryale-70b","stepfun/step-3.5-flash","stepfun/step-3.7-flash","tencent/hy3","tencent/hy3-preview","tencent/hy4-preview","thedrummer/unslopnemo-12b","thinkingmachines/inkling","thinkingmachines/inkling-small","thinkingmachines/inkling-small:free","thinkingmachines/inkling:free","upstage/solar-pro-3","upstage/solar-pro4","x-ai/grok-4.20","x-ai/grok-4.3","x-ai/grok-4.6","x-ai/grok-build-0.1","xiaomi/mimo-v2.5","xiaomi/mimo-v2.5-pro","z-ai/glm-4.5","z-ai/glm-4.5-air","z-ai/glm-4.5v","z-ai/glm-4.6","z-ai/glm-4.6v","z-ai/glm-4.7","z-ai/glm-4.7-flash","z-ai/glm-5","z-ai/glm-5-turbo","z-ai/glm-5.1","z-ai/glm-5.2","z-ai/glm-5.3","z-ai/glm-5.3-flash","z-ai/glm-5v-turbo"],"models":{"~anthropic/claude-fable-latest":{"metadata":{"displayName":"Claude Fable Latest","description":"Claude model for creative writing, analysis, and controlled agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-06-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"~anthropic/claude-fable-latest","displayName":"Claude Fable Latest","description":"Claude model for creative writing, analysis, and controlled agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"~anthropic/claude-haiku-latest":{"metadata":{"displayName":"Claude Haiku Latest","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"~anthropic/claude-haiku-latest","displayName":"Claude Haiku Latest","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}},"~anthropic/claude-opus-latest":{"metadata":{"displayName":"Claude Opus Latest","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"~anthropic/claude-opus-latest","displayName":"Claude Opus Latest","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"~anthropic/claude-sonnet-latest":{"metadata":{"displayName":"Claude Sonnet Latest","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"~anthropic/claude-sonnet-latest","displayName":"Claude Sonnet Latest","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"~deepseek/deepseek-flash-latest":{"metadata":{"displayName":"DeepSeek Flash Latest","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":943718,"structuredOutput":true,"lastUpdated":"2026-09-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"~deepseek/deepseek-flash-latest","displayName":"DeepSeek Flash Latest","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"~deepseek/deepseek-pro-latest":{"metadata":{"displayName":"DeepSeek Pro Latest","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":943718,"structuredOutput":true,"lastUpdated":"2026-09-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"~deepseek/deepseek-pro-latest","displayName":"DeepSeek Pro Latest","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"~deepseek/deepseek-v4-flash-latest":{"metadata":{"displayName":"DeepSeek V4 Flash Latest","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","lifecycle":"active","contextWindow":1310720,"maxOutputTokens":393216,"structuredOutput":true,"lastUpdated":"2026-08-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"~deepseek/deepseek-v4-flash-latest","displayName":"DeepSeek V4 Flash Latest","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1310720,"defaultContextWindow":1310720}},"~google/gemini-flash-latest":{"metadata":{"displayName":"Gemini Flash Latest","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01-01","structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"entry":{"id":"~google/gemini-flash-latest","displayName":"Gemini Flash Latest","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01-01"}},"~google/gemini-pro-latest":{"metadata":{"displayName":"Gemini Pro Latest","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["audio","pdf","image","text","video"],"output":["text"]}},"entry":{"id":"~google/gemini-pro-latest","displayName":"Gemini Pro Latest","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"~moonshotai/kimi-latest":{"metadata":{"displayName":"Kimi Latest","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":943718,"structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"~moonshotai/kimi-latest","displayName":"Kimi Latest","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"~openai/gpt-astra-latest":{"metadata":{"displayName":"GPT Astra Latest","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-09-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"entry":{"id":"~openai/gpt-astra-latest","displayName":"GPT Astra Latest","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1050000,"defaultContextWindow":1050000}},"~openai/gpt-luna-latest":{"metadata":{"displayName":"GPT Luna Latest","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-09-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"entry":{"id":"~openai/gpt-luna-latest","displayName":"GPT Luna Latest","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2026-02-16"}},"~openai/gpt-mini-latest":{"metadata":{"displayName":"GPT Mini Latest","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"entry":{"id":"~openai/gpt-mini-latest","displayName":"GPT Mini Latest","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-08-31"}},"~openai/gpt-sol-latest":{"metadata":{"displayName":"GPT Sol Latest","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-09-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"entry":{"id":"~openai/gpt-sol-latest","displayName":"GPT Sol Latest","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2026-02-16"}},"~openai/gpt-terra-latest":{"metadata":{"displayName":"GPT Terra Latest","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-09-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"entry":{"id":"~openai/gpt-terra-latest","displayName":"GPT Terra Latest","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2026-02-16"}},"~x-ai/grok-latest":{"metadata":{"displayName":"Grok Latest","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":500000,"maxOutputTokens":450000,"structuredOutput":true,"lastUpdated":"2026-07-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"~x-ai/grok-latest","displayName":"Grok Latest","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":500000,"defaultContextWindow":500000}},"~z-ai/glm-flash-latest":{"metadata":{"displayName":"GLM Flash Latest","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":1310720,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"~z-ai/glm-flash-latest","displayName":"GLM Flash Latest","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1310720,"defaultContextWindow":1310720}},"~z-ai/glm-latest":{"metadata":{"displayName":"GLM Latest","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":1310720,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"~z-ai/glm-latest","displayName":"GLM Latest","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1310720,"defaultContextWindow":1310720}},"aion-labs/aion-2.0":{"metadata":{"displayName":"Aion-2.0","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-02-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"aion-labs/aion-2.0","displayName":"Aion-2.0","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"aion-labs/aion-3.0":{"metadata":{"displayName":"Aion-3.0","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-07-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"aion-labs/aion-3.0","displayName":"Aion-3.0","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"aion-labs/aion-3.0-mini":{"metadata":{"displayName":"Aion-3.0-Mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-07-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"aion-labs/aion-3.0-mini","displayName":"Aion-3.0-Mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"aion-labs/aion-rp-llama-3.1-8b":{"metadata":{"displayName":"Aion-RP 1.0 (8B)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":32768,"maxOutputTokens":29491,"knowledgeCutoff":"2023-12-31","structuredOutput":false,"lastUpdated":"2025-02-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"aion-labs/aion-rp-llama-3.1-8b","displayName":"Aion-RP 1.0 (8B)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2023-12-31"}},"amazon/nova-2-lite-v1":{"metadata":{"displayName":"Nova 2 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65535,"structuredOutput":false,"lastUpdated":"2025-12-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"amazon/nova-2-lite-v1","displayName":"Nova 2 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"amazon/nova-lite-v1":{"metadata":{"displayName":"Nova Lite 1.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":300000,"maxOutputTokens":5120,"knowledgeCutoff":"2024-10-31","structuredOutput":false,"lastUpdated":"2024-12-05","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"amazon/nova-lite-v1","displayName":"Nova Lite 1.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":300000,"defaultContextWindow":300000,"knowledgeCutoff":"2024-10-31"}},"amazon/nova-micro-v1":{"metadata":{"displayName":"Nova Micro 1.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":128000,"maxOutputTokens":5120,"knowledgeCutoff":"2024-10-31","structuredOutput":false,"lastUpdated":"2024-12-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"amazon/nova-micro-v1","displayName":"Nova Micro 1.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-10-31"}},"amazon/nova-premier-v1":{"metadata":{"displayName":"Nova Premier 1.0","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":32000,"structuredOutput":false,"lastUpdated":"2025-10-31","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"amazon/nova-premier-v1","displayName":"Nova Premier 1.0","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"amazon/nova-pro-v1":{"metadata":{"displayName":"Nova Pro 1.0","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":300000,"maxOutputTokens":5120,"knowledgeCutoff":"2024-10-31","structuredOutput":false,"lastUpdated":"2024-12-05","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"amazon/nova-pro-v1","displayName":"Nova Pro 1.0","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":300000,"defaultContextWindow":300000,"knowledgeCutoff":"2024-10-31"}},"anthracite-org/magnum-v4-72b":{"metadata":{"displayName":"Magnum v4 72B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","lifecycle":"active","contextWindow":32768,"maxOutputTokens":4096,"knowledgeCutoff":"2024-06-30","structuredOutput":true,"lastUpdated":"2024-10-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"anthracite-org/magnum-v4-72b","displayName":"Magnum v4 72B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-06-30"}},"anthropic/claude-3-haiku":{"metadata":{"displayName":"Claude 3 Haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-08-31","structuredOutput":false,"lastUpdated":"2024-03-13","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"anthropic/claude-3-haiku","displayName":"Claude 3 Haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2023-08-31"}},"anthropic/claude-fable-5":{"metadata":{"displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","structuredOutput":true,"lastUpdated":"2026-06-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-fable-5","displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"anthropic/claude-fable-5.1":{"metadata":{"displayName":"Claude Fable 5.1","description":"Claude model for creative writing, analysis, and controlled agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-06","structuredOutput":true,"lastUpdated":"2026-09-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-fable-5.1","displayName":"Claude Fable 5.1","description":"Claude model for creative writing, analysis, and controlled agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-06"}},"anthropic/claude-haiku-4.5":{"metadata":{"displayName":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-02-28","structuredOutput":true,"lastUpdated":"2025-10-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-haiku-4.5","displayName":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-02-28"}},"anthropic/claude-opus-4":{"metadata":{"displayName":"Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-01-31","structuredOutput":false,"lastUpdated":"2025-05-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4","displayName":"Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-01-31"}},"anthropic/claude-opus-4.1":{"metadata":{"displayName":"Claude Opus 4.1 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-03-31","structuredOutput":false,"lastUpdated":"2025-08-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4.1","displayName":"Claude Opus 4.1 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-03-31"}},"anthropic/claude-opus-4.5":{"metadata":{"displayName":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2025-11-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4.5","displayName":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-05"}},"anthropic/claude-opus-4.6":{"metadata":{"displayName":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-05-31","structuredOutput":true,"lastUpdated":"2026-03-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4.6","displayName":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05-31"}},"anthropic/claude-opus-4.7":{"metadata":{"displayName":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","structuredOutput":true,"lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4.7","displayName":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"anthropic/claude-opus-4.8":{"metadata":{"displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01","structuredOutput":true,"lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-4.8","displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01"}},"anthropic/claude-opus-5":{"metadata":{"displayName":"Claude Opus 5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-05","structuredOutput":true,"lastUpdated":"2026-07-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-opus-5","displayName":"Claude Opus 5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-05"}},"anthropic/claude-sonnet-4":{"metadata":{"displayName":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01-31","structuredOutput":false,"lastUpdated":"2025-05-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-sonnet-4","displayName":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-01-31"}},"anthropic/claude-sonnet-4.5":{"metadata":{"displayName":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-07-31","structuredOutput":true,"lastUpdated":"2025-09-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-sonnet-4.5","displayName":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-07-31"}},"anthropic/claude-sonnet-4.6":{"metadata":{"displayName":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-sonnet-4.6","displayName":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-08-31"}},"anthropic/claude-sonnet-5":{"metadata":{"displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","structuredOutput":true,"lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"anthropic/claude-sonnet-5","displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"arcee-ai/trinity-large-thinking":{"metadata":{"displayName":"Trinity Large Thinking","description":"Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":80000,"structuredOutput":false,"lastUpdated":"2026-05-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"arcee-ai/trinity-large-thinking","displayName":"Trinity Large Thinking","description":"Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"baidu/ernie-4.5-vl-424b-a47b":{"metadata":{"displayName":"ERNIE 4.5 VL 424B A47B ","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":123000,"maxOutputTokens":16000,"knowledgeCutoff":"2025-03-31","structuredOutput":false,"lastUpdated":"2025-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["image","text"],"output":["text"]}},"entry":{"id":"baidu/ernie-4.5-vl-424b-a47b","displayName":"ERNIE 4.5 VL 424B A47B ","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":123000,"defaultContextWindow":123000,"knowledgeCutoff":"2025-03-31"}},"bytedance-seed/seed-1.6":{"metadata":{"displayName":"Seed 1.6","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2025-12-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["image","text","video"],"output":["text"]}},"entry":{"id":"bytedance-seed/seed-1.6","displayName":"Seed 1.6","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"bytedance-seed/seed-1.6-flash":{"metadata":{"displayName":"Seed 1.6 Flash","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2025-12-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["image","text","video"],"output":["text"]}},"entry":{"id":"bytedance-seed/seed-1.6-flash","displayName":"Seed 1.6 Flash","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"bytedance-seed/seed-2-1-turbo":{"metadata":{"displayName":"Seed 2.1 Turbo","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"bytedance-seed/seed-2-1-turbo","displayName":"Seed 2.1 Turbo","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"bytedance-seed/seed-2.0-code":{"metadata":{"displayName":"Seed 2.0 Code","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-02-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"bytedance-seed/seed-2.0-code","displayName":"Seed 2.0 Code","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":262144,"defaultContextWindow":262144}},"bytedance-seed/seed-2.0-lite":{"metadata":{"displayName":"Seed 2.0 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-02-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"bytedance-seed/seed-2.0-lite","displayName":"Seed 2.0 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":262144,"defaultContextWindow":262144}},"bytedance-seed/seed-2.0-mini":{"metadata":{"displayName":"Seed 2.0 Mini","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-02-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"bytedance-seed/seed-2.0-mini","displayName":"Seed 2.0 Mini","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":262144,"defaultContextWindow":262144}},"bytedance/ui-tars-1.5-7b":{"metadata":{"displayName":"UI-TARS 7B ","description":"Multimodal model for analyzing text, images, documents, and rich media","lifecycle":"active","contextWindow":128000,"maxOutputTokens":2048,"knowledgeCutoff":"2025-01-31","structuredOutput":true,"lastUpdated":"2025-07-22","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["image","text"],"output":["text"]}},"entry":{"id":"bytedance/ui-tars-1.5-7b","displayName":"UI-TARS 7B ","description":"Multimodal model for analyzing text, images, documents, and rich media","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-01-31"}},"cognitivecomputations/dolphin-mistral-24b-venice-edition":{"metadata":{"displayName":"Uncensored","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04-30","structuredOutput":false,"lastUpdated":"2025-07-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","displayName":"Uncensored","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-04-30"}},"cohere/command-a":{"metadata":{"displayName":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","lifecycle":"active","contextWindow":256000,"maxOutputTokens":8192,"knowledgeCutoff":"2024-08-31","structuredOutput":true,"lastUpdated":"2025-03-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"cohere/command-a","displayName":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2024-08-31"}},"cohere/command-r-08-2024":{"metadata":{"displayName":"Command R","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4000,"knowledgeCutoff":"2024-06-01","structuredOutput":true,"lastUpdated":"2024-08-30","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"cohere/command-r-08-2024","displayName":"Command R","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-06-01"}},"cohere/command-r-plus-08-2024":{"metadata":{"displayName":"Command R+","description":"Cohere's RAG workhorse for long-context enterprise search and tool use","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4000,"knowledgeCutoff":"2024-06-01","structuredOutput":true,"lastUpdated":"2024-08-30","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"cohere/command-r-plus-08-2024","displayName":"Command R+","description":"Cohere's RAG workhorse for long-context enterprise search and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-06-01"}},"cohere/command-r7b-12-2024":{"metadata":{"displayName":"Command R7B","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4000,"knowledgeCutoff":"2024-06-01","structuredOutput":true,"lastUpdated":"2024-12-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"cohere/command-r7b-12-2024","displayName":"Command R7B","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-06-01"}},"cohere/north-mini-code:free":{"metadata":{"displayName":"North Mini Code (free)","description":"Cohere coding model for practical software engineering and agentic edits","lifecycle":"active","contextWindow":256000,"maxOutputTokens":64000,"structuredOutput":false,"lastUpdated":"2026-06-17","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"cohere/north-mini-code:free","displayName":"North Mini Code (free)","description":"Cohere coding model for practical software engineering and agentic edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"deepseek/deepseek-chat":{"metadata":{"displayName":"DeepSeek Chat","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":16000,"knowledgeCutoff":"2025-09","structuredOutput":true,"lastUpdated":"2026-02-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-chat","displayName":"DeepSeek Chat","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2025-09"}},"deepseek/deepseek-chat-v3-0324":{"metadata":{"displayName":"DeepSeek V3 0324","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":147456,"knowledgeCutoff":"2024-07-31","structuredOutput":true,"lastUpdated":"2025-03-24","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-chat-v3-0324","displayName":"DeepSeek V3 0324","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2024-07-31"}},"deepseek/deepseek-chat-v3.1":{"metadata":{"displayName":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":32768,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-08-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-chat-v3.1","displayName":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2025-03-31"}},"deepseek/deepseek-r1":{"metadata":{"displayName":"DeepSeek-R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","lifecycle":"active","contextWindow":64000,"maxOutputTokens":16000,"knowledgeCutoff":"2024-07","structuredOutput":false,"lastUpdated":"2025-05-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-r1","displayName":"DeepSeek-R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":64000,"defaultContextWindow":64000,"knowledgeCutoff":"2024-07"}},"deepseek/deepseek-r1-0528":{"metadata":{"displayName":"R1 0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","lifecycle":"active","contextWindow":163840,"maxOutputTokens":32768,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-05-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-r1-0528","displayName":"R1 0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2025-03-31"}},"deepseek/deepseek-r1-distill-llama-70b":{"metadata":{"displayName":"R1 Distill Llama 70B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","lifecycle":"active","contextWindow":8192,"maxOutputTokens":7372,"knowledgeCutoff":"2024-07-31","structuredOutput":false,"lastUpdated":"2025-01-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-r1-distill-llama-70b","displayName":"R1 Distill Llama 70B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2024-07-31"}},"deepseek/deepseek-v3.1-terminus":{"metadata":{"displayName":"DeepSeek V3.1 Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":32768,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-09-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v3.1-terminus","displayName":"DeepSeek V3.1 Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2025-03-31"}},"deepseek/deepseek-v3.2":{"metadata":{"displayName":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":65536,"knowledgeCutoff":"2024-07","structuredOutput":true,"lastUpdated":"2025-12-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v3.2","displayName":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2024-07"}},"deepseek/deepseek-v3.2-exp":{"metadata":{"displayName":"DeepSeek V3.2 Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":65536,"knowledgeCutoff":"2025-07-31","structuredOutput":true,"lastUpdated":"2025-09-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v3.2-exp","displayName":"DeepSeek V3.2 Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2025-07-31"}},"deepseek/deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-flash","displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"deepseek/deepseek-v4-flash-0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1310720,"maxOutputTokens":943718,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-flash-0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1310720,"defaultContextWindow":1310720,"knowledgeCutoff":"2025-05"}},"deepseek/deepseek-v4-flash-vision-exp":{"metadata":{"displayName":"DeepSeek V4 Flash Vision Exp","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":943718,"structuredOutput":true,"lastUpdated":"2026-08-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-flash-vision-exp","displayName":"DeepSeek V4 Flash Vision Exp","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"deepseek/deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":393216,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-pro","displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"deepseek/deepseek-v4-pro-0813":{"metadata":{"displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4-pro-0813","displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"deepseek/deepseek-v4.1-flash":{"metadata":{"displayName":"DeepSeek V4.1 Flash","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek/deepseek-v4.1-flash","displayName":"DeepSeek V4.1 Flash","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"dots-studio/dots-3-note-preview:free":{"metadata":{"displayName":"Dots3-Note Preview (free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":512000,"maxOutputTokens":460800,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"dots-studio/dots-3-note-preview:free","displayName":"Dots3-Note Preview (free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":512000,"defaultContextWindow":512000}},"google/gemini-2.5-flash":{"metadata":{"displayName":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65535,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-06-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-2.5-flash","displayName":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-2.5-flash-image":{"metadata":{"displayName":"Nano Banana","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","lifecycle":"active","contextWindow":32768,"maxOutputTokens":8192,"knowledgeCutoff":"2024-06","structuredOutput":true,"lastUpdated":"2025-08-26","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"google/gemini-2.5-flash-image","displayName":"Nano Banana","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-06"}},"google/gemini-2.5-flash-lite":{"metadata":{"displayName":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65535,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-06-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-2.5-flash-lite","displayName":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-2.5-pro":{"metadata":{"displayName":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-06-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-2.5-pro","displayName":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-2.5-pro-preview":{"metadata":{"displayName":"Gemini 2.5 Pro Preview 06-05","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01-31","structuredOutput":true,"lastUpdated":"2025-06-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["pdf","image","text","audio"],"output":["text"]}},"entry":{"id":"google/gemini-2.5-pro-preview","displayName":"Gemini 2.5 Pro Preview 06-05","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01-31"}},"google/gemini-3-flash-preview":{"metadata":{"displayName":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-12-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"],"toggle":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3-flash-preview","displayName":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-3-pro-image":{"metadata":{"displayName":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"google/gemini-3-pro-image","displayName":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"google/gemini-3-pro-image-preview":{"metadata":{"displayName":"Nano Banana Pro Preview","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","lifecycle":"active","contextWindow":65536,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-11-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"google/gemini-3-pro-image-preview","displayName":"Nano Banana Pro Preview","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-flash-image":{"metadata":{"displayName":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["minimal","high"],"toggle":true},"modalities":{"input":["image","text"],"output":["text","image"]}},"entry":{"id":"google/gemini-3.1-flash-image","displayName":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","high"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-flash-image-preview":{"metadata":{"displayName":"Nano Banana 2 Preview","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":65536,"maxOutputTokens":58982,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-02-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["minimal","high"],"toggle":true},"modalities":{"input":["image","text"],"output":["text","image"]}},"entry":{"id":"google/gemini-3.1-flash-image-preview","displayName":"Nano Banana 2 Preview","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","high"],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-flash-lite":{"metadata":{"displayName":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"],"toggle":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.1-flash-lite","displayName":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-flash-lite-image":{"metadata":{"displayName":"Nano Banana 2 Lite","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":65536,"maxOutputTokens":58982,"knowledgeCutoff":"2025-01","structuredOutput":false,"lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["minimal","high"],"toggle":true},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"google/gemini-3.1-flash-lite-image","displayName":"Nano Banana 2 Lite","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","high"],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-flash-lite-preview":{"metadata":{"displayName":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-03-03","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"],"toggle":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.1-flash-lite-preview","displayName":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-pro-preview":{"metadata":{"displayName":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-02-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.1-pro-preview","displayName":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-3.1-pro-preview-customtools":{"metadata":{"displayName":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-02-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.1-pro-preview-customtools","displayName":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-3.5-flash":{"metadata":{"displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.5-flash","displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-01"}},"google/gemini-3.5-flash-lite":{"metadata":{"displayName":"Gemini 3.5 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-07-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.5-flash-lite","displayName":"Gemini 3.5 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2026-03"}},"google/gemini-3.6-flash":{"metadata":{"displayName":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-07-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.6-flash","displayName":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2026-03"}},"google/gemini-3.7-flash":{"metadata":{"displayName":"Gemini 3.7 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-08-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.7-flash","displayName":"Gemini 3.7 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2026-03"}},"google/gemini-3.8-flash":{"metadata":{"displayName":"Gemini 3.8 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"google/gemini-3.8-flash","displayName":"Gemini 3.8 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1048576,"defaultContextWindow":1048576}},"google/gemma-2-27b-it":{"metadata":{"displayName":"Gemma 2 27B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":8192,"maxOutputTokens":2048,"knowledgeCutoff":"2024-06-30","structuredOutput":true,"lastUpdated":"2024-07-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"google/gemma-2-27b-it","displayName":"Gemma 2 27B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2024-06-30"}},"google/gemma-3-12b-it":{"metadata":{"displayName":"Gemma 3 12B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2024-08","structuredOutput":true,"lastUpdated":"2025-03-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3-12b-it","displayName":"Gemma 3 12B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-08"}},"google/gemma-3-27b-it":{"metadata":{"displayName":"Gemma 3 27B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"knowledgeCutoff":"2024-08","structuredOutput":true,"lastUpdated":"2025-03-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3-27b-it","displayName":"Gemma 3 27B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-08"}},"google/gemma-3-4b-it":{"metadata":{"displayName":"Gemma 3 4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2024-08","structuredOutput":true,"lastUpdated":"2025-03-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"google/gemma-3-4b-it","displayName":"Gemma 3 4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-08"}},"google/gemma-4-26b-a4b-it":{"metadata":{"displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["image","text","video"],"output":["text"]}},"entry":{"id":"google/gemma-4-26b-a4b-it","displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"google/gemma-4-26b-a4b-it:free":{"metadata":{"displayName":"Gemma 4 26B A4B (free)","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["image","text","video"],"output":["text"]}},"entry":{"id":"google/gemma-4-26b-a4b-it:free","displayName":"Gemma 4 26B A4B (free)","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"google/gemma-4-31b-it":{"metadata":{"displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["image","text","video"],"output":["text"]}},"entry":{"id":"google/gemma-4-31b-it","displayName":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"google/gemma-4-31b-it:free":{"metadata":{"displayName":"Gemma 4 31B (free)","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["image","text","video"],"output":["text"]}},"entry":{"id":"google/gemma-4-31b-it:free","displayName":"Gemma 4 31B (free)","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"google/lyria-3-clip-preview":{"metadata":{"displayName":"Lyria 3 Clip Preview","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"structuredOutput":false,"lastUpdated":"2026-03-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","audio"]}},"entry":{"id":"google/lyria-3-clip-preview","displayName":"Lyria 3 Clip Preview","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}},"google/lyria-3-pro-preview":{"metadata":{"displayName":"Lyria 3 Pro Preview","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"structuredOutput":false,"lastUpdated":"2026-03-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","audio"]}},"entry":{"id":"google/lyria-3-pro-preview","displayName":"Lyria 3 Pro Preview","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}},"gryphe/mythomax-l2-13b":{"metadata":{"displayName":"MythoMax 13B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","lifecycle":"active","contextWindow":8192,"maxOutputTokens":3686,"knowledgeCutoff":"2023-06-30","structuredOutput":true,"lastUpdated":"2023-07-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"gryphe/mythomax-l2-13b","displayName":"MythoMax 13B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2023-06-30"}},"ibm-granite/granite-4.0-h-micro":{"metadata":{"displayName":"Granite 4.0 Micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":131000,"maxOutputTokens":117900,"structuredOutput":false,"lastUpdated":"2025-10-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"ibm-granite/granite-4.0-h-micro","displayName":"Granite 4.0 Micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000}},"ibm-granite/granite-4.2-8b":{"metadata":{"displayName":"Granite 4.2 8B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"structuredOutput":true,"lastUpdated":"2026-08-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"ibm-granite/granite-4.2-8b","displayName":"Granite 4.2 8B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","high"],"contextWindow":131072,"defaultContextWindow":131072}},"inception/mercury-2":{"metadata":{"displayName":"Mercury 2","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":128000,"maxOutputTokens":50000,"structuredOutput":true,"lastUpdated":"2026-03-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inception/mercury-2","displayName":"Mercury 2","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high"],"contextWindow":128000,"defaultContextWindow":128000}},"inception/mercury-2.5":{"metadata":{"displayName":"Mercury 2.5","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":260000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-09-08","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inception/mercury-2.5","displayName":"Mercury 2.5","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high"],"contextWindow":260000,"defaultContextWindow":260000}},"inclusionai/ling-3.0-flash":{"metadata":{"displayName":"Ling 3.0 Flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-07-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash","displayName":"Ling 3.0 Flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"inclusionai/ling-3.0-flash-fin":{"metadata":{"displayName":"Ling 3.0 Flash Fin","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2026-08-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash-fin","displayName":"Ling 3.0 Flash Fin","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"inclusionai/ling-3.0-flash-fin:free":{"metadata":{"displayName":"Ling 3.0 Flash Fin (free)","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-08-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash-fin:free","displayName":"Ling 3.0 Flash Fin (free)","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"inclusionai/ling-3.0-flash-sante:free":{"metadata":{"displayName":"Ling 3.0 Flash Sante (free)","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-09-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash-sante:free","displayName":"Ling 3.0 Flash Sante (free)","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"inclusionai/ling-3.0-flash-vl":{"metadata":{"displayName":"Ling 3.0 Flash VL","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash-vl","displayName":"Ling 3.0 Flash VL","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"inclusionai/ling-3.0-flash-vl:free":{"metadata":{"displayName":"Ling 3.0 Flash VL (free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"inclusionai/ling-3.0-flash-vl:free","displayName":"Ling 3.0 Flash VL (free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"inference-net/schematron-v2-small":{"metadata":{"displayName":"Schematron V2 Small","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"structuredOutput":true,"lastUpdated":"2026-09-12","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inference-net/schematron-v2-small","displayName":"Schematron V2 Small","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"inference-net/schematron-v2-turbo":{"metadata":{"displayName":"Schematron V2 Turbo","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"structuredOutput":true,"lastUpdated":"2026-09-12","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"inference-net/schematron-v2-turbo","displayName":"Schematron V2 Turbo","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"kwaipilot/kat-coder-pro-v2":{"metadata":{"displayName":"KAT-Coder-Pro V2","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":144000,"structuredOutput":true,"lastUpdated":"2026-03-27","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"kwaipilot/kat-coder-pro-v2","displayName":"KAT-Coder-Pro V2","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"kwaipilot/kat-coder-pro-v2.5":{"metadata":{"displayName":"KAT-Coder-Pro V2.5","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2026-07-10","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"kwaipilot/kat-coder-pro-v2.5","displayName":"KAT-Coder-Pro V2.5","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"liquid/lfm-2.5-2.6b:free":{"metadata":{"displayName":"LFM2.5-2.6B (free)","description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","lifecycle":"active","contextWindow":65536,"maxOutputTokens":8192,"structuredOutput":true,"lastUpdated":"2026-08-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"liquid/lfm-2.5-2.6b:free","displayName":"LFM2.5-2.6B (free)","description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536}},"mancer/weaver":{"metadata":{"displayName":"Weaver (alpha)","description":"General-purpose chat model for instruction following, writing, and analysis","lifecycle":"active","contextWindow":8000,"maxOutputTokens":6000,"knowledgeCutoff":"2023-06-30","structuredOutput":false,"lastUpdated":"2023-08-02","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mancer/weaver","displayName":"Weaver (alpha)","description":"General-purpose chat model for instruction following, writing, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8000,"defaultContextWindow":8000,"knowledgeCutoff":"2023-06-30"}},"meituan/longcat-2.0":{"metadata":{"displayName":"LongCat 2.0","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":1048756,"maxOutputTokens":262144,"structuredOutput":false,"lastUpdated":"2026-07-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meituan/longcat-2.0","displayName":"LongCat 2.0","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048756,"defaultContextWindow":1048756}},"meta-llama/llama-3.1-70b-instruct":{"metadata":{"displayName":"Llama-3.1-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2023-12","structuredOutput":true,"lastUpdated":"2024-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/llama-3.1-70b-instruct","displayName":"Llama-3.1-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12"}},"meta-llama/llama-3.1-8b-instruct":{"metadata":{"displayName":"Llama-3.1-8B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"knowledgeCutoff":"2023-12","structuredOutput":true,"lastUpdated":"2024-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/llama-3.1-8b-instruct","displayName":"Llama-3.1-8B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12"}},"meta-llama/llama-3.2-1b-instruct":{"metadata":{"displayName":"Llama 3.2 1B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":60000,"maxOutputTokens":54000,"knowledgeCutoff":"2023-12-31","structuredOutput":false,"lastUpdated":"2024-09-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/llama-3.2-1b-instruct","displayName":"Llama 3.2 1B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":60000,"defaultContextWindow":60000,"knowledgeCutoff":"2023-12-31"}},"meta-llama/llama-3.2-3b-instruct":{"metadata":{"displayName":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"knowledgeCutoff":"2023-12-31","structuredOutput":true,"lastUpdated":"2024-09-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/llama-3.2-3b-instruct","displayName":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12-31"}},"meta-llama/llama-3.3-70b-instruct":{"metadata":{"displayName":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2023-12","structuredOutput":true,"lastUpdated":"2024-12-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"meta-llama/llama-3.3-70b-instruct","displayName":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12"}},"meta-llama/llama-4-maverick":{"metadata":{"displayName":"Llama 4 Maverick","description":"Open multimodal Llama model for strong reasoning and fast responses","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":16384,"knowledgeCutoff":"2024-08-31","structuredOutput":true,"lastUpdated":"2025-04-05","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta-llama/llama-4-maverick","displayName":"Llama 4 Maverick","description":"Open multimodal Llama model for strong reasoning and fast responses","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2024-08-31"}},"meta-llama/llama-4-scout":{"metadata":{"displayName":"Llama 4 Scout","description":"Open multimodal Llama model for long-context analysis and efficient agents","lifecycle":"active","contextWindow":1310720,"maxOutputTokens":16384,"knowledgeCutoff":"2024-08-31","structuredOutput":true,"lastUpdated":"2025-04-05","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta-llama/llama-4-scout","displayName":"Llama 4 Scout","description":"Open multimodal Llama model for long-context analysis and efficient agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1310720,"defaultContextWindow":1310720,"knowledgeCutoff":"2024-08-31"}},"meta-llama/llama-guard-4-12b":{"metadata":{"displayName":"Llama Guard 4 12B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"active","contextWindow":163840,"maxOutputTokens":16384,"knowledgeCutoff":"2024-08-31","structuredOutput":false,"lastUpdated":"2025-04-30","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["image","text"],"output":["text"]}},"entry":{"id":"meta-llama/llama-guard-4-12b","displayName":"Llama Guard 4 12B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840,"knowledgeCutoff":"2024-08-31"}},"meta/muse-glimmer-30b":{"metadata":{"displayName":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"knowledgeCutoff":"2026-01-04","structuredOutput":true,"lastUpdated":"2026-08-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"meta/muse-glimmer-30b","displayName":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2026-01-04"}},"meta/muse-spark-1.1":{"metadata":{"displayName":"Muse Spark 1.1","description":"Open Llama multimodal model for image understanding and text reasoning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":943718,"structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"entry":{"id":"meta/muse-spark-1.1","displayName":"Muse Spark 1.1","description":"Open Llama multimodal model for image understanding and text reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"meta/muse-spark-1.2":{"metadata":{"displayName":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":943718,"structuredOutput":true,"lastUpdated":"2026-08-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"entry":{"id":"meta/muse-spark-1.2","displayName":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"meta/muse-spark-1.2-contributor":{"metadata":{"displayName":"Muse Spark 1.2 Contributor","description":"Open Llama multimodal model for image understanding and text reasoning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":943718,"structuredOutput":true,"lastUpdated":"2026-08-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"entry":{"id":"meta/muse-spark-1.2-contributor","displayName":"Muse Spark 1.2 Contributor","description":"Open Llama multimodal model for image understanding and text reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"meta/muse-spark-1.3":{"metadata":{"displayName":"Muse Spark 1.3","description":"Open Llama multimodal model for image understanding and text reasoning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":943718,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"entry":{"id":"meta/muse-spark-1.3","displayName":"Muse Spark 1.3","description":"Open Llama multimodal model for image understanding and text reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"meta/muse-spark-1.3-contributor":{"metadata":{"displayName":"Muse Spark 1.3 Contributor","description":"Open Llama multimodal model for image understanding and text reasoning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":943718,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]}},"entry":{"id":"meta/muse-spark-1.3-contributor","displayName":"Muse Spark 1.3 Contributor","description":"Open Llama multimodal model for image understanding and text reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"microsoft/phi-4":{"metadata":{"displayName":"Phi 4","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","lifecycle":"active","contextWindow":16384,"maxOutputTokens":14745,"knowledgeCutoff":"2024-06-30","structuredOutput":true,"lastUpdated":"2025-01-10","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"microsoft/phi-4","displayName":"Phi 4","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16384,"defaultContextWindow":16384,"knowledgeCutoff":"2024-06-30"}},"microsoft/wizardlm-2-8x22b":{"metadata":{"displayName":"WizardLM-2 8x22B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","lifecycle":"active","contextWindow":65535,"maxOutputTokens":8000,"knowledgeCutoff":"2024-04-30","structuredOutput":false,"lastUpdated":"2024-04-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"microsoft/wizardlm-2-8x22b","displayName":"WizardLM-2 8x22B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":65535,"defaultContextWindow":65535,"knowledgeCutoff":"2024-04-30"}},"minimax/minimax-01":{"metadata":{"displayName":"MiniMax-01","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","lifecycle":"active","contextWindow":1000192,"maxOutputTokens":900172,"knowledgeCutoff":"2024-03-31","structuredOutput":false,"lastUpdated":"2025-01-15","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"minimax/minimax-01","displayName":"MiniMax-01","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000192,"defaultContextWindow":1000192,"knowledgeCutoff":"2024-03-31"}},"minimax/minimax-m1":{"metadata":{"displayName":"MiniMax M1","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":40000,"knowledgeCutoff":"2024-06-30","structuredOutput":false,"lastUpdated":"2025-06-17","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m1","displayName":"MiniMax M1","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-06-30"}},"minimax/minimax-m2":{"metadata":{"displayName":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2025-10-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2","displayName":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"minimax/minimax-m2-her":{"metadata":{"displayName":"MiniMax-M2 Her","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":65536,"maxOutputTokens":2048,"structuredOutput":false,"lastUpdated":"2026-01-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2-her","displayName":"MiniMax-M2 Her","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536}},"minimax/minimax-m2.1":{"metadata":{"displayName":"MiniMax-M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"structuredOutput":false,"lastUpdated":"2025-12-23","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2.1","displayName":"MiniMax-M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"minimax/minimax-m2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","lifecycle":"active","contextWindow":204800,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2.5","displayName":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"minimax/minimax-m2.7":{"metadata":{"displayName":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax/minimax-m2.7","displayName":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"minimax/minimax-m3":{"metadata":{"displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":512000,"structuredOutput":true,"lastUpdated":"2026-06-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"minimax/minimax-m3","displayName":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}},"mistralai/codestral-2508":{"metadata":{"displayName":"Codestral 2508","description":"Mistral coding model for code completion, generation, and developer workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":204800,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-08-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","pdf"],"output":["text"]}},"entry":{"id":"mistralai/codestral-2508","displayName":"Codestral 2508","description":"Mistral coding model for code completion, generation, and developer workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2025-03-31"}},"mistralai/devstral-2512":{"metadata":{"displayName":"Devstral 2","description":"Mistral coding agent model for repository tasks and software engineering workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":209715,"knowledgeCutoff":"2025-12","structuredOutput":true,"lastUpdated":"2025-12-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","pdf"],"output":["text"]}},"entry":{"id":"mistralai/devstral-2512","displayName":"Devstral 2","description":"Mistral coding agent model for repository tasks and software engineering workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-12"}},"mistralai/ministral-14b-2512":{"metadata":{"displayName":"Ministral 3 14B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":209715,"structuredOutput":true,"lastUpdated":"2025-12-02","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistralai/ministral-14b-2512","displayName":"Ministral 3 14B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"mistralai/ministral-3b-2512":{"metadata":{"displayName":"Ministral 3 3B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":104857,"structuredOutput":true,"lastUpdated":"2025-12-02","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistralai/ministral-3b-2512","displayName":"Ministral 3 3B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"mistralai/ministral-8b-2512":{"metadata":{"displayName":"Ministral 3 8B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":209715,"structuredOutput":true,"lastUpdated":"2025-12-02","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistralai/ministral-8b-2512","displayName":"Ministral 3 8B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"mistralai/mistral-large":{"metadata":{"displayName":"Mistral Large","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","lifecycle":"active","contextWindow":128000,"maxOutputTokens":102400,"knowledgeCutoff":"2024-11-30","structuredOutput":true,"lastUpdated":"2024-02-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","pdf"],"output":["text"]}},"entry":{"id":"mistralai/mistral-large","displayName":"Mistral Large","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-11-30"}},"mistralai/mistral-large-2407":{"metadata":{"displayName":"Mistral Large 2407","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","lifecycle":"active","contextWindow":131072,"maxOutputTokens":104857,"knowledgeCutoff":"2024-03-31","structuredOutput":true,"lastUpdated":"2024-11-19","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","pdf"],"output":["text"]}},"entry":{"id":"mistralai/mistral-large-2407","displayName":"Mistral Large 2407","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-03-31"}},"mistralai/mistral-large-2512":{"metadata":{"displayName":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":209715,"knowledgeCutoff":"2024-11","structuredOutput":true,"lastUpdated":"2025-12-02","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"mistralai/mistral-large-2512","displayName":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-11"}},"mistralai/mistral-medium-3":{"metadata":{"displayName":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":104857,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-05-07","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"mistralai/mistral-medium-3","displayName":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-03-31"}},"mistralai/mistral-medium-3-5":{"metadata":{"displayName":"Mistral Medium 3.5","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":209715,"structuredOutput":true,"lastUpdated":"2026-04-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"mistralai/mistral-medium-3-5","displayName":"Mistral Medium 3.5","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","high"],"contextWindow":262144,"defaultContextWindow":262144}},"mistralai/mistral-medium-3.1":{"metadata":{"displayName":"Mistral Medium 3.1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":104857,"knowledgeCutoff":"2025-06-30","structuredOutput":true,"lastUpdated":"2025-08-13","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"mistralai/mistral-medium-3.1","displayName":"Mistral Medium 3.1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-06-30"}},"mistralai/mistral-nemo":{"metadata":{"displayName":"Mistral Nemo","description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2024-07","structuredOutput":true,"lastUpdated":"2024-07-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistralai/mistral-nemo","displayName":"Mistral Nemo","description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-07"}},"mistralai/mistral-saba":{"metadata":{"displayName":"Saba","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":32768,"maxOutputTokens":26214,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-02-17","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","pdf"],"output":["text"]}},"entry":{"id":"mistralai/mistral-saba","displayName":"Saba","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-09-30"}},"mistralai/mistral-small-24b-instruct-2501":{"metadata":{"displayName":"Mistral Small 3","description":"Efficient Mistral model for fast chat, extraction, and production assistants","lifecycle":"active","contextWindow":32768,"maxOutputTokens":16384,"knowledgeCutoff":"2023-10-31","structuredOutput":true,"lastUpdated":"2025-01-30","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mistralai/mistral-small-24b-instruct-2501","displayName":"Mistral Small 3","description":"Efficient Mistral model for fast chat, extraction, and production assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2023-10-31"}},"mistralai/mistral-small-2603":{"metadata":{"displayName":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","lifecycle":"active","contextWindow":262144,"maxOutputTokens":209715,"knowledgeCutoff":"2025-06","structuredOutput":true,"lastUpdated":"2026-03-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistralai/mistral-small-2603","displayName":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","high"],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-06"}},"mistralai/mistral-small-3.1-24b-instruct":{"metadata":{"displayName":"Mistral Small 3.1 24B","description":"Efficient Mistral model for fast chat, extraction, and production assistants","lifecycle":"active","contextWindow":128000,"maxOutputTokens":102400,"knowledgeCutoff":"2023-10-31","structuredOutput":false,"lastUpdated":"2025-03-17","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistralai/mistral-small-3.1-24b-instruct","displayName":"Mistral Small 3.1 24B","description":"Efficient Mistral model for fast chat, extraction, and production assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-10-31"}},"mistralai/mistral-small-3.2-24b-instruct":{"metadata":{"displayName":"Mistral Small 3.2 24B","description":"Efficient Mistral model for fast chat, extraction, and production assistants","lifecycle":"active","contextWindow":256000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-10-31","structuredOutput":true,"lastUpdated":"2025-06-20","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["image","text"],"output":["text"]}},"entry":{"id":"mistralai/mistral-small-3.2-24b-instruct","displayName":"Mistral Small 3.2 24B","description":"Efficient Mistral model for fast chat, extraction, and production assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000,"knowledgeCutoff":"2023-10-31"}},"mistralai/mixtral-8x22b-instruct":{"metadata":{"displayName":"Mixtral 8x22B Instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","lifecycle":"active","contextWindow":65536,"maxOutputTokens":52428,"knowledgeCutoff":"2024-01-31","structuredOutput":true,"lastUpdated":"2024-04-17","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","pdf"],"output":["text"]}},"entry":{"id":"mistralai/mixtral-8x22b-instruct","displayName":"Mixtral 8x22B Instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2024-01-31"}},"mistralai/voxtral-small-24b-2507":{"metadata":{"displayName":"Voxtral Small 24B 2507","description":"Efficient Mistral model for fast chat, extraction, and production assistants","lifecycle":"active","contextWindow":32768,"maxOutputTokens":26214,"structuredOutput":true,"lastUpdated":"2025-07-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","audio","pdf"],"output":["text"]}},"entry":{"id":"mistralai/voxtral-small-24b-2507","displayName":"Voxtral Small 24B 2507","description":"Efficient Mistral model for fast chat, extraction, and production assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"moonshotai/kimi-k2":{"metadata":{"displayName":"Kimi K2 0711","description":"Kimi model for long-context chat, coding, and agentic reasoning","lifecycle":"active","contextWindow":131072,"maxOutputTokens":98304,"knowledgeCutoff":"2024-12-31","structuredOutput":false,"lastUpdated":"2025-07-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2","displayName":"Kimi K2 0711","description":"Kimi model for long-context chat, coding, and agentic reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-12-31"}},"moonshotai/kimi-k2-0905":{"metadata":{"displayName":"Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":98304,"knowledgeCutoff":"2024-12-31","structuredOutput":true,"lastUpdated":"2025-09-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2-0905","displayName":"Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-12-31"}},"moonshotai/kimi-k2-thinking":{"metadata":{"displayName":"Kimi K2 Thinking","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","lifecycle":"active","contextWindow":262144,"maxOutputTokens":98304,"knowledgeCutoff":"2024-08","structuredOutput":true,"lastUpdated":"2025-11-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2-thinking","displayName":"Kimi K2 Thinking","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2024-08"}},"moonshotai/kimi-k2.5":{"metadata":{"displayName":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.5","displayName":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/kimi-k2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.6","displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/kimi-k2.7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k2.7-code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"moonshotai/kimi-k3":{"metadata":{"displayName":"Kimi K3","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":943718,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"moonshotai/kimi-k3","displayName":"Kimi K3","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"morph/morph-v3-fast":{"metadata":{"displayName":"Morph V3 Fast","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":81920,"maxOutputTokens":38000,"structuredOutput":false,"lastUpdated":"2025-07-07","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"morph/morph-v3-fast","displayName":"Morph V3 Fast","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":81920,"defaultContextWindow":81920}},"morph/morph-v3-large":{"metadata":{"displayName":"Morph V3 Large","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2025-07-07","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"morph/morph-v3-large","displayName":"Morph V3 Large","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"nex-agi/nex-n2.5-mini:free":{"metadata":{"displayName":"Nex-N2.5-Mini (free)","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2026-09-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"nex-agi/nex-n2.5-mini:free","displayName":"Nex-N2.5-Mini (free)","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","medium","high"],"contextWindow":262144,"defaultContextWindow":262144}},"nex-agi/nex-n2.5-pro:free":{"metadata":{"displayName":"Nex-N2.5-Pro (free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2026-09-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"nex-agi/nex-n2.5-pro:free","displayName":"Nex-N2.5-Pro (free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","medium","high"],"contextWindow":262144,"defaultContextWindow":262144}},"nousresearch/hermes-3-llama-3.1-405b":{"metadata":{"displayName":"Hermes 3 405B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2023-12-31","structuredOutput":true,"lastUpdated":"2024-08-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nousresearch/hermes-3-llama-3.1-405b","displayName":"Hermes 3 405B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12-31"}},"nousresearch/hermes-3-llama-3.1-70b":{"metadata":{"displayName":"Hermes 3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2023-12-31","structuredOutput":true,"lastUpdated":"2024-08-18","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nousresearch/hermes-3-llama-3.1-70b","displayName":"Hermes 3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12-31"}},"nousresearch/hermes-4-405b":{"metadata":{"displayName":"Hermes 4 405B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"knowledgeCutoff":"2024-08-31","structuredOutput":false,"lastUpdated":"2025-08-26","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nousresearch/hermes-4-405b","displayName":"Hermes 4 405B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-08-31"}},"nvidia/nemotron-3-nano-30b-a3b":{"metadata":{"displayName":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2025-12-15","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-nano-30b-a3b","displayName":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free":{"metadata":{"displayName":"Nemotron 3 Nano Omni (free)","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","lifecycle":"active","contextWindow":256000,"maxOutputTokens":65536,"structuredOutput":false,"lastUpdated":"2026-04-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","displayName":"Nemotron 3 Nano Omni (free)","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"nvidia/nemotron-3-super-120b-a12b":{"metadata":{"displayName":"Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2026-03-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-super-120b-a12b","displayName":"Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium"],"contextWindow":262144,"defaultContextWindow":262144}},"nvidia/nemotron-3-super-120b-a12b:free":{"metadata":{"displayName":"Nemotron 3 Super (free)","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2026-03-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-super-120b-a12b:free","displayName":"Nemotron 3 Super (free)","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium"],"contextWindow":262144,"defaultContextWindow":262144}},"nvidia/nemotron-3-ultra-550b-a55b":{"metadata":{"displayName":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","lifecycle":"active","contextWindow":262144,"maxOutputTokens":182520,"structuredOutput":true,"lastUpdated":"2026-06-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-ultra-550b-a55b","displayName":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["medium","high"],"contextWindow":262144,"defaultContextWindow":262144}},"nvidia/nemotron-3-ultra-550b-a55b:free":{"metadata":{"displayName":"Nemotron 3 Ultra (free)","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":false,"lastUpdated":"2026-06-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3-ultra-550b-a55b:free","displayName":"Nemotron 3 Ultra (free)","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000}},"nvidia/nemotron-3.5-content-safety":{"metadata":{"displayName":"Nemotron 3.5 Content Safety","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"structuredOutput":false,"lastUpdated":"2026-06-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3.5-content-safety","displayName":"Nemotron 3.5 Content Safety","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"nvidia/nemotron-3.5-content-safety:free":{"metadata":{"displayName":"Nemotron 3.5 Content Safety (free)","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":8192,"structuredOutput":false,"lastUpdated":"2026-06-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3.5-content-safety:free","displayName":"Nemotron 3.5 Content Safety (free)","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"nvidia/nemotron-3.5-lightning":{"metadata":{"displayName":"Nemotron 3.5 Lightning 30B A3B","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","contextWindow":262144,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3.5-lightning","displayName":"Nemotron 3.5 Lightning 30B A3B","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"nvidia/nemotron-3.5-lightning:free":{"metadata":{"displayName":"Nemotron 3.5 Lightning (free)","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":false,"lastUpdated":"2026-08-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nvidia/nemotron-3.5-lightning:free","displayName":"Nemotron 3.5 Lightning (free)","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"openai/gpt-3.5-turbo":{"metadata":{"displayName":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":16385,"maxOutputTokens":4096,"knowledgeCutoff":"2021-09-01","structuredOutput":true,"lastUpdated":"2023-11-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-3.5-turbo","displayName":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16385,"defaultContextWindow":16385,"knowledgeCutoff":"2021-09-01"}},"openai/gpt-3.5-turbo-0613":{"metadata":{"displayName":"GPT-3.5 Turbo (older v0613)","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":4095,"maxOutputTokens":3685,"knowledgeCutoff":"2021-09-30","structuredOutput":true,"lastUpdated":"2024-01-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-3.5-turbo-0613","displayName":"GPT-3.5 Turbo (older v0613)","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":4095,"defaultContextWindow":4095,"knowledgeCutoff":"2021-09-30"}},"openai/gpt-3.5-turbo-16k":{"metadata":{"displayName":"GPT-3.5 Turbo 16k","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":16385,"maxOutputTokens":4096,"knowledgeCutoff":"2021-09-30","structuredOutput":true,"lastUpdated":"2023-08-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-3.5-turbo-16k","displayName":"GPT-3.5 Turbo 16k","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16385,"defaultContextWindow":16385,"knowledgeCutoff":"2021-09-30"}},"openai/gpt-3.5-turbo-instruct":{"metadata":{"displayName":"GPT-3.5 Turbo Instruct","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":4095,"maxOutputTokens":3685,"knowledgeCutoff":"2021-09-30","structuredOutput":true,"lastUpdated":"2023-09-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-3.5-turbo-instruct","displayName":"GPT-3.5 Turbo Instruct","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":4095,"defaultContextWindow":4095,"knowledgeCutoff":"2021-09-30"}},"openai/gpt-4":{"metadata":{"displayName":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":8191,"maxOutputTokens":4096,"knowledgeCutoff":"2023-11","structuredOutput":true,"lastUpdated":"2024-04-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-4","displayName":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8191,"defaultContextWindow":8191,"knowledgeCutoff":"2023-11"}},"openai/gpt-4-turbo":{"metadata":{"displayName":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-12","structuredOutput":true,"lastUpdated":"2024-04-09","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openai/gpt-4-turbo","displayName":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-12"}},"openai/gpt-4.1":{"metadata":{"displayName":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","lifecycle":"active","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4.1","displayName":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"openai/gpt-4.1-mini":{"metadata":{"displayName":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","lifecycle":"active","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4.1-mini","displayName":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"openai/gpt-4.1-nano":{"metadata":{"displayName":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","lifecycle":"active","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4.1-nano","displayName":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"openai/gpt-4o":{"metadata":{"displayName":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-08-06","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4o","displayName":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"openai/gpt-4o-2024-05-13":{"metadata":{"displayName":"GPT-4o (2024-05-13)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-05-13","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4o-2024-05-13","displayName":"GPT-4o (2024-05-13)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"openai/gpt-4o-2024-08-06":{"metadata":{"displayName":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-08-06","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4o-2024-08-06","displayName":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"openai/gpt-4o-2024-11-20":{"metadata":{"displayName":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-11-20","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4o-2024-11-20","displayName":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"openai/gpt-4o-mini":{"metadata":{"displayName":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-07-18","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4o-mini","displayName":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"openai/gpt-4o-mini-2024-07-18":{"metadata":{"displayName":"GPT-4o-mini (2024-07-18)","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-10-31","structuredOutput":true,"lastUpdated":"2024-07-18","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-4o-mini-2024-07-18","displayName":"GPT-4o-mini (2024-07-18)","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-10-31"}},"openai/gpt-5":{"metadata":{"displayName":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5","displayName":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5-image":{"metadata":{"displayName":"GPT-5 Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-10-01","structuredOutput":true,"lastUpdated":"2025-10-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"modalities":{"input":["image","text","pdf"],"output":["image","text"]}},"entry":{"id":"openai/gpt-5-image","displayName":"GPT-5 Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2024-10-01"}},"openai/gpt-5-image-mini":{"metadata":{"displayName":"GPT-5 Image Mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2025-10-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"modalities":{"input":["pdf","image","text"],"output":["image","text"]}},"entry":{"id":"openai/gpt-5-image-mini","displayName":"GPT-5 Image Mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":400000,"defaultContextWindow":400000}},"openai/gpt-5-mini":{"metadata":{"displayName":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-05-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5-mini","displayName":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-05-30"}},"openai/gpt-5-nano":{"metadata":{"displayName":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-05-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5-nano","displayName":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-05-30"}},"openai/gpt-5-pro":{"metadata":{"displayName":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-10-06","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high"]},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5-pro","displayName":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5.1":{"metadata":{"displayName":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.1","displayName":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5.1-codex":{"metadata":{"displayName":"GPT-5.1 Codex","description":"Codex GPT for repository edits, code review, and practical software agents","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openai/gpt-5.1-codex","displayName":"GPT-5.1 Codex","description":"Codex GPT for repository edits, code review, and practical software agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5.1-codex-max":{"metadata":{"displayName":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openai/gpt-5.1-codex-max","displayName":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5.1-codex-mini":{"metadata":{"displayName":"GPT-5.1 Codex mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openai/gpt-5.1-codex-mini","displayName":"GPT-5.1 Codex mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2024-09-30"}},"openai/gpt-5.2":{"metadata":{"displayName":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"entry":{"id":"openai/gpt-5.2","displayName":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.2-chat":{"metadata":{"displayName":"GPT-5.2 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","lifecycle":"active","contextWindow":128000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2025-12-10","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"entry":{"id":"openai/gpt-5.2-chat","displayName":"GPT-5.2 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.2-codex":{"metadata":{"displayName":"GPT-5.2 Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openai/gpt-5.2-codex","displayName":"GPT-5.2 Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.2-pro":{"metadata":{"displayName":"GPT-5.2 Pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.2-pro","displayName":"GPT-5.2 Pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.3-codex":{"metadata":{"displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-02-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.3-codex","displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4":{"metadata":{"displayName":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.4","displayName":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4-image-2":{"metadata":{"displayName":"GPT-5.4 Image 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":272000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["image","text","pdf"],"output":["image","text"]}},"entry":{"id":"openai/gpt-5.4-image-2","displayName":"GPT-5.4 Image 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":272000,"defaultContextWindow":272000}},"openai/gpt-5.4-mini":{"metadata":{"displayName":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"entry":{"id":"openai/gpt-5.4-mini","displayName":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4-nano":{"metadata":{"displayName":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"entry":{"id":"openai/gpt-5.4-nano","displayName":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.4-pro":{"metadata":{"displayName":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.4-pro","displayName":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-08-31"}},"openai/gpt-5.5":{"metadata":{"displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.5","displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-12-01"}},"openai/gpt-5.5-pro":{"metadata":{"displayName":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.5-pro","displayName":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-12-01"}},"openai/gpt-5.6-luna":{"metadata":{"displayName":"GPT-5.6 Luna","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-luna","displayName":"GPT-5.6 Luna","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-luna-pro":{"metadata":{"displayName":"GPT-5.6 Luna Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-luna-pro","displayName":"GPT-5.6 Luna Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-sol":{"metadata":{"displayName":"GPT-5.6 Sol","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"],"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-sol","displayName":"GPT-5.6 Sol","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-sol-pro":{"metadata":{"displayName":"GPT-5.6 Sol Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-sol-pro","displayName":"GPT-5.6 Sol Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-terra":{"metadata":{"displayName":"GPT-5.6 Terra","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-terra","displayName":"GPT-5.6 Terra","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-5.6-terra-pro":{"metadata":{"displayName":"GPT-5.6 Terra Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-5.6-terra-pro","displayName":"GPT-5.6 Terra Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"openai/gpt-6-astra":{"metadata":{"displayName":"GPT-6 Astra","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-04-30","structuredOutput":true,"lastUpdated":"2026-09-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-6-astra","displayName":"GPT-6 Astra","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-04-30"}},"openai/gpt-6-astra-pro":{"metadata":{"displayName":"GPT-6 Astra Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-09-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["pdf","image","text"],"output":["text"]}},"entry":{"id":"openai/gpt-6-astra-pro","displayName":"GPT-6 Astra Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1050000,"defaultContextWindow":1050000}},"openai/gpt-audio":{"metadata":{"displayName":"GPT Audio","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","audio"],"output":["text","audio"]}},"entry":{"id":"openai/gpt-audio","displayName":"GPT Audio","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"openai/gpt-audio-mini":{"metadata":{"displayName":"GPT Audio Mini","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","audio"],"output":["text","audio"]}},"entry":{"id":"openai/gpt-audio-mini","displayName":"GPT Audio Mini","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"openai/gpt-chat-latest":{"metadata":{"displayName":"GPT Chat Latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-05-05","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/gpt-chat-latest","displayName":"GPT Chat Latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":400000,"defaultContextWindow":400000}},"openai/gpt-oss-120b":{"metadata":{"displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-120b","displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"openai/gpt-oss-20b":{"metadata":{"displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-20b","displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"openai/gpt-oss-safeguard-20b":{"metadata":{"displayName":"GPT OSS Safeguard 20B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2025-10-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openai/gpt-oss-safeguard-20b","displayName":"GPT OSS Safeguard 20B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"openai/o1":{"metadata":{"displayName":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-12-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/o1","displayName":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2023-09"}},"openai/o1-pro":{"metadata":{"displayName":"o1-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2025-03-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/o1-pro","displayName":"o1-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2023-09"}},"openai/o3":{"metadata":{"displayName":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"openai/o3","displayName":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"openai/o3-mini":{"metadata":{"displayName":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-01-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","pdf"],"output":["text"]}},"entry":{"id":"openai/o3-mini","displayName":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"openai/o3-mini-high":{"metadata":{"displayName":"o3 Mini High","description":"O-series reasoning model for hard analysis, math, coding, and planning","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2023-10-31","structuredOutput":true,"lastUpdated":"2025-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high"]},"modalities":{"input":["text","pdf"],"output":["text"]}},"entry":{"id":"openai/o3-mini-high","displayName":"o3 Mini High","description":"O-series reasoning model for hard analysis, math, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2023-10-31"}},"openai/o3-pro":{"metadata":{"displayName":"o3-pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-06-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","pdf","image"],"output":["text"]}},"entry":{"id":"openai/o3-pro","displayName":"o3-pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"openai/o4-mini":{"metadata":{"displayName":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"entry":{"id":"openai/o4-mini","displayName":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"openai/o4-mini-high":{"metadata":{"displayName":"o4 Mini High","description":"O-series reasoning model for hard analysis, math, coding, and planning","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-06-30","structuredOutput":true,"lastUpdated":"2025-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high"]},"modalities":{"input":["image","text","pdf"],"output":["text"]}},"entry":{"id":"openai/o4-mini-high","displayName":"o4 Mini High","description":"O-series reasoning model for hard analysis, math, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-06-30"}},"openrouter/auto":{"metadata":{"displayName":"Auto Router","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":2000000,"structuredOutput":true,"lastUpdated":"2023-11-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","audio","pdf","video"],"output":["text","image"]}},"entry":{"id":"openrouter/auto","displayName":"Auto Router","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000}},"openrouter/bodybuilder":{"metadata":{"displayName":"Body Builder (beta)","description":"Preview model for early access evaluation, prototyping, and compatibility testing","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"structuredOutput":false,"lastUpdated":"2025-12-05","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openrouter/bodybuilder","displayName":"Body Builder (beta)","description":"Preview model for early access evaluation, prototyping, and compatibility testing","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"openrouter/free":{"metadata":{"displayName":"Free Models Router","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":200000,"inputLimit":200000,"maxOutputTokens":8000,"structuredOutput":true,"lastUpdated":"2026-02-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"openrouter/free","displayName":"Free Models Router","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"inputLimit":200000,"defaultContextWindow":200000,"defaultInputLimit":200000}},"openrouter/fusion":{"metadata":{"displayName":"Fusion","description":"General-purpose chat model for instruction following, writing, and analysis","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"structuredOutput":false,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openrouter/fusion","displayName":"Fusion","description":"General-purpose chat model for instruction following, writing, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"openrouter/pareto-code":{"metadata":{"displayName":"Pareto Code Router","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":200000,"structuredOutput":false,"lastUpdated":"2026-04-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"openrouter/pareto-code","displayName":"Pareto Code Router","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000}},"perceptron/perceptron-mk1":{"metadata":{"displayName":"Perceptron Mk1","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":32768,"maxOutputTokens":8192,"structuredOutput":true,"lastUpdated":"2026-05-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"perceptron/perceptron-mk1","displayName":"Perceptron Mk1","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"perplexity/sonar":{"metadata":{"displayName":"Sonar","description":"Sonar search model for current answers, retrieval, and citation-backed chat","lifecycle":"active","contextWindow":127072,"maxOutputTokens":114364,"structuredOutput":false,"lastUpdated":"2025-01-27","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"perplexity/sonar","displayName":"Sonar","description":"Sonar search model for current answers, retrieval, and citation-backed chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":127072,"defaultContextWindow":127072}},"perplexity/sonar-deep-research":{"metadata":{"displayName":"Sonar Deep Research","description":"Sonar search model for current answers, retrieval, and citation-backed chat","lifecycle":"active","contextWindow":128000,"maxOutputTokens":115200,"structuredOutput":false,"lastUpdated":"2025-03-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"perplexity/sonar-deep-research","displayName":"Sonar Deep Research","description":"Sonar search model for current answers, retrieval, and citation-backed chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"perplexity/sonar-pro":{"metadata":{"displayName":"Sonar Pro","description":"Advanced Sonar search model for deeper research and cited synthesis","lifecycle":"active","contextWindow":200000,"maxOutputTokens":8000,"structuredOutput":false,"lastUpdated":"2025-03-07","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"perplexity/sonar-pro","displayName":"Sonar Pro","description":"Advanced Sonar search model for deeper research and cited synthesis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}},"perplexity/sonar-pro-search":{"metadata":{"displayName":"Sonar Pro Search","description":"Advanced Sonar search model for deeper research and cited synthesis","lifecycle":"active","contextWindow":200000,"maxOutputTokens":8000,"structuredOutput":true,"lastUpdated":"2025-10-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"perplexity/sonar-pro-search","displayName":"Sonar Pro Search","description":"Advanced Sonar search model for deeper research and cited synthesis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000}},"perplexity/sonar-reasoning-pro":{"metadata":{"displayName":"Sonar Reasoning Pro","description":"Web-grounded reasoning model for multi-step research and cited answers","lifecycle":"active","contextWindow":128000,"maxOutputTokens":115200,"structuredOutput":false,"lastUpdated":"2025-03-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"perplexity/sonar-reasoning-pro","displayName":"Sonar Reasoning Pro","description":"Web-grounded reasoning model for multi-step research and cited answers","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"poolside/laguna-s-2.1":{"metadata":{"displayName":"Laguna S 2.1","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":false,"lastUpdated":"2026-07-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"poolside/laguna-s-2.1","displayName":"Laguna S 2.1","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576}},"poolside/laguna-s-2.1:free":{"metadata":{"displayName":"Laguna S 2.1 (free)","description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-07-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"poolside/laguna-s-2.1:free","displayName":"Laguna S 2.1 (free)","description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"poolside/laguna-xs-2.1":{"metadata":{"displayName":"Laguna XS 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"poolside/laguna-xs-2.1","displayName":"Laguna XS 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"poolside/laguna-xs-2.1:free":{"metadata":{"displayName":"Laguna XS 2.1 (free)","description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2026-07-02","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"poolside/laguna-xs-2.1:free","displayName":"Laguna XS 2.1 (free)","description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen-2.5-72b-instruct":{"metadata":{"displayName":"Qwen2.5 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":32768,"maxOutputTokens":16384,"knowledgeCutoff":"2024-06-30","structuredOutput":true,"lastUpdated":"2024-09-19","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen-2.5-72b-instruct","displayName":"Qwen2.5 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-06-30"}},"qwen/qwen-2.5-7b-instruct":{"metadata":{"displayName":"Qwen2.5 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":32768,"maxOutputTokens":29491,"knowledgeCutoff":"2024-06-30","structuredOutput":true,"lastUpdated":"2024-10-16","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen-2.5-7b-instruct","displayName":"Qwen2.5 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-06-30"}},"qwen/qwen-2.5-coder-32b-instruct":{"metadata":{"displayName":"Qwen2.5 Coder 32B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":32768,"maxOutputTokens":29491,"knowledgeCutoff":"2024-06-30","structuredOutput":false,"lastUpdated":"2024-11-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen-2.5-coder-32b-instruct","displayName":"Qwen2.5 Coder 32B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-06-30"}},"qwen/qwen-plus":{"metadata":{"displayName":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-09-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen-plus","displayName":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-04"}},"qwen/qwen-plus-2025-07-28":{"metadata":{"displayName":"Qwen Plus 0728","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":32768,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-09-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen-plus-2025-07-28","displayName":"Qwen Plus 0728","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-03-31"}},"qwen/qwen2.5-vl-72b-instruct":{"metadata":{"displayName":"Qwen2.5 VL 72B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":128000,"maxOutputTokens":115200,"knowledgeCutoff":"2024-06-30","structuredOutput":true,"lastUpdated":"2025-02-01","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen2.5-vl-72b-instruct","displayName":"Qwen2.5 VL 72B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-06-30"}},"qwen/qwen3-14b":{"metadata":{"displayName":"Qwen3 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-04-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-14b","displayName":"Qwen3 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-03-31"}},"qwen/qwen3-235b-a22b":{"metadata":{"displayName":"Qwen3 235B-A22B","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2025-04","structuredOutput":false,"lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-235b-a22b","displayName":"Qwen3 235B-A22B","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen/qwen3-235b-a22b-2507":{"metadata":{"displayName":"Qwen3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"knowledgeCutoff":"2025-06-30","structuredOutput":true,"lastUpdated":"2025-07-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-235b-a22b-2507","displayName":"Qwen3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-06-30"}},"qwen/qwen3-235b-a22b-thinking-2507":{"metadata":{"displayName":"Qwen3 235B A22B Thinking 2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"knowledgeCutoff":"2025-06-30","structuredOutput":false,"lastUpdated":"2025-07-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-235b-a22b-thinking-2507","displayName":"Qwen3 235B A22B Thinking 2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-06-30"}},"qwen/qwen3-30b-a3b":{"metadata":{"displayName":"Qwen3 30B A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-04-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-30b-a3b","displayName":"Qwen3 30B A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"qwen/qwen3-30b-a3b-instruct-2507":{"metadata":{"displayName":"Qwen3 30B A3B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32000,"knowledgeCutoff":"2025-06-30","structuredOutput":true,"lastUpdated":"2025-07-29","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-30b-a3b-instruct-2507","displayName":"Qwen3 30B A3B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-06-30"}},"qwen/qwen3-30b-a3b-thinking-2507":{"metadata":{"displayName":"Qwen3 30B A3B Thinking 2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":81920,"maxOutputTokens":32768,"knowledgeCutoff":"2025-06-30","structuredOutput":false,"lastUpdated":"2025-08-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-30b-a3b-thinking-2507","displayName":"Qwen3 30B A3B Thinking 2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":81920,"defaultContextWindow":81920,"knowledgeCutoff":"2025-06-30"}},"qwen/qwen3-32b":{"metadata":{"displayName":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-32b","displayName":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen/qwen3-8b":{"metadata":{"displayName":"Qwen3 8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2025-03-31","structuredOutput":false,"lastUpdated":"2025-04-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-8b","displayName":"Qwen3 8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-03-31"}},"qwen/qwen3-coder":{"metadata":{"displayName":"Qwen3 Coder 480B A35B","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-06-30","structuredOutput":true,"lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-coder","displayName":"Qwen3 Coder 480B A35B","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-06-30"}},"qwen/qwen3-coder-30b-a3b-instruct":{"metadata":{"displayName":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-coder-30b-a3b-instruct","displayName":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen/qwen3-coder-flash":{"metadata":{"displayName":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":false,"lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-coder-flash","displayName":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen/qwen3-coder-next":{"metadata":{"displayName":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"knowledgeCutoff":"2025-09","structuredOutput":true,"lastUpdated":"2026-02-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-coder-next","displayName":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-09"}},"qwen/qwen3-coder-plus":{"metadata":{"displayName":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-coder-plus","displayName":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen/qwen3-max":{"metadata":{"displayName":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-09-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-max","displayName":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen/qwen3-max-thinking":{"metadata":{"displayName":"Qwen3 Max Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-09","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-max-thinking","displayName":"Qwen3 Max Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen3-next-80b-a3b-instruct":{"metadata":{"displayName":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-next-80b-a3b-instruct","displayName":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen/qwen3-next-80b-a3b-thinking":{"metadata":{"displayName":"Qwen3-Next 80B-A3B (Thinking)","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-09","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-next-80b-a3b-thinking","displayName":"Qwen3-Next 80B-A3B (Thinking)","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen/qwen3-vl-235b-a22b-instruct":{"metadata":{"displayName":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-09-23","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen3-vl-235b-a22b-instruct","displayName":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-03-31"}},"qwen/qwen3-vl-235b-a22b-thinking":{"metadata":{"displayName":"Qwen3 VL 235B A22B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-09-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen3-vl-235b-a22b-thinking","displayName":"Qwen3 VL 235B A22B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-03-31"}},"qwen/qwen3-vl-30b-a3b-instruct":{"metadata":{"displayName":"Qwen3 VL 30B A3B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-10-06","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen3-vl-30b-a3b-instruct","displayName":"Qwen3 VL 30B A3B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-03-31"}},"qwen/qwen3-vl-30b-a3b-thinking":{"metadata":{"displayName":"Qwen3 VL 30B A3B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-10-06","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen3-vl-30b-a3b-thinking","displayName":"Qwen3 VL 30B A3B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-03-31"}},"qwen/qwen3-vl-32b-instruct":{"metadata":{"displayName":"Qwen3 VL 32B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2025-10-23","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen3-vl-32b-instruct","displayName":"Qwen3 VL 32B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"qwen/qwen3-vl-8b-instruct":{"metadata":{"displayName":"Qwen3 VL 8B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2025-10-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["image","text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-vl-8b-instruct","displayName":"Qwen3 VL 8B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen3-vl-8b-thinking":{"metadata":{"displayName":"Qwen3 VL 8B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2025-10-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["image","text"],"output":["text"]}},"entry":{"id":"qwen/qwen3-vl-8b-thinking","displayName":"Qwen3 VL 8B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"qwen/qwen3.5-122b-a10b":{"metadata":{"displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-122b-a10b","displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen3.5-27b":{"metadata":{"displayName":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-27b","displayName":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen3.5-35b-a3b":{"metadata":{"displayName":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-35b-a3b","displayName":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen3.5-397b-a17b":{"metadata":{"displayName":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2026-02-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-397b-a17b","displayName":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen3.5-9b":{"metadata":{"displayName":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-9b","displayName":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen3.5-flash-02-23":{"metadata":{"displayName":"Qwen3.5-Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-25","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-flash-02-23","displayName":"Qwen3.5-Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen/qwen3.5-plus-02-15":{"metadata":{"displayName":"Qwen3.5 Plus 2026-02-15","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-02-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-plus-02-15","displayName":"Qwen3.5 Plus 2026-02-15","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen/qwen3.5-plus-20260420":{"metadata":{"displayName":"Qwen3.5 Plus 2026-04-20","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.5-plus-20260420","displayName":"Qwen3.5 Plus 2026-04-20","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen/qwen3.6-27b":{"metadata":{"displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.6-27b","displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen3.6-35b-a3b":{"metadata":{"displayName":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":true,"lastUpdated":"2026-04-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.6-35b-a3b","displayName":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen/qwen3.6-flash":{"metadata":{"displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.6-flash","displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen/qwen3.6-max-preview":{"metadata":{"displayName":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-04-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3.6-max-preview","displayName":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen/qwen3.6-plus":{"metadata":{"displayName":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.6-plus","displayName":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen/qwen3.7-flash":{"metadata":{"displayName":"Qwen3.7 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"inputLimit":991000,"maxOutputTokens":65536,"structuredOutput":false,"lastUpdated":"2026-07-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.7-flash","displayName":"Qwen3.7 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"inputLimit":991000,"defaultContextWindow":1000000,"defaultInputLimit":991000}},"qwen/qwen3.7-max":{"metadata":{"displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3.7-max","displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen/qwen3.7-plus":{"metadata":{"displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-06-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen/qwen3.7-plus","displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen/qwen3.8-2.4t-a95b":{"metadata":{"displayName":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen/qwen3.8-2.4t-a95b","displayName":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"qwen/qwen3.8-27b":{"metadata":{"displayName":"Qwen3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.8-27b","displayName":"Qwen3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen/qwen3.8-flash":{"metadata":{"displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.8-flash","displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen/qwen3.8-max-0902":{"metadata":{"displayName":"Qwen3.8 Max 0902","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen/qwen3.8-max-0902","displayName":"Qwen3.8 Max 0902","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"rekaai/reka-edge":{"metadata":{"displayName":"Reka Edge","description":"Multimodal model for analyzing text, images, documents, and rich media","lifecycle":"active","contextWindow":16384,"maxOutputTokens":14745,"structuredOutput":true,"lastUpdated":"2026-03-20","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["image","text","video"],"output":["text"]}},"entry":{"id":"rekaai/reka-edge","displayName":"Reka Edge","description":"Multimodal model for analyzing text, images, documents, and rich media","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":16384,"defaultContextWindow":16384}},"rekaai/reka-flash-3":{"metadata":{"displayName":"Reka Flash 3","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":65536,"maxOutputTokens":58982,"knowledgeCutoff":"2025-01-31","structuredOutput":true,"lastUpdated":"2025-03-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"rekaai/reka-flash-3","displayName":"Reka Flash 3","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-01-31"}},"relace/relace-apply-3":{"metadata":{"displayName":"Relace Apply 3","description":"General-purpose chat model for instruction following, writing, and analysis","lifecycle":"active","contextWindow":256000,"maxOutputTokens":128000,"structuredOutput":false,"lastUpdated":"2025-09-26","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"relace/relace-apply-3","displayName":"Relace Apply 3","description":"General-purpose chat model for instruction following, writing, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"relace/relace-search":{"metadata":{"displayName":"Relace Search","description":"Tool-capable chat model for instruction following and agentic application workflows","lifecycle":"active","contextWindow":256000,"maxOutputTokens":128000,"structuredOutput":false,"lastUpdated":"2025-12-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"relace/relace-search","displayName":"Relace Search","description":"Tool-capable chat model for instruction following and agentic application workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"sakana/fugu-max":{"metadata":{"displayName":"Fugu Max","description":"Multi-agent model for routing expert agents across complex analytical tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-09-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"sakana/fugu-max","displayName":"Fugu Max","description":"Multi-agent model for routing expert agents across complex analytical tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"sakana/fugu-ultra":{"metadata":{"displayName":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-06-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"sakana/fugu-ultra","displayName":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"sakana/fugu-ultra-v2":{"metadata":{"displayName":"Fugu Ultra v2","description":"Quality-first multi-agent model for hard research, analysis, and competitions","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-08-28","structuredOutput":true,"lastUpdated":"2026-09-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"sakana/fugu-ultra-v2","displayName":"Fugu Ultra v2","description":"Quality-first multi-agent model for hard research, analysis, and competitions","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-08-28"}},"sakana/sakana-namazu":{"metadata":{"displayName":"Sakana Namazu","description":"Multi-agent model for routing expert agents across complex analytical tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-08-03","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"sakana/sakana-namazu","displayName":"Sakana Namazu","description":"Multi-agent model for routing expert agents across complex analytical tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","high"],"contextWindow":262144,"defaultContextWindow":262144}},"sao10k/l3-lunaris-8b":{"metadata":{"displayName":"Llama 3 8B Lunaris","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":8192,"maxOutputTokens":7372,"knowledgeCutoff":"2023-12-31","structuredOutput":true,"lastUpdated":"2024-08-13","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"sao10k/l3-lunaris-8b","displayName":"Llama 3 8B Lunaris","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2023-12-31"}},"sao10k/l3.1-euryale-70b":{"metadata":{"displayName":"Llama 3.1 Euryale 70B v2.2","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2023-12-31","structuredOutput":true,"lastUpdated":"2024-08-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"sao10k/l3.1-euryale-70b","displayName":"Llama 3.1 Euryale 70B v2.2","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12-31"}},"sao10k/l3.3-euryale-70b":{"metadata":{"displayName":"Llama 3.3 Euryale 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2023-12-31","structuredOutput":true,"lastUpdated":"2024-12-18","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"sao10k/l3.3-euryale-70b","displayName":"Llama 3.3 Euryale 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12-31"}},"stepfun/step-3.5-flash":{"metadata":{"displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":false,"lastUpdated":"2026-02-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"stepfun/step-3.5-flash","displayName":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"stepfun/step-3.7-flash":{"metadata":{"displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","lifecycle":"active","contextWindow":262144,"inputLimit":256000,"maxOutputTokens":230400,"knowledgeCutoff":"2026-03-01","structuredOutput":true,"lastUpdated":"2026-05-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"stepfun/step-3.7-flash","displayName":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":262144,"inputLimit":256000,"defaultContextWindow":262144,"defaultInputLimit":256000,"knowledgeCutoff":"2026-03-01"}},"tencent/hunyuan-a13b-instruct":{"metadata":{"displayName":"Hunyuan A13B Instruct","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"knowledgeCutoff":"2025-03-31","structuredOutput":true,"lastUpdated":"2025-07-08","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hunyuan-a13b-instruct","displayName":"Hunyuan A13B Instruct","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-03-31"}},"tencent/hy-mt2-1.8b":{"metadata":{"displayName":"Hy-MT2-1.8B","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":8192,"maxOutputTokens":4096,"structuredOutput":false,"lastUpdated":"2026-08-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy-mt2-1.8b","displayName":"Hy-MT2-1.8B","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"tencent/hy-mt2-30b-a3b":{"metadata":{"displayName":"Hy-MT2-30B-A3B","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":8192,"maxOutputTokens":4096,"structuredOutput":true,"lastUpdated":"2026-08-20","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy-mt2-30b-a3b","displayName":"Hy-MT2-30B-A3B","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"tencent/hy-mt2-7b":{"metadata":{"displayName":"Hy-MT2-7B","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":8192,"maxOutputTokens":4096,"structuredOutput":true,"lastUpdated":"2026-08-19","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy-mt2-7b","displayName":"Hy-MT2-7B","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"tencent/hy3":{"metadata":{"displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":262144,"inputLimit":192000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-07-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy3","displayName":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","high"],"contextWindow":262144,"inputLimit":192000,"defaultContextWindow":262144,"defaultInputLimit":192000}},"tencent/hy3-preview":{"metadata":{"displayName":"Hy3 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":235929,"structuredOutput":false,"lastUpdated":"2026-04-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy3-preview","displayName":"Hy3 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","high"],"contextWindow":262144,"defaultContextWindow":262144}},"tencent/hy4-preview":{"metadata":{"displayName":"Hy4 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":64000,"structuredOutput":true,"lastUpdated":"2026-08-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tencent/hy4-preview","displayName":"Hy4 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","high"],"contextWindow":1048576,"defaultContextWindow":1048576}},"thedrummer/cydonia-24b-v4.1":{"metadata":{"displayName":"Cydonia 24B V4.1","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"knowledgeCutoff":"2024-04-30","structuredOutput":true,"lastUpdated":"2025-09-27","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"thedrummer/cydonia-24b-v4.1","displayName":"Cydonia 24B V4.1","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04-30"}},"thedrummer/skyfall-36b-v2":{"metadata":{"displayName":"Skyfall 36B V2","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","lifecycle":"active","contextWindow":32768,"maxOutputTokens":29491,"knowledgeCutoff":"2024-06-30","structuredOutput":true,"lastUpdated":"2025-03-10","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"thedrummer/skyfall-36b-v2","displayName":"Skyfall 36B V2","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-06-30"}},"thedrummer/unslopnemo-12b":{"metadata":{"displayName":"UnslopNemo 12B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","lifecycle":"active","contextWindow":1024000,"maxOutputTokens":819200,"knowledgeCutoff":"2024-04-30","structuredOutput":true,"lastUpdated":"2024-11-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"thedrummer/unslopnemo-12b","displayName":"UnslopNemo 12B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1024000,"defaultContextWindow":1024000,"knowledgeCutoff":"2024-04-30"}},"thinkingmachines/inkling":{"metadata":{"displayName":"Inkling","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":471859,"structuredOutput":false,"lastUpdated":"2026-07-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","minimal","low","medium","high","max"]},"modalities":{"input":["text","image","audio"],"output":["text"]}},"entry":{"id":"thinkingmachines/inkling","displayName":"Inkling","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","minimal","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"thinkingmachines/inkling-small":{"metadata":{"displayName":"Inkling Small","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":262144,"structuredOutput":false,"lastUpdated":"2026-07-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","minimal","low","medium","high","max"]},"modalities":{"input":["text","image","audio"],"output":["text"]}},"entry":{"id":"thinkingmachines/inkling-small","displayName":"Inkling Small","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","minimal","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"thinkingmachines/inkling-small:free":{"metadata":{"displayName":"Inkling Small (free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":262144,"structuredOutput":false,"lastUpdated":"2026-07-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","minimal","low","medium","high","max"]},"modalities":{"input":["text","image","audio"],"output":["text"]}},"entry":{"id":"thinkingmachines/inkling-small:free","displayName":"Inkling Small (free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","minimal","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"thinkingmachines/inkling:free":{"metadata":{"displayName":"Inkling (free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":262144,"structuredOutput":false,"lastUpdated":"2026-07-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","minimal","low","medium","high","max"]},"modalities":{"input":["text","image","audio"],"output":["text"]}},"entry":{"id":"thinkingmachines/inkling:free","displayName":"Inkling (free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","minimal","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"undi95/remm-slerp-l2-13b":{"metadata":{"displayName":"ReMM SLERP 13B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","lifecycle":"active","contextWindow":6144,"maxOutputTokens":5529,"knowledgeCutoff":"2023-06-30","structuredOutput":true,"lastUpdated":"2023-07-22","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"undi95/remm-slerp-l2-13b","displayName":"ReMM SLERP 13B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":6144,"defaultContextWindow":6144,"knowledgeCutoff":"2023-06-30"}},"upstage/solar-pro-3":{"metadata":{"displayName":"Solar Pro 3","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":117964,"structuredOutput":true,"lastUpdated":"2026-01-27","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"upstage/solar-pro-3","displayName":"Solar Pro 3","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"upstage/solar-pro4":{"metadata":{"displayName":"Solar Pro 4","description":"Flagship model for demanding analysis, coding, and production agent workflows","lifecycle":"active","contextWindow":524288,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-10","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"upstage/solar-pro4","displayName":"Solar Pro 4","description":"Flagship model for demanding analysis, coding, and production agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":524288,"defaultContextWindow":524288}},"writer/palmyra-x5":{"metadata":{"displayName":"Palmyra X5","description":"General-purpose chat model for instruction following, writing, and analysis","lifecycle":"active","contextWindow":1040000,"maxOutputTokens":8192,"structuredOutput":false,"lastUpdated":"2026-01-21","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"writer/palmyra-x5","displayName":"Palmyra X5","description":"General-purpose chat model for instruction following, writing, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1040000,"defaultContextWindow":1040000}},"x-ai/grok-4.20":{"metadata":{"displayName":"Grok 4.20","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":1800000,"knowledgeCutoff":"2025-09-01","structuredOutput":true,"lastUpdated":"2026-03-31","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"x-ai/grok-4.20","displayName":"Grok 4.20","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":2000000,"defaultContextWindow":2000000,"knowledgeCutoff":"2025-09-01"}},"x-ai/grok-4.20-multi-agent":{"metadata":{"displayName":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":2000000,"maxOutputTokens":1800000,"knowledgeCutoff":"2025-09-01","structuredOutput":true,"lastUpdated":"2026-03-31","capabilities":{"vision":true,"reasoning":true,"functionCalling":false},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"x-ai/grok-4.20-multi-agent","displayName":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":2000000,"defaultContextWindow":2000000,"knowledgeCutoff":"2025-09-01"}},"x-ai/grok-4.3":{"metadata":{"displayName":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":900000,"structuredOutput":true,"lastUpdated":"2026-04-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"x-ai/grok-4.3","displayName":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":1000000,"defaultContextWindow":1000000}},"x-ai/grok-4.5":{"metadata":{"displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","lifecycle":"active","contextWindow":500000,"maxOutputTokens":450000,"structuredOutput":true,"lastUpdated":"2026-07-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"x-ai/grok-4.5","displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":500000,"defaultContextWindow":500000}},"x-ai/grok-4.6":{"metadata":{"displayName":"Grok 4.6","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","lifecycle":"active","contextWindow":500000,"maxOutputTokens":450000,"knowledgeCutoff":"2026-02-01","structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"x-ai/grok-4.6","displayName":"Grok 4.6","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":500000,"defaultContextWindow":500000,"knowledgeCutoff":"2026-02-01"}},"x-ai/grok-build-0.1":{"metadata":{"displayName":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","lifecycle":"active","contextWindow":256000,"maxOutputTokens":230400,"structuredOutput":true,"lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"x-ai/grok-build-0.1","displayName":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"defaultContextWindow":256000}},"xiaomi/mimo-v2.5":{"metadata":{"displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]}},"entry":{"id":"xiaomi/mimo-v2.5","displayName":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2024-12"}},"xiaomi/mimo-v2.5-pro":{"metadata":{"displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":131072,"knowledgeCutoff":"2024-12","structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"xiaomi/mimo-v2.5-pro","displayName":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2024-12"}},"z-ai/glm-4.5":{"metadata":{"displayName":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","lifecycle":"active","contextWindow":131072,"maxOutputTokens":98304,"knowledgeCutoff":"2025-04","structuredOutput":false,"lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.5","displayName":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"z-ai/glm-4.5-air":{"metadata":{"displayName":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":98304,"knowledgeCutoff":"2025-04","structuredOutput":false,"lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.5-air","displayName":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"z-ai/glm-4.5v":{"metadata":{"displayName":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":65536,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","structuredOutput":false,"lastUpdated":"2025-08-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.5v","displayName":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2025-04"}},"z-ai/glm-4.6":{"metadata":{"displayName":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-09-30","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.6","displayName":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"z-ai/glm-4.6v":{"metadata":{"displayName":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","structuredOutput":false,"lastUpdated":"2025-12-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.6v","displayName":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"z-ai/glm-4.7":{"metadata":{"displayName":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2025-12-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.7","displayName":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-04"}},"z-ai/glm-4.7-flash":{"metadata":{"displayName":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","lifecycle":"active","contextWindow":200000,"maxOutputTokens":117964,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-4.7-flash","displayName":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2025-04"}},"z-ai/glm-5":{"metadata":{"displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","lifecycle":"active","contextWindow":204800,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-5","displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"z-ai/glm-5-turbo":{"metadata":{"displayName":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","lifecycle":"active","contextWindow":202752,"maxOutputTokens":131072,"structuredOutput":false,"lastUpdated":"2026-03-16","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-5-turbo","displayName":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"z-ai/glm-5.1":{"metadata":{"displayName":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","lifecycle":"active","contextWindow":204800,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-5.1","displayName":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"z-ai/glm-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","xhigh"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","xhigh"],"contextWindow":1048576,"defaultContextWindow":1048576}},"z-ai/glm-5.3":{"metadata":{"displayName":"GLM-5.3","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":1310720,"maxOutputTokens":943717,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"z-ai/glm-5.3","displayName":"GLM-5.3","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","high","max"],"contextWindow":1310720,"defaultContextWindow":1310720}},"z-ai/glm-5.3-flash":{"metadata":{"displayName":"GLM-5.3-Flash","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":1310720,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"z-ai/glm-5.3-flash","displayName":"GLM-5.3-Flash","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1310720,"defaultContextWindow":1310720}},"z-ai/glm-5v-turbo":{"metadata":{"displayName":"GLM-5V-Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","lifecycle":"active","contextWindow":202752,"maxOutputTokens":131072,"structuredOutput":false,"lastUpdated":"2026-04-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["image","text","video"],"output":["text"]}},"entry":{"id":"z-ai/glm-5v-turbo","displayName":"GLM-5V-Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}}}},"alibaba":{"baseUrl":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","label":"Alibaba","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["qwen3.7-plus","deepseek-v4-flash-0731","glm-5.2","qvq-max","qwen-flash","qwen-max","qwen-omni-turbo","qwen-omni-turbo-realtime","qwen-plus","qwen-plus-character-ja","qwen-turbo","qwen-vl-max","qwen-vl-plus","qwen2-5-14b-instruct","qwen2-5-32b-instruct","qwen2-5-72b-instruct","qwen2-5-7b-instruct","qwen2-5-omni-7b","qwen2-5-vl-72b-instruct","qwen2-5-vl-7b-instruct","qwen3-14b","qwen3-235b-a22b","qwen3-32b","qwen3-8b","qwen3-coder-30b-a3b-instruct","qwen3-coder-480b-a35b-instruct","qwen3-coder-flash","qwen3-coder-plus","qwen3-max","qwen3-next-80b-a3b-instruct","qwen3-next-80b-a3b-thinking","qwen3-omni-flash","qwen3-omni-flash-realtime","qwen3-vl-235b-a22b","qwen3-vl-30b-a3b","qwen3-vl-plus","qwen3.5-122b-a10b","qwen3.5-27b","qwen3.5-35b-a3b","qwen3.5-397b-a17b","qwen3.5-plus","qwen3.6-27b","qwen3.6-35b-a3b","qwen3.6-flash","qwen3.6-max-preview","qwen3.6-plus","qwen3.7-max","qwen3.8-flash","qwen3.8-max","qwq-plus"],"models":{"deepseek-v4-flash-0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash-0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"glm-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","minimal","low","medium","high","xhigh","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","minimal","low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qvq-max":{"metadata":{"displayName":"QVQ Max","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-03-25","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qvq-max","displayName":"QVQ Max","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen-flash":{"metadata":{"displayName":"Qwen Flash","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-flash","displayName":"Qwen Flash","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-04"}},"qwen-max":{"metadata":{"displayName":"Qwen Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","lifecycle":"active","contextWindow":32768,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-01-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-max","displayName":"Qwen Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-04"}},"qwen-mt-plus":{"metadata":{"displayName":"Qwen-MT Plus","description":"Translation model for multilingual conversion, localization, and cross-language workflows","lifecycle":"active","contextWindow":16384,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-mt-plus","displayName":"Qwen-MT Plus","description":"Translation model for multilingual conversion, localization, and cross-language workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16384,"defaultContextWindow":16384,"knowledgeCutoff":"2024-04"}},"qwen-mt-turbo":{"metadata":{"displayName":"Qwen-MT Turbo","description":"Translation model for multilingual conversion, localization, and cross-language workflows","lifecycle":"active","contextWindow":16384,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-mt-turbo","displayName":"Qwen-MT Turbo","description":"Translation model for multilingual conversion, localization, and cross-language workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16384,"defaultContextWindow":16384,"knowledgeCutoff":"2024-04"}},"qwen-omni-turbo":{"metadata":{"displayName":"Qwen-Omni Turbo","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","lifecycle":"active","contextWindow":32768,"maxOutputTokens":2048,"knowledgeCutoff":"2024-04","lastUpdated":"2025-03-26","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","audio","video"],"output":["text","audio"]}},"entry":{"id":"qwen-omni-turbo","displayName":"Qwen-Omni Turbo","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-04"}},"qwen-omni-turbo-realtime":{"metadata":{"displayName":"Qwen-Omni Turbo Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","lifecycle":"active","contextWindow":32768,"maxOutputTokens":2048,"knowledgeCutoff":"2024-04","lastUpdated":"2025-05-08","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","audio"],"output":["text","audio"]}},"entry":{"id":"qwen-omni-turbo-realtime","displayName":"Qwen-Omni Turbo Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-04"}},"qwen-plus":{"metadata":{"displayName":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","lastUpdated":"2025-09-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-plus","displayName":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-04"}},"qwen-plus-character-ja":{"metadata":{"displayName":"Qwen Plus Character (Japanese)","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":8192,"maxOutputTokens":512,"knowledgeCutoff":"2024-04","lastUpdated":"2024-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-plus-character-ja","displayName":"Qwen Plus Character (Japanese)","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2024-04"}},"qwen-turbo":{"metadata":{"displayName":"Qwen Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":16384,"knowledgeCutoff":"2024-04","lastUpdated":"2025-04-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-turbo","displayName":"Qwen Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-04"}},"qwen-vl-max":{"metadata":{"displayName":"Qwen-VL Max","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-08-13","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen-vl-max","displayName":"Qwen-VL Max","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen-vl-ocr":{"metadata":{"displayName":"Qwen-VL OCR","description":"OCR model for extracting structured text from documents and screenshots","lifecycle":"active","contextWindow":34096,"maxOutputTokens":4096,"knowledgeCutoff":"2024-04","lastUpdated":"2025-04-13","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen-vl-ocr","displayName":"Qwen-VL OCR","description":"OCR model for extracting structured text from documents and screenshots","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":34096,"defaultContextWindow":34096,"knowledgeCutoff":"2024-04"}},"qwen-vl-plus":{"metadata":{"displayName":"Qwen-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-08-15","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen-vl-plus","displayName":"Qwen-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-14b-instruct":{"metadata":{"displayName":"Qwen2.5 14B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-14b-instruct","displayName":"Qwen2.5 14B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-32b-instruct":{"metadata":{"displayName":"Qwen2.5 32B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-32b-instruct","displayName":"Qwen2.5 32B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-72b-instruct":{"metadata":{"displayName":"Qwen2.5 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-72b-instruct","displayName":"Qwen2.5 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-7b-instruct":{"metadata":{"displayName":"Qwen2.5 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-7b-instruct","displayName":"Qwen2.5 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-omni-7b":{"metadata":{"displayName":"Qwen2.5-Omni 7B","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","lifecycle":"active","contextWindow":32768,"maxOutputTokens":2048,"knowledgeCutoff":"2024-04","lastUpdated":"2024-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","audio","video"],"output":["text","audio"]}},"entry":{"id":"qwen2-5-omni-7b","displayName":"Qwen2.5-Omni 7B","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-04"}},"qwen2-5-vl-72b-instruct":{"metadata":{"displayName":"Qwen2.5-VL 72B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen2-5-vl-72b-instruct","displayName":"Qwen2.5-VL 72B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-vl-7b-instruct":{"metadata":{"displayName":"Qwen2.5-VL 7B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen2-5-vl-7b-instruct","displayName":"Qwen2.5-VL 7B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen3-14b":{"metadata":{"displayName":"Qwen3 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-14b","displayName":"Qwen3 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-235b-a22b":{"metadata":{"displayName":"Qwen3 235B-A22B","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-235b-a22b","displayName":"Qwen3 235B-A22B","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-32b":{"metadata":{"displayName":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-32b","displayName":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-8b":{"metadata":{"displayName":"Qwen3 8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-8b","displayName":"Qwen3 8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-asr-flash":{"metadata":{"displayName":"Qwen3-ASR Flash","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","contextWindow":53248,"maxOutputTokens":4096,"knowledgeCutoff":"2024-04","lastUpdated":"2025-09-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"qwen3-asr-flash","displayName":"Qwen3-ASR Flash","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":53248,"defaultContextWindow":53248,"knowledgeCutoff":"2024-04"}},"qwen3-coder-30b-a3b-instruct":{"metadata":{"displayName":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-30b-a3b-instruct","displayName":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3-coder-480b-a35b-instruct":{"metadata":{"displayName":"Qwen3-Coder 480B-A35B Instruct","description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-480b-a35b-instruct","displayName":"Qwen3-Coder 480B-A35B Instruct","description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3-coder-flash":{"metadata":{"displayName":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-flash","displayName":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3-coder-plus":{"metadata":{"displayName":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-plus","displayName":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-04"}},"qwen3-livetranslate-flash-realtime":{"metadata":{"displayName":"Qwen3-LiveTranslate Flash Realtime","description":"Speech generation model for controllable voice, narration, and audio delivery","lifecycle":"active","contextWindow":53248,"maxOutputTokens":4096,"knowledgeCutoff":"2024-04","lastUpdated":"2025-09-22","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image","audio","video"],"output":["text","audio"]}},"entry":{"id":"qwen3-livetranslate-flash-realtime","displayName":"Qwen3-LiveTranslate Flash Realtime","description":"Speech generation model for controllable voice, narration, and audio delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":53248,"defaultContextWindow":53248,"knowledgeCutoff":"2024-04"}},"qwen3-max":{"metadata":{"displayName":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-max","displayName":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3-next-80b-a3b-instruct":{"metadata":{"displayName":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-next-80b-a3b-instruct","displayName":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-next-80b-a3b-thinking":{"metadata":{"displayName":"Qwen3-Next 80B-A3B (Thinking)","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-next-80b-a3b-thinking","displayName":"Qwen3-Next 80B-A3B (Thinking)","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-omni-flash":{"metadata":{"displayName":"Qwen3-Omni Flash","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","lifecycle":"active","contextWindow":65536,"maxOutputTokens":16384,"knowledgeCutoff":"2024-04","lastUpdated":"2025-09-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video"],"output":["text","audio"]}},"entry":{"id":"qwen3-omni-flash","displayName":"Qwen3-Omni Flash","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2024-04"}},"qwen3-omni-flash-realtime":{"metadata":{"displayName":"Qwen3-Omni Flash Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","lifecycle":"active","contextWindow":65536,"maxOutputTokens":16384,"knowledgeCutoff":"2024-04","lastUpdated":"2025-09-15","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","audio","video"],"output":["text","audio"]}},"entry":{"id":"qwen3-omni-flash-realtime","displayName":"Qwen3-Omni Flash Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2024-04"}},"qwen3-vl-235b-a22b":{"metadata":{"displayName":"Qwen3-VL 235B-A22B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen3-vl-235b-a22b","displayName":"Qwen3-VL 235B-A22B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-vl-30b-a3b":{"metadata":{"displayName":"Qwen3-VL 30B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen3-vl-30b-a3b","displayName":"Qwen3-VL 30B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-vl-plus":{"metadata":{"displayName":"Qwen3-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen3-vl-plus","displayName":"Qwen3-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3.5-122b-a10b":{"metadata":{"displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"qwen3.5-122b-a10b","displayName":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen3.5-27b":{"metadata":{"displayName":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"qwen3.5-27b","displayName":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen3.5-35b-a3b":{"metadata":{"displayName":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"qwen3.5-35b-a3b","displayName":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen3.5-397b-a17b":{"metadata":{"displayName":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"qwen3.5-397b-a17b","displayName":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen3.5-plus":{"metadata":{"displayName":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.5-plus","displayName":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.6-27b":{"metadata":{"displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-22","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"qwen3.6-27b","displayName":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen3.6-35b-a3b":{"metadata":{"displayName":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]}},"entry":{"id":"qwen3.6-35b-a3b","displayName":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen3.6-flash":{"metadata":{"displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-flash","displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.6-max-preview":{"metadata":{"displayName":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-04-20","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3.6-max-preview","displayName":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3.6-plus":{"metadata":{"displayName":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-plus","displayName":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.7-max":{"metadata":{"displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3.7-max","displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.7-plus":{"metadata":{"displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-06-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.7-plus","displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.8-flash":{"metadata":{"displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.8-flash","displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.8-max":{"metadata":{"displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-03","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"qwen3.8-max","displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwq-plus":{"metadata":{"displayName":"QwQ Plus","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-03-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwq-plus","displayName":"QwQ Plus","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}}}},"alibaba-cn":{"baseUrl":"https://dashscope.aliyuncs.com/compatible-mode/v1","label":"Alibaba (China)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["qwen3.8-max","deepseek-r1","deepseek-r1-0528","deepseek-r1-distill-llama-70b","deepseek-r1-distill-llama-8b","deepseek-r1-distill-qwen-1-5b","deepseek-r1-distill-qwen-14b","deepseek-r1-distill-qwen-32b","deepseek-r1-distill-qwen-7b","deepseek-v3","deepseek-v3-1","deepseek-v3-2-exp","deepseek-v4-flash","deepseek-v4-pro","glm-5","glm-5.1","glm-5.2","kimi-k2-thinking","kimi-k2.5","kimi-k2.6","kimi/kimi-k2.5","MiniMax-M2.5","MiniMax/MiniMax-M2.7","moonshot-kimi-k2-instruct","qvq-max","qwen-deep-research","qwen-doc-turbo","qwen-flash","qwen-long","qwen-math-plus","qwen-math-turbo","qwen-max","qwen-omni-turbo","qwen-omni-turbo-realtime","qwen-plus","qwen-plus-character","qwen-turbo","qwen-vl-max","qwen-vl-plus","qwen2-5-14b-instruct","qwen2-5-32b-instruct","qwen2-5-72b-instruct","qwen2-5-7b-instruct","qwen2-5-coder-32b-instruct","qwen2-5-coder-7b-instruct","qwen2-5-math-72b-instruct","qwen2-5-math-7b-instruct","qwen2-5-omni-7b","qwen2-5-vl-72b-instruct","qwen2-5-vl-7b-instruct","qwen3-14b","qwen3-235b-a22b","qwen3-32b","qwen3-8b","qwen3-coder-30b-a3b-instruct","qwen3-coder-480b-a35b-instruct","qwen3-coder-flash","qwen3-coder-plus","qwen3-max","qwen3-next-80b-a3b-instruct","qwen3-next-80b-a3b-thinking","qwen3-omni-flash","qwen3-omni-flash-realtime","qwen3-vl-235b-a22b","qwen3-vl-30b-a3b","qwen3-vl-plus","qwen3.5-397b-a17b","qwen3.5-flash","qwen3.5-plus","qwen3.6-flash","qwen3.6-max-preview","qwen3.6-plus","qwen3.7-flash","qwen3.7-max","qwen3.7-plus","qwen3.8-flash","qwq-32b","qwq-plus","siliconflow/deepseek-r1-0528","siliconflow/deepseek-v3-0324","siliconflow/deepseek-v3.1-terminus","siliconflow/deepseek-v3.2"],"models":{"deepseek-r1":{"metadata":{"displayName":"DeepSeek R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-r1","displayName":"DeepSeek R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"deepseek-r1-0528":{"metadata":{"displayName":"DeepSeek R1 0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"lastUpdated":"2025-05-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-r1-0528","displayName":"DeepSeek R1 0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"deepseek-r1-distill-llama-70b":{"metadata":{"displayName":"DeepSeek R1 Distill Llama 70B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","lifecycle":"active","contextWindow":32768,"maxOutputTokens":16384,"lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-r1-distill-llama-70b","displayName":"DeepSeek R1 Distill Llama 70B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"deepseek-r1-distill-llama-8b":{"metadata":{"displayName":"DeepSeek R1 Distill Llama 8B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","lifecycle":"active","contextWindow":32768,"maxOutputTokens":16384,"lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-r1-distill-llama-8b","displayName":"DeepSeek R1 Distill Llama 8B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"deepseek-r1-distill-qwen-1-5b":{"metadata":{"displayName":"DeepSeek R1 Distill Qwen 1.5B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":32768,"maxOutputTokens":16384,"lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-r1-distill-qwen-1-5b","displayName":"DeepSeek R1 Distill Qwen 1.5B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"deepseek-r1-distill-qwen-14b":{"metadata":{"displayName":"DeepSeek R1 Distill Qwen 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":32768,"maxOutputTokens":16384,"lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-r1-distill-qwen-14b","displayName":"DeepSeek R1 Distill Qwen 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"deepseek-r1-distill-qwen-32b":{"metadata":{"displayName":"DeepSeek R1 Distill Qwen 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":32768,"maxOutputTokens":16384,"lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-r1-distill-qwen-32b","displayName":"DeepSeek R1 Distill Qwen 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"deepseek-r1-distill-qwen-7b":{"metadata":{"displayName":"DeepSeek R1 Distill Qwen 7B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":32768,"maxOutputTokens":16384,"lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-r1-distill-qwen-7b","displayName":"DeepSeek R1 Distill Qwen 7B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"deepseek-v3":{"metadata":{"displayName":"DeepSeek V3","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":65536,"maxOutputTokens":8192,"lastUpdated":"2024-12-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v3","displayName":"DeepSeek V3","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536}},"deepseek-v3-1":{"metadata":{"displayName":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v3-1","displayName":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"deepseek-v3-2-exp":{"metadata":{"displayName":"DeepSeek V3.2 Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v3-2-exp","displayName":"DeepSeek V3.2 Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash","displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-pro","displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"glm-5":{"metadata":{"displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":16384,"lastUpdated":"2026-02-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5","displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"glm-5.1":{"metadata":{"displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-04-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.1","displayName":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"glm-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"kimi-k2-thinking":{"metadata":{"displayName":"Moonshot Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-11-06","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"kimi-k2-thinking","displayName":"Moonshot Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"kimi-k2.5":{"metadata":{"displayName":"Moonshot Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","structuredOutput":false,"lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.5","displayName":"Moonshot Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k2.6":{"metadata":{"displayName":"Moonshot Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":16384,"knowledgeCutoff":"2025-01","structuredOutput":false,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.6","displayName":"Moonshot Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi/kimi-k2.5":{"metadata":{"displayName":"kimi/kimi-k2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi/kimi-k2.5","displayName":"kimi/kimi-k2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"MiniMax-M2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.5","displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"MiniMax/MiniMax-M2.7":{"metadata":{"displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax/MiniMax-M2.7","displayName":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":204800,"defaultContextWindow":204800}},"moonshot-kimi-k2-instruct":{"metadata":{"displayName":"Moonshot Kimi K2 Instruct","description":"Kimi model for long-context chat, coding, and agentic reasoning","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"structuredOutput":false,"lastUpdated":"2025-01-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"moonshot-kimi-k2-instruct","displayName":"Moonshot Kimi K2 Instruct","description":"Kimi model for long-context chat, coding, and agentic reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072}},"qvq-max":{"metadata":{"displayName":"QVQ Max","description":"Multimodal reasoning model for visual analysis, planning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-03-25","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qvq-max","displayName":"QVQ Max","description":"Multimodal reasoning model for visual analysis, planning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen-deep-research":{"metadata":{"displayName":"Qwen Deep Research","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","lastUpdated":"2024-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-deep-research","displayName":"Qwen Deep Research","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-04"}},"qwen-doc-turbo":{"metadata":{"displayName":"Qwen Doc Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-doc-turbo","displayName":"Qwen Doc Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen-flash":{"metadata":{"displayName":"Qwen Flash","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-flash","displayName":"Qwen Flash","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-04"}},"qwen-long":{"metadata":{"displayName":"Qwen Long","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":10000000,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-01-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-long","displayName":"Qwen Long","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":10000000,"defaultContextWindow":10000000,"knowledgeCutoff":"2024-04"}},"qwen-math-plus":{"metadata":{"displayName":"Qwen Math Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":4096,"maxOutputTokens":3072,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09-19","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-math-plus","displayName":"Qwen Math Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":4096,"defaultContextWindow":4096,"knowledgeCutoff":"2024-04"}},"qwen-math-turbo":{"metadata":{"displayName":"Qwen Math Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","lifecycle":"active","contextWindow":4096,"maxOutputTokens":3072,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09-19","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-math-turbo","displayName":"Qwen Math Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":4096,"defaultContextWindow":4096,"knowledgeCutoff":"2024-04"}},"qwen-max":{"metadata":{"displayName":"Qwen Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-01-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-max","displayName":"Qwen Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen-mt-plus":{"metadata":{"displayName":"Qwen-MT Plus","description":"Translation model for multilingual conversion, localization, and cross-language workflows","lifecycle":"active","contextWindow":16384,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-mt-plus","displayName":"Qwen-MT Plus","description":"Translation model for multilingual conversion, localization, and cross-language workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16384,"defaultContextWindow":16384,"knowledgeCutoff":"2024-04"}},"qwen-mt-turbo":{"metadata":{"displayName":"Qwen-MT Turbo","description":"Translation model for multilingual conversion, localization, and cross-language workflows","lifecycle":"active","contextWindow":16384,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-mt-turbo","displayName":"Qwen-MT Turbo","description":"Translation model for multilingual conversion, localization, and cross-language workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16384,"defaultContextWindow":16384,"knowledgeCutoff":"2024-04"}},"qwen-omni-turbo":{"metadata":{"displayName":"Qwen-Omni Turbo","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","lifecycle":"active","contextWindow":32768,"maxOutputTokens":2048,"knowledgeCutoff":"2024-04","lastUpdated":"2025-03-26","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","audio","video"],"output":["text","audio"]}},"entry":{"id":"qwen-omni-turbo","displayName":"Qwen-Omni Turbo","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-04"}},"qwen-omni-turbo-realtime":{"metadata":{"displayName":"Qwen-Omni Turbo Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","lifecycle":"active","contextWindow":32768,"maxOutputTokens":2048,"knowledgeCutoff":"2024-04","lastUpdated":"2025-05-08","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","audio"],"output":["text","audio"]}},"entry":{"id":"qwen-omni-turbo-realtime","displayName":"Qwen-Omni Turbo Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-04"}},"qwen-plus":{"metadata":{"displayName":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","lastUpdated":"2025-09-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-plus","displayName":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-04"}},"qwen-plus-character":{"metadata":{"displayName":"Qwen Plus Character","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":32768,"maxOutputTokens":4096,"knowledgeCutoff":"2024-04","lastUpdated":"2024-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-plus-character","displayName":"Qwen Plus Character","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-04"}},"qwen-turbo":{"metadata":{"displayName":"Qwen Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":16384,"knowledgeCutoff":"2024-04","lastUpdated":"2025-07-15","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen-turbo","displayName":"Qwen Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2024-04"}},"qwen-vl-max":{"metadata":{"displayName":"Qwen-VL Max","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-08-13","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen-vl-max","displayName":"Qwen-VL Max","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen-vl-ocr":{"metadata":{"displayName":"Qwen-VL OCR","description":"OCR model for extracting structured text from documents and screenshots","lifecycle":"active","contextWindow":34096,"maxOutputTokens":4096,"knowledgeCutoff":"2024-04","lastUpdated":"2025-04-13","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen-vl-ocr","displayName":"Qwen-VL OCR","description":"OCR model for extracting structured text from documents and screenshots","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":34096,"defaultContextWindow":34096,"knowledgeCutoff":"2024-04"}},"qwen-vl-plus":{"metadata":{"displayName":"Qwen-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-08-15","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen-vl-plus","displayName":"Qwen-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-14b-instruct":{"metadata":{"displayName":"Qwen2.5 14B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-14b-instruct","displayName":"Qwen2.5 14B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-32b-instruct":{"metadata":{"displayName":"Qwen2.5 32B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-32b-instruct","displayName":"Qwen2.5 32B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-72b-instruct":{"metadata":{"displayName":"Qwen2.5 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-72b-instruct","displayName":"Qwen2.5 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-7b-instruct":{"metadata":{"displayName":"Qwen2.5 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-7b-instruct","displayName":"Qwen2.5 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-coder-32b-instruct":{"metadata":{"displayName":"Qwen2.5-Coder 32B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-coder-32b-instruct","displayName":"Qwen2.5-Coder 32B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-coder-7b-instruct":{"metadata":{"displayName":"Qwen2.5-Coder 7B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-11","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-coder-7b-instruct","displayName":"Qwen2.5-Coder 7B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-math-72b-instruct":{"metadata":{"displayName":"Qwen2.5-Math 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":4096,"maxOutputTokens":3072,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-math-72b-instruct","displayName":"Qwen2.5-Math 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":4096,"defaultContextWindow":4096,"knowledgeCutoff":"2024-04"}},"qwen2-5-math-7b-instruct":{"metadata":{"displayName":"Qwen2.5-Math 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":4096,"maxOutputTokens":3072,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen2-5-math-7b-instruct","displayName":"Qwen2.5-Math 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":4096,"defaultContextWindow":4096,"knowledgeCutoff":"2024-04"}},"qwen2-5-omni-7b":{"metadata":{"displayName":"Qwen2.5-Omni 7B","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","lifecycle":"active","contextWindow":32768,"maxOutputTokens":2048,"knowledgeCutoff":"2024-04","lastUpdated":"2024-12","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","audio","video"],"output":["text","audio"]}},"entry":{"id":"qwen2-5-omni-7b","displayName":"Qwen2.5-Omni 7B","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768,"knowledgeCutoff":"2024-04"}},"qwen2-5-vl-72b-instruct":{"metadata":{"displayName":"Qwen2.5-VL 72B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen2-5-vl-72b-instruct","displayName":"Qwen2.5-VL 72B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen2-5-vl-7b-instruct":{"metadata":{"displayName":"Qwen2.5-VL 7B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-09","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen2-5-vl-7b-instruct","displayName":"Qwen2.5-VL 7B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwen3-14b":{"metadata":{"displayName":"Qwen3 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-14b","displayName":"Qwen3 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-235b-a22b":{"metadata":{"displayName":"Qwen3 235B-A22B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-235b-a22b","displayName":"Qwen3 235B-A22B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-32b":{"metadata":{"displayName":"Qwen3 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-32b","displayName":"Qwen3 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-8b":{"metadata":{"displayName":"Qwen3 8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-8b","displayName":"Qwen3 8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-asr-flash":{"metadata":{"displayName":"Qwen3-ASR Flash","description":"Speech transcription model for accurate audio-to-text and captioning workflows","lifecycle":"active","contextWindow":53248,"maxOutputTokens":4096,"knowledgeCutoff":"2024-04","lastUpdated":"2025-09-08","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["audio"],"output":["text"]}},"entry":{"id":"qwen3-asr-flash","displayName":"Qwen3-ASR Flash","description":"Speech transcription model for accurate audio-to-text and captioning workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":53248,"defaultContextWindow":53248,"knowledgeCutoff":"2024-04"}},"qwen3-coder-30b-a3b-instruct":{"metadata":{"displayName":"Qwen3-Coder 30B-A3B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-30b-a3b-instruct","displayName":"Qwen3-Coder 30B-A3B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3-coder-480b-a35b-instruct":{"metadata":{"displayName":"Qwen3-Coder 480B-A35B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-480b-a35b-instruct","displayName":"Qwen3-Coder 480B-A35B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3-coder-flash":{"metadata":{"displayName":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-28","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-flash","displayName":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3-coder-plus":{"metadata":{"displayName":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-plus","displayName":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-04"}},"qwen3-max":{"metadata":{"displayName":"Qwen3 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-max","displayName":"Qwen3 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3-next-80b-a3b-instruct":{"metadata":{"displayName":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-next-80b-a3b-instruct","displayName":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-next-80b-a3b-thinking":{"metadata":{"displayName":"Qwen3-Next 80B-A3B (Thinking)","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-next-80b-a3b-thinking","displayName":"Qwen3-Next 80B-A3B (Thinking)","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-omni-flash":{"metadata":{"displayName":"Qwen3-Omni Flash","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","lifecycle":"active","contextWindow":65536,"maxOutputTokens":16384,"knowledgeCutoff":"2024-04","lastUpdated":"2025-09-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","audio","video"],"output":["text","audio"]}},"entry":{"id":"qwen3-omni-flash","displayName":"Qwen3-Omni Flash","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2024-04"}},"qwen3-omni-flash-realtime":{"metadata":{"displayName":"Qwen3-Omni Flash Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","lifecycle":"active","contextWindow":65536,"maxOutputTokens":16384,"knowledgeCutoff":"2024-04","lastUpdated":"2025-09-15","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","audio"],"output":["text","audio"]}},"entry":{"id":"qwen3-omni-flash-realtime","displayName":"Qwen3-Omni Flash Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":65536,"defaultContextWindow":65536,"knowledgeCutoff":"2024-04"}},"qwen3-vl-235b-a22b":{"metadata":{"displayName":"Qwen3-VL 235B-A22B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen3-vl-235b-a22b","displayName":"Qwen3-VL 235B-A22B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-vl-30b-a3b":{"metadata":{"displayName":"Qwen3-VL 30B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen3-vl-30b-a3b","displayName":"Qwen3-VL 30B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"qwen3-vl-plus":{"metadata":{"displayName":"Qwen3-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2025-09-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen3-vl-plus","displayName":"Qwen3-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3.5-397b-a17b":{"metadata":{"displayName":"Qwen3.5 397B-A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.5-397b-a17b","displayName":"Qwen3.5 397B-A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3.5-flash":{"metadata":{"displayName":"Qwen3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-02-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.5-flash","displayName":"Qwen3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.5-plus":{"metadata":{"displayName":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.5-plus","displayName":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.6-flash":{"metadata":{"displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-flash","displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.6-max-preview":{"metadata":{"displayName":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","lifecycle":"active","contextWindow":245800,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3.6-max-preview","displayName":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":245800,"defaultContextWindow":245800}},"qwen3.6-plus":{"metadata":{"displayName":"Qwen3.6 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-plus","displayName":"Qwen3.6 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.7-flash":{"metadata":{"displayName":"Qwen3.7 Flash","description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","lifecycle":"active","contextWindow":1000000,"inputLimit":991000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-07-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.7-flash","displayName":"Qwen3.7 Flash","description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"inputLimit":991000,"defaultContextWindow":1000000,"defaultInputLimit":991000}},"qwen3.7-max":{"metadata":{"displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3.7-max","displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.7-plus":{"metadata":{"displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-04","lastUpdated":"2026-06-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.7-plus","displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.8-flash":{"metadata":{"displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.8-flash","displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.8-max":{"metadata":{"displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-03","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"qwen3.8-max","displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwq-32b":{"metadata":{"displayName":"QwQ 32B","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2024-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwq-32b","displayName":"QwQ 32B","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"qwq-plus":{"metadata":{"displayName":"QwQ Plus","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":131072,"maxOutputTokens":8192,"knowledgeCutoff":"2024-04","lastUpdated":"2025-03-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwq-plus","displayName":"QwQ Plus","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2024-04"}},"siliconflow/deepseek-r1-0528":{"metadata":{"displayName":"siliconflow/deepseek-r1-0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","lifecycle":"active","contextWindow":163840,"maxOutputTokens":32768,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"siliconflow/deepseek-r1-0528","displayName":"siliconflow/deepseek-r1-0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840}},"siliconflow/deepseek-v3-0324":{"metadata":{"displayName":"siliconflow/deepseek-v3-0324","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":163840,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"siliconflow/deepseek-v3-0324","displayName":"siliconflow/deepseek-v3-0324","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840}},"siliconflow/deepseek-v3.1-terminus":{"metadata":{"displayName":"siliconflow/deepseek-v3.1-terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2025-11-25","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"siliconflow/deepseek-v3.1-terminus","displayName":"siliconflow/deepseek-v3.1-terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840}},"siliconflow/deepseek-v3.2":{"metadata":{"displayName":"siliconflow/deepseek-v3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":163840,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2025-12-03","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"siliconflow/deepseek-v3.2","displayName":"siliconflow/deepseek-v3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":163840,"defaultContextWindow":163840}},"tongyi-intent-detect-v3":{"metadata":{"displayName":"Tongyi Intent Detect V3","description":"General-purpose chat model for instruction following, writing, and analysis","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1024,"knowledgeCutoff":"2024-04","lastUpdated":"2024-01","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"tongyi-intent-detect-v3","displayName":"Tongyi Intent Detect V3","description":"General-purpose chat model for instruction following, writing, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2024-04"}}}},"alibaba-coding-plan-cn":{"baseUrl":"https://coding.dashscope.aliyuncs.com/v1","label":"Alibaba Coding Plan (China)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["qwen3.7-plus","qwen3.7-max","qwen3.6-plus","qwen3.6-flash","qwen3.5-plus","qwen3-max-2026-01-23","qwen3-coder-next","qwen3-coder-plus","glm-5","glm-4.7","kimi-k2.5","MiniMax-M2.5"],"models":{"glm-4.7":{"metadata":{"displayName":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","lastUpdated":"2025-12-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.7","displayName":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752,"knowledgeCutoff":"2025-04"}},"glm-5":{"metadata":{"displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":16384,"lastUpdated":"2026-02-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5","displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"kimi-k2.5":{"metadata":{"displayName":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"kimi-k2.5","displayName":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"MiniMax-M2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":196608,"maxOutputTokens":24576,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.5","displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":196608,"defaultContextWindow":196608}},"qwen3-coder-next":{"metadata":{"displayName":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-next","displayName":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen3-coder-plus":{"metadata":{"displayName":"Qwen3 Coder Plus","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-plus","displayName":"Qwen3 Coder Plus","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3-max-2026-01-23":{"metadata":{"displayName":"Qwen3 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2026-01-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-max-2026-01-23","displayName":"Qwen3 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3.5-plus":{"metadata":{"displayName":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen3.5-plus","displayName":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.6-flash":{"metadata":{"displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-flash","displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.6-plus":{"metadata":{"displayName":"Qwen3.6 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-plus","displayName":"Qwen3.6 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.7-max":{"metadata":{"displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3.7-max","displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.7-plus":{"metadata":{"displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-04","lastUpdated":"2026-06-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.7-plus","displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}}}},"alibaba-coding-plan":{"baseUrl":"https://coding-intl.dashscope.aliyuncs.com/v1","label":"Alibaba Coding Plan","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["qwen3.7-plus","qwen3.7-max","qwen3.6-plus","qwen3.6-flash","qwen3.5-plus","qwen3-max-2026-01-23","qwen3-coder-next","qwen3-coder-plus","glm-5","glm-4.7","kimi-k2.5","MiniMax-M2.5"],"models":{"glm-4.7":{"metadata":{"displayName":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":16384,"knowledgeCutoff":"2025-04","lastUpdated":"2025-12-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-4.7","displayName":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752,"knowledgeCutoff":"2025-04"}},"glm-5":{"metadata":{"displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":16384,"lastUpdated":"2026-02-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5","displayName":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"kimi-k2.5":{"metadata":{"displayName":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-01","lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.5","displayName":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"MiniMax-M2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":196608,"inputLimit":196601,"maxOutputTokens":24576,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.5","displayName":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":196608,"inputLimit":196601,"defaultContextWindow":196608,"defaultInputLimit":196601}},"qwen3-coder-next":{"metadata":{"displayName":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-02-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-next","displayName":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"qwen3-coder-plus":{"metadata":{"displayName":"Qwen3 Coder Plus","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2025-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-coder-plus","displayName":"Qwen3 Coder Plus","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3-max-2026-01-23":{"metadata":{"displayName":"Qwen3 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","lifecycle":"active","contextWindow":262144,"maxOutputTokens":32768,"knowledgeCutoff":"2025-04","lastUpdated":"2026-01-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3-max-2026-01-23","displayName":"Qwen3 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-04"}},"qwen3.5-plus":{"metadata":{"displayName":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-02-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.5-plus","displayName":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.6-flash":{"metadata":{"displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-flash","displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.6-plus":{"metadata":{"displayName":"Qwen3.6 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-plus","displayName":"Qwen3.6 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.7-max":{"metadata":{"displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3.7-max","displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.7-plus":{"metadata":{"displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-04","lastUpdated":"2026-06-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.7-plus","displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}}}},"alibaba-token-plan-cn":{"baseUrl":"https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1","label":"Alibaba Token Plan (China)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider","responses":{"adapter":"open-responses","reasoningReplay":"plaintext-summary","compatibility":"alibaba-token-plan"}},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["qwen3.8-max","qwen3.7-max","qwen3.7-plus","qwen3.6-plus","qwen3.6-flash","deepseek-v4-pro","deepseek-v4-flash","deepseek-v3.2","kimi-k2.7-code","kimi-k2.6","kimi-k2.5","glm-5.2","glm-5.1","glm-5","MiniMax-M2.5"],"models":{"deepseek-v3.2":{"metadata":{"displayName":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-12-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v3.2","displayName":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash","displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-flash-0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash-0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-pro","displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-pro-0813":{"metadata":{"displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-pro-0813","displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"deepseek-v4.1-flash":{"metadata":{"displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-v4.1-flash","displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"glm-5":{"metadata":{"displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","lifecycle":"active","contextWindow":202752,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5","displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"glm-5.1":{"metadata":{"displayName":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","lifecycle":"active","contextWindow":202752,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.1","displayName":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"glm-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"happyhorse-1.1-i2v":{"metadata":{"displayName":"HappyHorse 1.1 Image-to-Video","description":"Video model for image-to-video generation","lifecycle":"active","lastUpdated":"2026-07-17","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["image","text"],"output":["video"]}},"entry":{"id":"happyhorse-1.1-i2v","displayName":"HappyHorse 1.1 Image-to-Video","description":"Video model for image-to-video generation","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"happyhorse-1.1-r2v":{"metadata":{"displayName":"HappyHorse 1.1 Reference-to-Video","description":"Video model for reference-guided video generation","lifecycle":"active","lastUpdated":"2026-07-17","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["image","text"],"output":["video"]}},"entry":{"id":"happyhorse-1.1-r2v","displayName":"HappyHorse 1.1 Reference-to-Video","description":"Video model for reference-guided video generation","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"happyhorse-1.1-t2v":{"metadata":{"displayName":"HappyHorse 1.1 Text-to-Video","description":"Video model for prompt-driven text-to-video generation","lifecycle":"active","lastUpdated":"2026-07-17","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"happyhorse-1.1-t2v","displayName":"HappyHorse 1.1 Text-to-Video","description":"Video model for prompt-driven text-to-video generation","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"kimi-k2.5":{"metadata":{"displayName":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","lifecycle":"active","contextWindow":262144,"maxOutputTokens":98304,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.5","displayName":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.6","displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k2.7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.7-code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"MiniMax-M2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","lifecycle":"active","contextWindow":196608,"inputLimit":196601,"maxOutputTokens":32768,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.5","displayName":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":196608,"inputLimit":196601,"defaultContextWindow":196608,"defaultInputLimit":196601}},"qwen-image-2.0":{"metadata":{"displayName":"Qwen Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":8192,"lastUpdated":"2026-03-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"qwen-image-2.0","displayName":"Qwen Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"qwen-image-2.0-pro":{"metadata":{"displayName":"Qwen Image 2.0 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":8192,"lastUpdated":"2026-03-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"qwen-image-2.0-pro","displayName":"Qwen Image 2.0 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"qwen3.6-flash":{"metadata":{"displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-flash","displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.6-plus":{"metadata":{"displayName":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-plus","displayName":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.7-max":{"metadata":{"displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3.7-max","displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.7-plus":{"metadata":{"displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-06-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.7-plus","displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.8-flash":{"metadata":{"displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.8-flash","displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.8-max":{"metadata":{"displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-03","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"qwen3.8-max","displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.8-max-preview":{"metadata":{"displayName":"Qwen3.8 Max Preview","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","lifecycle":"deprecated","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.8-max-preview","displayName":"Qwen3.8 Max Preview","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"wan2.7-image":{"metadata":{"displayName":"Wan2.7 Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":8192,"lastUpdated":"2026-05-29","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"wan2.7-image","displayName":"Wan2.7 Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"wan2.7-image-pro":{"metadata":{"displayName":"Wan2.7 Image Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":8192,"lastUpdated":"2026-05-29","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"wan2.7-image-pro","displayName":"Wan2.7 Image Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}}}},"alibaba-token-plan":{"baseUrl":"https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","label":"Alibaba Token Plan","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider","responses":{"adapter":"open-responses","reasoningReplay":"plaintext-summary","compatibility":"alibaba-token-plan"}},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["qwen3.8-max","qwen3.7-max","qwen3.7-plus","qwen3.6-plus","qwen3.6-flash","deepseek-v4-pro","deepseek-v4-flash","deepseek-v3.2","kimi-k2.7-code","kimi-k2.6","kimi-k2.5","glm-5.2","glm-5.1","glm-5","MiniMax-M2.5"],"models":{"deepseek-v3.2":{"metadata":{"displayName":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","lifecycle":"active","contextWindow":131072,"maxOutputTokens":65536,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2025-12-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v3.2","displayName":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-01"}},"deepseek-v4-flash":{"metadata":{"displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash","displayName":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-flash-0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash-0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-pro":{"metadata":{"displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-pro","displayName":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-05"}},"deepseek-v4-pro-0813":{"metadata":{"displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":384000,"structuredOutput":true,"lastUpdated":"2026-08-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-pro-0813","displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"glm-5":{"metadata":{"displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","lifecycle":"active","contextWindow":202752,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5","displayName":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"glm-5.1":{"metadata":{"displayName":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","lifecycle":"active","contextWindow":202752,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.1","displayName":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":202752,"defaultContextWindow":202752}},"glm-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"happyhorse-1.1-i2v":{"metadata":{"displayName":"HappyHorse 1.1 Image-to-Video","description":"Video model for image-to-video generation","lifecycle":"active","lastUpdated":"2026-07-17","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["image","text"],"output":["video"]}},"entry":{"id":"happyhorse-1.1-i2v","displayName":"HappyHorse 1.1 Image-to-Video","description":"Video model for image-to-video generation","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"happyhorse-1.1-r2v":{"metadata":{"displayName":"HappyHorse 1.1 Reference-to-Video","description":"Video model for reference-guided video generation","lifecycle":"active","lastUpdated":"2026-07-17","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["image","text"],"output":["video"]}},"entry":{"id":"happyhorse-1.1-r2v","displayName":"HappyHorse 1.1 Reference-to-Video","description":"Video model for reference-guided video generation","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"happyhorse-1.1-t2v":{"metadata":{"displayName":"HappyHorse 1.1 Text-to-Video","description":"Video model for prompt-driven text-to-video generation","lifecycle":"active","lastUpdated":"2026-07-17","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["video"]}},"entry":{"id":"happyhorse-1.1-t2v","displayName":"HappyHorse 1.1 Text-to-Video","description":"Video model for prompt-driven text-to-video generation","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"kimi-k2.5":{"metadata":{"displayName":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","lifecycle":"active","contextWindow":262144,"maxOutputTokens":98304,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.5","displayName":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.6","displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k2.7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"kimi-k2.7-code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"MiniMax-M2.5":{"metadata":{"displayName":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","lifecycle":"active","contextWindow":196608,"inputLimit":196601,"maxOutputTokens":32768,"lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"MiniMax-M2.5","displayName":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":196608,"inputLimit":196601,"defaultContextWindow":196608,"defaultInputLimit":196601}},"qwen-image-2.0":{"metadata":{"displayName":"Qwen Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":8192,"lastUpdated":"2026-03-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"qwen-image-2.0","displayName":"Qwen Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"qwen-image-2.0-pro":{"metadata":{"displayName":"Qwen Image 2.0 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":8192,"lastUpdated":"2026-03-03","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"qwen-image-2.0-pro","displayName":"Qwen Image 2.0 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"qwen3.6-flash":{"metadata":{"displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"structuredOutput":true,"lastUpdated":"2026-04-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-flash","displayName":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.6-plus":{"metadata":{"displayName":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.6-plus","displayName":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.7-max":{"metadata":{"displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-05-21","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"qwen3.7-max","displayName":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.7-plus":{"metadata":{"displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":65536,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-06-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.7-plus","displayName":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2025-04"}},"qwen3.8-flash":{"metadata":{"displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.8-flash","displayName":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.8-max":{"metadata":{"displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-03","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"qwen3.8-max","displayName":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"qwen3.8-max-preview":{"metadata":{"displayName":"Qwen3.8 Max Preview","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","lifecycle":"deprecated","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"]},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"qwen3.8-max-preview","displayName":"Qwen3.8 Max Preview","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":1000000,"defaultContextWindow":1000000}},"wan2.7-image":{"metadata":{"displayName":"Wan2.7 Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":8192,"lastUpdated":"2026-05-29","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"wan2.7-image","displayName":"Wan2.7 Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}},"wan2.7-image-pro":{"metadata":{"displayName":"Wan2.7 Image Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","contextWindow":8192,"lastUpdated":"2026-05-29","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["image"]}},"entry":{"id":"wan2.7-image-pro","displayName":"Wan2.7 Image Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192}}}},"commandcode":{"baseUrl":"https://api.commandcode.ai/provider/v1","label":"Command Code","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{"anthropic-messages":{"kind":"anthropic","auth":"bearer","normalizeBaseUrl":true}},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol","modelProtocols":"commandcode"},"fallbackModels":[],"models":{}},"cloudflare-workers-ai":{"baseUrl":"","label":"Cloudflare Workers AI","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider","requireBaseUrl":true,"replayAssistantReasoningAs":"reasoning"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"cloudflare"},"fallbackModels":["@cf/moonshotai/kimi-k2.6","@cf/moonshotai/kimi-k2.7-code","@cf/deepseek-ai/deepseek-v4-flash-0731","@cf/deepseek-ai/deepseek-v4-pro-0813","@cf/google/gemma-4-26b-a4b-it","@cf/ibm-granite/granite-4.0-h-micro","@cf/meta/llama-3.3-70b-instruct-fp8-fast","@cf/meta/llama-4-scout-17b-16e-instruct","@cf/mistralai/mistral-small-3.1-24b-instruct","@cf/nvidia/nemotron-3-120b-a12b","@cf/openai/gpt-oss-120b","@cf/openai/gpt-oss-20b","@cf/qwen/qwen3-30b-a3b-fp8","@cf/qwen/qwen3.8-27b","@cf/zai-org/glm-4.7-flash","@cf/zai-org/glm-5.2","@cf/zai-org/glm-5.3","@cf/zai-org/glm-5.3-flash"],"models":{"@cf/aisingapore/gemma-sea-lion-v4-27b-it":{"metadata":{"displayName":"Gemma Sea Lion V4 27B It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"structuredOutput":false,"lastUpdated":"2025-09-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/aisingapore/gemma-sea-lion-v4-27b-it","displayName":"Gemma Sea Lion V4 27B It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"@cf/deepseek-ai/deepseek-r1-distill-qwen-32b":{"metadata":{"displayName":"Deepseek R1 Distill Qwen 32B","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","lifecycle":"active","contextWindow":80000,"maxOutputTokens":80000,"knowledgeCutoff":"2024-07","structuredOutput":false,"lastUpdated":"2025-05-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","displayName":"Deepseek R1 Distill Qwen 32B","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":80000,"defaultContextWindow":80000,"knowledgeCutoff":"2024-07"}},"@cf/deepseek-ai/deepseek-v4-flash-0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1310720,"maxOutputTokens":1048576,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/deepseek-ai/deepseek-v4-flash-0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1310720,"defaultContextWindow":1310720,"knowledgeCutoff":"2025-05"}},"@cf/deepseek-ai/deepseek-v4-pro-0813":{"metadata":{"displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"structuredOutput":true,"lastUpdated":"2026-08-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/deepseek-ai/deepseek-v4-pro-0813","displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"@cf/google/gemma-4-26b-a4b-it":{"metadata":{"displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":256000,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2026-04-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"@cf/google/gemma-4-26b-a4b-it","displayName":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000}},"@cf/ibm-granite/granite-4.0-h-micro":{"metadata":{"displayName":"Granite 4.0 H Micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","lifecycle":"active","contextWindow":131000,"maxOutputTokens":131000,"structuredOutput":false,"lastUpdated":"2025-10-07","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/ibm-granite/granite-4.0-h-micro","displayName":"Granite 4.0 H Micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000}},"@cf/meta/llama-3.1-8b-instruct-fp8":{"metadata":{"displayName":"Llama 3.1 8B Instruct fp8","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":32000,"maxOutputTokens":32000,"knowledgeCutoff":"2023-12","structuredOutput":false,"lastUpdated":"2024-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/meta/llama-3.1-8b-instruct-fp8","displayName":"Llama 3.1 8B Instruct fp8","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32000,"defaultContextWindow":32000,"knowledgeCutoff":"2023-12"}},"@cf/meta/llama-3.2-11b-vision-instruct":{"metadata":{"displayName":"Llama 3.2 11B Vision Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2023-12","structuredOutput":false,"lastUpdated":"2024-09-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"@cf/meta/llama-3.2-11b-vision-instruct","displayName":"Llama 3.2 11B Vision Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-12"}},"@cf/meta/llama-3.2-1b-instruct":{"metadata":{"displayName":"Llama 3.2 1B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":60000,"maxOutputTokens":60000,"knowledgeCutoff":"2023-12","structuredOutput":false,"lastUpdated":"2024-09-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/meta/llama-3.2-1b-instruct","displayName":"Llama 3.2 1B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":60000,"defaultContextWindow":60000,"knowledgeCutoff":"2023-12"}},"@cf/meta/llama-3.2-3b-instruct":{"metadata":{"displayName":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","lifecycle":"active","contextWindow":80000,"maxOutputTokens":80000,"knowledgeCutoff":"2023-12","structuredOutput":false,"lastUpdated":"2024-09-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/meta/llama-3.2-3b-instruct","displayName":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":80000,"defaultContextWindow":80000,"knowledgeCutoff":"2023-12"}},"@cf/meta/llama-3.3-70b-instruct-fp8-fast":{"metadata":{"displayName":"Llama 3.3 70B Instruct fp8 Fast","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","lifecycle":"active","contextWindow":24000,"maxOutputTokens":24000,"knowledgeCutoff":"2023-12","structuredOutput":false,"lastUpdated":"2024-12-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/meta/llama-3.3-70b-instruct-fp8-fast","displayName":"Llama 3.3 70B Instruct fp8 Fast","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":24000,"defaultContextWindow":24000,"knowledgeCutoff":"2023-12"}},"@cf/meta/llama-4-scout-17b-16e-instruct":{"metadata":{"displayName":"Llama 4 Scout 17B 16E Instruct","description":"Open Llama with long-context vision for efficient multimodal agents","lifecycle":"active","contextWindow":131000,"maxOutputTokens":16384,"knowledgeCutoff":"2024-08","structuredOutput":false,"lastUpdated":"2025-04-05","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"@cf/meta/llama-4-scout-17b-16e-instruct","displayName":"Llama 4 Scout 17B 16E Instruct","description":"Open Llama with long-context vision for efficient multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":131000,"defaultContextWindow":131000,"knowledgeCutoff":"2024-08"}},"@cf/meta/llama-guard-3-8b":{"metadata":{"displayName":"Llama Guard 3 8B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2023-12","structuredOutput":false,"lastUpdated":"2024-07-23","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/meta/llama-guard-3-8b","displayName":"Llama Guard 3 8B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2023-12"}},"@cf/mistralai/mistral-small-3.1-24b-instruct":{"metadata":{"displayName":"Mistral Small 3.1 24B Instruct","description":"Efficient Mistral model for fast chat, extraction, and production assistants","lifecycle":"active","contextWindow":128000,"maxOutputTokens":128000,"structuredOutput":false,"lastUpdated":"2025-03-18","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/mistralai/mistral-small-3.1-24b-instruct","displayName":"Mistral Small 3.1 24B Instruct","description":"Efficient Mistral model for fast chat, extraction, and production assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"@cf/moonshotai/kimi-k2.6":{"metadata":{"displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","lifecycle":"active","contextWindow":262144,"maxOutputTokens":256000,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true,"offBehavior":"cloudflare-chat-template-thinking-false"},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"@cf/moonshotai/kimi-k2.6","displayName":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"@cf/moonshotai/kimi-k2.7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"@cf/moonshotai/kimi-k2.7-code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"@cf/nvidia/nemotron-3-120b-a12b":{"metadata":{"displayName":"Nemotron 3 Super 120B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","lifecycle":"active","contextWindow":256000,"maxOutputTokens":256000,"structuredOutput":true,"lastUpdated":"2026-03-11","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/nvidia/nemotron-3-120b-a12b","displayName":"Nemotron 3 Super 120B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"defaultContextWindow":256000}},"@cf/openai/gpt-oss-120b":{"metadata":{"displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/openai/gpt-oss-120b","displayName":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":128000,"defaultContextWindow":128000}},"@cf/openai/gpt-oss-20b":{"metadata":{"displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"structuredOutput":true,"lastUpdated":"2025-08-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/openai/gpt-oss-20b","displayName":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000}},"@cf/qwen/qwen2.5-coder-32b-instruct":{"metadata":{"displayName":"Qwen2.5 Coder 32B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","lifecycle":"active","contextWindow":32768,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2024-11-12","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/qwen/qwen2.5-coder-32b-instruct","displayName":"Qwen2.5 Coder 32B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"@cf/qwen/qwen3-30b-a3b-fp8":{"metadata":{"displayName":"Qwen3 30B A3b fp8","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","lifecycle":"active","contextWindow":32768,"maxOutputTokens":32768,"structuredOutput":false,"lastUpdated":"2025-04-28","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/qwen/qwen3-30b-a3b-fp8","displayName":"Qwen3 30B A3b fp8","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":32768,"defaultContextWindow":32768}},"@cf/qwen/qwen3.8-27b":{"metadata":{"displayName":"Qwen3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","xhigh"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"@cf/qwen/qwen3.8-27b","displayName":"Qwen3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","xhigh"],"contextWindow":262144,"defaultContextWindow":262144}},"@cf/qwen/qwq-32b":{"metadata":{"displayName":"Qwq 32B","description":"Qwen reasoning model for deliberate problem solving, math, and coding","lifecycle":"active","contextWindow":24000,"maxOutputTokens":24000,"knowledgeCutoff":"2024-04","structuredOutput":false,"lastUpdated":"2025-03-05","capabilities":{"vision":false,"reasoning":true,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/qwen/qwq-32b","displayName":"Qwq 32B","description":"Qwen reasoning model for deliberate problem solving, math, and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":24000,"defaultContextWindow":24000,"knowledgeCutoff":"2024-04"}},"@cf/zai-org/glm-4.7-flash":{"metadata":{"displayName":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","lifecycle":"active","contextWindow":131072,"maxOutputTokens":131072,"knowledgeCutoff":"2025-04","structuredOutput":true,"lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/zai-org/glm-4.7-flash","displayName":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072,"knowledgeCutoff":"2025-04"}},"@cf/zai-org/glm-5.2":{"metadata":{"displayName":"Glm 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":262144,"maxOutputTokens":256000,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/zai-org/glm-5.2","displayName":"Glm 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":262144,"defaultContextWindow":262144}},"@cf/zai-org/glm-5.3":{"metadata":{"displayName":"Glm 5.3","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":1310720,"maxOutputTokens":1310720,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"@cf/zai-org/glm-5.3","displayName":"Glm 5.3","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":1310720,"defaultContextWindow":1310720}},"@cf/zai-org/glm-5.3-flash":{"metadata":{"displayName":"Glm 5.3 Flash","description":"GLM vision model for visual reasoning, documents, and multimodal agents","lifecycle":"active","contextWindow":1310720,"maxOutputTokens":1048576,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"@cf/zai-org/glm-5.3-flash","displayName":"Glm 5.3 Flash","description":"GLM vision model for visual reasoning, documents, and multimodal agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1310720,"defaultContextWindow":1310720}}}},"ollama-cloud":{"baseUrl":"https://ollama.com/v1","label":"Ollama Cloud","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider","includeUsage":true,"replayAssistantReasoningAs":"reasoning"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["qwen3.5:397b","gpt-oss:120b","deepseek-v4-flash","deepseek-v4-flash:0731","deepseek-v4-pro","deepseek-v4-pro:0813","deepseek-v4.1-flash","gemma4:31b","glm-5.1","glm-5.2","glm-5.3","glm-5.3-flash","gpt-oss:20b","kimi-k2.5","kimi-k2.6","kimi-k2.7-code","kimi-k3","minimax-m2.5","minimax-m2.7","minimax-m3","mistral-large-3:675b","nemotron-3-nano:30b","nemotron-3-super","nemotron-3-ultra"],"models":{"deepseek-v4-flash":{"metadata":{"displayName":"deepseek-v4-flash","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash","displayName":"deepseek-v4-flash","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"deepseek-v4-flash:0731":{"metadata":{"displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-07-31","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-flash:0731","displayName":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"deepseek-v4-pro":{"metadata":{"displayName":"deepseek-v4-pro","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"lastUpdated":"2026-04-24","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-pro","displayName":"deepseek-v4-pro","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"deepseek-v4-pro:0813":{"metadata":{"displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":1048576,"structuredOutput":true,"lastUpdated":"2026-08-22","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"deepseek-v4-pro:0813","displayName":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"deepseek-v4.1-flash":{"metadata":{"displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":384000,"knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2026-09-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"deepseek-v4.1-flash","displayName":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576,"knowledgeCutoff":"2025-05"}},"gemma4:31b":{"metadata":{"displayName":"gemma4:31b","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","lastUpdated":"2026-04-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gemma4:31b","displayName":"gemma4:31b","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"glm-5.1":{"metadata":{"displayName":"glm-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","lifecycle":"active","contextWindow":202752,"maxOutputTokens":131072,"lastUpdated":"2026-04-07","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.1","displayName":"glm-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":202752,"defaultContextWindow":202752}},"glm-5.2":{"metadata":{"displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","lifecycle":"active","contextWindow":976000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-06-13","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.2","displayName":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":976000,"defaultContextWindow":976000}},"glm-5.3":{"metadata":{"displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-14","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"glm-5.3","displayName":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"glm-5.3-flash":{"metadata":{"displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-08-26","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]}},"entry":{"id":"glm-5.3-flash","displayName":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":1000000,"defaultContextWindow":1000000}},"gpt-oss:120b":{"metadata":{"displayName":"gpt-oss:120b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"gpt-oss:120b","displayName":"gpt-oss:120b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"gpt-oss:20b":{"metadata":{"displayName":"gpt-oss:20b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","lifecycle":"active","contextWindow":131072,"maxOutputTokens":32768,"lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"gpt-oss:20b","displayName":"gpt-oss:20b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":131072,"defaultContextWindow":131072}},"kimi-k2.5":{"metadata":{"displayName":"kimi-k2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"lastUpdated":"2026-01-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"kimi-k2.5","displayName":"kimi-k2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":262144,"defaultContextWindow":262144}},"kimi-k2.6":{"metadata":{"displayName":"kimi-k2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"lastUpdated":"2026-04-20","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"kimi-k2.6","displayName":"kimi-k2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":262144,"defaultContextWindow":262144}},"kimi-k2.7-code":{"metadata":{"displayName":"kimi-k2.7-code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"kimi-k2.7-code","displayName":"kimi-k2.7-code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":262144,"defaultContextWindow":262144,"knowledgeCutoff":"2025-01"}},"kimi-k3":{"metadata":{"displayName":"kimi-k3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-27","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"kimi-k3","displayName":"kimi-k3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"minimax-m2.5":{"metadata":{"displayName":"minimax-m2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":204800,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01","lastUpdated":"2026-02-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true}},"entry":{"id":"minimax-m2.5","displayName":"minimax-m2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":204800,"defaultContextWindow":204800,"knowledgeCutoff":"2025-01"}},"minimax-m2.7":{"metadata":{"displayName":"minimax-m2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","lifecycle":"active","contextWindow":196608,"maxOutputTokens":196608,"lastUpdated":"2026-03-18","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"minimax-m2.7","displayName":"minimax-m2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":196608,"defaultContextWindow":196608}},"minimax-m3":{"metadata":{"displayName":"minimax-m3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","lifecycle":"active","contextWindow":512000,"maxOutputTokens":131072,"knowledgeCutoff":"2025-01","lastUpdated":"2026-05-31","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image","video"],"output":["text"]}},"entry":{"id":"minimax-m3","displayName":"minimax-m3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":512000,"defaultContextWindow":512000,"knowledgeCutoff":"2025-01"}},"mistral-large-3:675b":{"metadata":{"displayName":"mistral-large-3:675b","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","lifecycle":"active","contextWindow":262144,"maxOutputTokens":262144,"lastUpdated":"2026-01-19","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"mistral-large-3:675b","displayName":"mistral-large-3:675b","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":262144,"defaultContextWindow":262144}},"nemotron-3-nano:30b":{"metadata":{"displayName":"nemotron-3-nano:30b","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"lastUpdated":"2026-01-19","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nemotron-3-nano:30b","displayName":"nemotron-3-nano:30b","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"nemotron-3-super":{"metadata":{"displayName":"nemotron-3-super","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"lastUpdated":"2026-03-12","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nemotron-3-super","displayName":"nemotron-3-super","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":262144,"defaultContextWindow":262144}},"nemotron-3-ultra":{"metadata":{"displayName":"nemotron-3-ultra","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","lifecycle":"active","contextWindow":262144,"maxOutputTokens":128000,"lastUpdated":"2026-06-04","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"nemotron-3-ultra","displayName":"nemotron-3-ultra","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":262144,"defaultContextWindow":262144}},"qwen3.5:397b":{"metadata":{"displayName":"qwen3.5:397b","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","lifecycle":"active","contextWindow":262144,"maxOutputTokens":65536,"lastUpdated":"2026-02-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","max"],"toggle":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"qwen3.5:397b","displayName":"qwen3.5:397b","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","max"],"contextWindow":262144,"defaultContextWindow":262144}}}},"ollama":{"baseUrl":"http://127.0.0.1:11434/v1","label":"Ollama","authKind":"none","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"ollama"},"fallbackModels":["llama3.2","qwen2.5-coder","gemma3"],"models":{"llama3.2":{"metadata":{},"entry":{"id":"llama3.2","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"qwen2.5-coder":{"metadata":{},"entry":{"id":"qwen2.5-coder","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}},"gemma3":{"metadata":{},"entry":{"id":"gemma3","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}}}},"lm-studio":{"baseUrl":"http://127.0.0.1:1234/v1","label":"LM Studio","authKind":"none","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}},"localai":{"baseUrl":"http://127.0.0.1:8080/v1","label":"LocalAI","authKind":"optional_api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":["qwen3-8b"],"models":{"qwen3-8b":{"metadata":{},"entry":{"id":"qwen3-8b","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[]}}}},"openai-compatible":{"baseUrl":"","label":"Custom relay (OpenAI Chat-compatible)","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"connection","requireBaseUrl":true},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}},"openai-responses-compatible":{"baseUrl":"","label":"Custom relay (OpenAI Responses)","authKind":"api_key","runtimeAdapter":{"kind":"openai","apiProtocol":"openai-responses","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}},"anthropic-compatible":{"baseUrl":"","label":"Custom relay (Anthropic)","authKind":"api_key","runtimeAdapter":{"kind":"anthropic","auth":"api-key","normalizeBaseUrl":true},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}},"github-copilot":{"baseUrl":"https://api.githubcopilot.com","label":"GitHub Copilot","authKind":"oauth_token","runtimeAdapter":{"kind":"openai-compatible","name":"provider","includeUsage":false},"protocolAdapters":{"anthropic-messages":{"kind":"anthropic","auth":"bearer","normalizeBaseUrl":true,"includeBetaHeaders":false},"openai-responses":{"kind":"openai","apiProtocol":"openai-responses","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}}},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol","auth":"github-copilot"},"fallbackModels":["gpt-5.4","claude-fable-5","claude-fable-5.1","claude-haiku-4.5","claude-opus-4.7","claude-opus-4.8","claude-opus-5","claude-sonnet-4.6","claude-sonnet-5","gemini-3.5-flash","gemini-3.6-flash","gemini-3.7-flash","gemini-3.8-flash","gpt-5-mini","gpt-5.3-codex","gpt-5.4-mini","gpt-5.4-nano","gpt-5.5","gpt-5.6-luna","gpt-5.6-sol","gpt-5.6-terra","gpt-6-astra","grok-4.5","grok-4.6","kimi-k2.7-code","kimi-k3","mai-code-1-flash-picker","mai-code-1.1-flash"],"models":{"claude-fable-5":{"metadata":{"displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-06-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-fable-5","displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"claude-fable-5.1":{"metadata":{"displayName":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-06","lastUpdated":"2026-09-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-fable-5.1","displayName":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-06"}},"claude-haiku-4.5":{"metadata":{"displayName":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","lifecycle":"active","contextWindow":200000,"inputLimit":136000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-02-28","lastUpdated":"2025-10-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-haiku-4.5","displayName":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":200000,"inputLimit":136000,"defaultContextWindow":200000,"defaultInputLimit":136000,"knowledgeCutoff":"2025-02-28"}},"claude-opus-4.7":{"metadata":{"displayName":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","lifecycle":"active","contextWindow":200000,"inputLimit":168000,"maxOutputTokens":32000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-opus-4.7","displayName":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":200000,"inputLimit":168000,"defaultContextWindow":200000,"defaultInputLimit":168000,"knowledgeCutoff":"2026-01-31"}},"claude-opus-4.8":{"metadata":{"displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","lifecycle":"active","contextWindow":200000,"inputLimit":168000,"maxOutputTokens":64000,"knowledgeCutoff":"2026-01","lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-opus-4.8","displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":200000,"inputLimit":168000,"defaultContextWindow":200000,"defaultInputLimit":168000,"knowledgeCutoff":"2026-01"}},"claude-opus-5":{"metadata":{"displayName":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","lifecycle":"active","contextWindow":1000000,"inputLimit":936000,"maxOutputTokens":64000,"knowledgeCutoff":"2026-05","structuredOutput":true,"lastUpdated":"2026-07-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-opus-5","displayName":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"inputLimit":936000,"defaultContextWindow":1000000,"defaultInputLimit":936000,"knowledgeCutoff":"2026-05"}},"claude-sonnet-4.6":{"metadata":{"displayName":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","lifecycle":"active","contextWindow":200000,"inputLimit":168000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-08-31","lastUpdated":"2026-03-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-sonnet-4.6","displayName":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","max"],"contextWindow":200000,"inputLimit":168000,"defaultContextWindow":200000,"defaultInputLimit":168000,"knowledgeCutoff":"2025-08-31"}},"claude-sonnet-5":{"metadata":{"displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","lifecycle":"active","contextWindow":1000000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-01-31","lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"claude-sonnet-5","displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1000000,"defaultContextWindow":1000000,"knowledgeCutoff":"2026-01-31"}},"gemini-3.5-flash":{"metadata":{"displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":200000,"inputLimit":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-05-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]}},"entry":{"id":"gemini-3.5-flash","displayName":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":200000,"inputLimit":128000,"defaultContextWindow":200000,"defaultInputLimit":128000,"knowledgeCutoff":"2025-01"}},"gemini-3.6-flash":{"metadata":{"displayName":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","lifecycle":"active","contextWindow":1000000,"inputLimit":936000,"maxOutputTokens":64000,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-07-21","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gemini-3.6-flash","displayName":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":1000000,"inputLimit":936000,"defaultContextWindow":1000000,"defaultInputLimit":936000,"knowledgeCutoff":"2026-03"}},"gemini-3.7-flash":{"metadata":{"displayName":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","lifecycle":"active","contextWindow":1000000,"inputLimit":936000,"maxOutputTokens":64000,"knowledgeCutoff":"2026-03","structuredOutput":true,"lastUpdated":"2026-08-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gemini-3.7-flash","displayName":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"inputLimit":936000,"defaultContextWindow":1000000,"defaultInputLimit":936000,"knowledgeCutoff":"2026-03"}},"gemini-3.8-flash":{"metadata":{"displayName":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","lifecycle":"active","contextWindow":1000000,"inputLimit":936000,"maxOutputTokens":64000,"structuredOutput":true,"lastUpdated":"2026-09-02","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gemini-3.8-flash","displayName":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":1000000,"inputLimit":936000,"defaultContextWindow":1000000,"defaultInputLimit":936000}},"gpt-5-mini":{"metadata":{"displayName":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","lifecycle":"active","contextWindow":264000,"inputLimit":128000,"maxOutputTokens":64000,"knowledgeCutoff":"2024-05-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5-mini","displayName":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":264000,"inputLimit":128000,"defaultContextWindow":264000,"defaultInputLimit":128000,"knowledgeCutoff":"2024-05-30"}},"gpt-5.3-codex":{"metadata":{"displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-02-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.3-codex","displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4":{"metadata":{"displayName":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.4","displayName":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4-mini":{"metadata":{"displayName":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.4-mini","displayName":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4-nano":{"metadata":{"displayName":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","lifecycle":"active","contextWindow":400000,"inputLimit":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.4-nano","displayName":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":400000,"inputLimit":272000,"defaultContextWindow":400000,"defaultInputLimit":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.5":{"metadata":{"displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.5","displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2025-12-01"}},"gpt-5.6-luna":{"metadata":{"displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.6-luna","displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"gpt-5.6-sol":{"metadata":{"displayName":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.6-sol","displayName":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"gpt-5.6-terra":{"metadata":{"displayName":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.6-terra","displayName":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-02-16"}},"gpt-6-astra":{"metadata":{"displayName":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","lifecycle":"active","contextWindow":1050000,"inputLimit":922000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-04-30","structuredOutput":true,"lastUpdated":"2026-09-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-6-astra","displayName":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1050000,"inputLimit":922000,"defaultContextWindow":1050000,"defaultInputLimit":922000,"knowledgeCutoff":"2026-04-30"}},"grok-4.5":{"metadata":{"displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","lifecycle":"active","contextWindow":500000,"inputLimit":372000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-07-08","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"grok-4.5","displayName":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":500000,"inputLimit":372000,"defaultContextWindow":500000,"defaultInputLimit":372000}},"grok-4.6":{"metadata":{"displayName":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","lifecycle":"active","contextWindow":500000,"inputLimit":372000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-01","structuredOutput":true,"lastUpdated":"2026-08-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"grok-4.6","displayName":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh"],"contextWindow":500000,"inputLimit":372000,"defaultContextWindow":500000,"defaultInputLimit":372000,"knowledgeCutoff":"2026-02-01"}},"kimi-k2.7-code":{"metadata":{"displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","lifecycle":"active","contextWindow":256000,"inputLimit":224000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-01","structuredOutput":true,"lastUpdated":"2026-06-12","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"kimi-k2.7-code","displayName":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":256000,"inputLimit":224000,"defaultContextWindow":256000,"defaultInputLimit":224000,"knowledgeCutoff":"2025-01"}},"kimi-k3":{"metadata":{"displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","lifecycle":"active","contextWindow":1048576,"maxOutputTokens":131072,"structuredOutput":true,"lastUpdated":"2026-07-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","high","max"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"kimi-k3","displayName":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","high","max"],"contextWindow":1048576,"defaultContextWindow":1048576}},"mai-code-1-flash-picker":{"metadata":{"displayName":"MAI-Code-1-Flash","description":"Microsoft coding model built for fast, efficient assistance in everyday developer workflows","lifecycle":"active","contextWindow":256000,"inputLimit":128000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12","structuredOutput":true,"lastUpdated":"2026-06-08","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"mai-code-1-flash-picker","displayName":"MAI-Code-1-Flash","description":"Microsoft coding model built for fast, efficient assistance in everyday developer workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"inputLimit":128000,"defaultContextWindow":256000,"defaultInputLimit":128000,"knowledgeCutoff":"2025-12"}},"mai-code-1.1-flash":{"metadata":{"displayName":"MAI-Code-1.1-Flash","description":"Microsoft coding model with native vision support, optimized for fast and efficient software development","lifecycle":"active","contextWindow":256000,"inputLimit":128000,"maxOutputTokens":128000,"structuredOutput":true,"lastUpdated":"2026-08-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"mai-code-1.1-flash","displayName":"MAI-Code-1.1-Flash","description":"Microsoft coding model with native vision support, optimized for fast and efficient software development","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":256000,"inputLimit":128000,"defaultContextWindow":256000,"defaultInputLimit":128000}}}},"claude-subscription":{"baseUrl":"https://api.anthropic.com","label":"Claude Subscription (Pro / Max OAuth)","authKind":"oauth_token","runtimeAdapter":{"kind":"unavailable"},"protocolAdapters":{},"retired":true,"supportsModelDiscovery":false,"modelDiscovery":{"kind":"fallback","reason":"Subscription OAuth tokens are session-scoped (user:sessions:claude_code, no user:inference), so GET /v1/models rejects them with 401"},"fallbackModels":["claude-opus-5","claude-sonnet-5","claude-sonnet-4-6","claude-opus-4-8","claude-haiku-4-5","claude-sonnet-4-5-20250929"],"models":{"claude-fable-5":{"metadata":{"displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","lifecycle":"active","structuredOutput":true,"lastUpdated":"2026-06-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]}},"entry":{"id":"claude-fable-5","displayName":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"]}},"claude-fable-5-1":{"metadata":{"displayName":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","lifecycle":"active","knowledgeCutoff":"2026-06","structuredOutput":true,"lastUpdated":"2026-09-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]}},"entry":{"id":"claude-fable-5-1","displayName":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"knowledgeCutoff":"2026-06"}},"claude-haiku-4-5":{"metadata":{"displayName":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","lifecycle":"active","knowledgeCutoff":"2025-02-28","structuredOutput":true,"lastUpdated":"2025-10-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"toggle":true,"offBehavior":"anthropic-thinking-disabled"}},"entry":{"id":"claude-haiku-4-5","displayName":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"],"knowledgeCutoff":"2025-02-28"}},"claude-haiku-4-5-20251001":{"metadata":{"displayName":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","lifecycle":"active","knowledgeCutoff":"2025-02-28","structuredOutput":true,"lastUpdated":"2025-10-15","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"toggle":true,"offBehavior":"anthropic-thinking-disabled"}},"entry":{"id":"claude-haiku-4-5-20251001","displayName":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"],"knowledgeCutoff":"2025-02-28"}},"claude-opus-4-5":{"metadata":{"displayName":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2025-11-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"efforts":["low","medium","high"]}},"entry":{"id":"claude-opus-4-5","displayName":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"knowledgeCutoff":"2025-05"}},"claude-opus-4-5-20251101":{"metadata":{"displayName":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","lifecycle":"active","knowledgeCutoff":"2025-05","structuredOutput":true,"lastUpdated":"2025-11-01","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"efforts":["low","medium","high"]}},"entry":{"id":"claude-opus-4-5-20251101","displayName":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"knowledgeCutoff":"2025-05"}},"claude-opus-4-6":{"metadata":{"displayName":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","lifecycle":"active","knowledgeCutoff":"2025-05-31","structuredOutput":true,"lastUpdated":"2026-03-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"efforts":["low","medium","high","max"]}},"entry":{"id":"claude-opus-4-6","displayName":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","max"],"knowledgeCutoff":"2025-05-31"}},"claude-opus-4-7":{"metadata":{"displayName":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","lifecycle":"active","knowledgeCutoff":"2026-01-31","structuredOutput":true,"lastUpdated":"2026-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]}},"entry":{"id":"claude-opus-4-7","displayName":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"knowledgeCutoff":"2026-01-31"}},"claude-opus-4-8":{"metadata":{"displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","lifecycle":"active","knowledgeCutoff":"2026-01","structuredOutput":true,"lastUpdated":"2026-05-28","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]}},"entry":{"id":"claude-opus-4-8","displayName":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"knowledgeCutoff":"2026-01"}},"claude-opus-5":{"metadata":{"displayName":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","lifecycle":"active","knowledgeCutoff":"2026-05","structuredOutput":true,"lastUpdated":"2026-07-24","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]}},"entry":{"id":"claude-opus-5","displayName":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"knowledgeCutoff":"2026-05"}},"claude-sonnet-4-5":{"metadata":{"displayName":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","knowledgeCutoff":"2025-07-31","structuredOutput":true,"lastUpdated":"2025-09-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"toggle":true,"offBehavior":"anthropic-thinking-disabled"}},"entry":{"id":"claude-sonnet-4-5","displayName":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"],"knowledgeCutoff":"2025-07-31"}},"claude-sonnet-4-5-20250929":{"metadata":{"displayName":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","lifecycle":"active","knowledgeCutoff":"2025-07-31","structuredOutput":true,"lastUpdated":"2025-09-29","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"toggle":true,"offBehavior":"anthropic-thinking-disabled"}},"entry":{"id":"claude-sonnet-4-5-20250929","displayName":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off"],"knowledgeCutoff":"2025-07-31"}},"claude-sonnet-4-6":{"metadata":{"displayName":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","lifecycle":"active","knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"efforts":["low","medium","high","max"]}},"entry":{"id":"claude-sonnet-4-6","displayName":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","max"],"knowledgeCutoff":"2025-08-31"}},"claude-sonnet-5":{"metadata":{"displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","lifecycle":"active","knowledgeCutoff":"2026-01-31","structuredOutput":true,"lastUpdated":"2026-06-30","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"],"toggle":true}},"entry":{"id":"claude-sonnet-5","displayName":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"knowledgeCutoff":"2026-01-31"}}}},"openai-codex":{"baseUrl":"https://chatgpt.com/backend-api/codex","label":"OpenAI OAuth (ChatGPT / Codex)","authKind":"oauth_token","runtimeAdapter":{"kind":"openai-codex","responses":{"adapter":"openai","reasoningReplay":"encrypted-content"}},"protocolAdapters":{},"retired":false,"supportsModelDiscovery":true,"modelDiscovery":{"kind":"protocol","auth":"openai-codex"},"fallbackModels":["gpt-6-astra","gpt-5.6-sol","gpt-5.6-terra","gpt-5.6-luna"],"models":{"chatgpt-image-latest":{"metadata":{"displayName":"chatgpt-image-latest","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-12-16","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"chatgpt-image-latest","displayName":"chatgpt-image-latest","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"gpt-3.5-turbo":{"metadata":{"displayName":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"deprecated","contextWindow":16385,"maxOutputTokens":4096,"knowledgeCutoff":"2021-09-01","structuredOutput":false,"lastUpdated":"2023-11-06","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"gpt-3.5-turbo","displayName":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":16385,"defaultContextWindow":16385,"knowledgeCutoff":"2021-09-01"}},"gpt-4":{"metadata":{"displayName":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"deprecated","contextWindow":8192,"maxOutputTokens":8192,"knowledgeCutoff":"2023-11","structuredOutput":false,"lastUpdated":"2024-04-09","capabilities":{"vision":false,"reasoning":false,"functionCalling":true},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"gpt-4","displayName":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2023-11"}},"gpt-4-turbo":{"metadata":{"displayName":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-12","structuredOutput":false,"lastUpdated":"2024-04-09","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-4-turbo","displayName":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-12"}},"gpt-4.1":{"metadata":{"displayName":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","lifecycle":"active","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-4.1","displayName":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"gpt-4.1-mini":{"metadata":{"displayName":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","lifecycle":"active","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-4.1-mini","displayName":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"gpt-4.1-nano":{"metadata":{"displayName":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","lifecycle":"deprecated","contextWindow":1047576,"maxOutputTokens":32768,"knowledgeCutoff":"2024-04","structuredOutput":true,"lastUpdated":"2025-04-14","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-4.1-nano","displayName":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":1047576,"defaultContextWindow":1047576,"knowledgeCutoff":"2024-04"}},"gpt-4o":{"metadata":{"displayName":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-08-06","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-4o","displayName":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"gpt-4o-2024-05-13":{"metadata":{"displayName":"GPT-4o (2024-05-13)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":4096,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-05-13","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-4o-2024-05-13","displayName":"GPT-4o (2024-05-13)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"gpt-4o-2024-08-06":{"metadata":{"displayName":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-08-06","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-4o-2024-08-06","displayName":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"gpt-4o-2024-11-20":{"metadata":{"displayName":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-11-20","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-4o-2024-11-20","displayName":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"gpt-4o-mini":{"metadata":{"displayName":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","lifecycle":"active","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-07-18","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-4o-mini","displayName":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2023-09"}},"gpt-5":{"metadata":{"displayName":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5","displayName":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2024-09-30"}},"gpt-5-mini":{"metadata":{"displayName":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-05-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5-mini","displayName":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2024-05-30"}},"gpt-5-nano":{"metadata":{"displayName":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-05-30","structuredOutput":true,"lastUpdated":"2025-08-07","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5-nano","displayName":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2024-05-30"}},"gpt-5-pro":{"metadata":{"displayName":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","lifecycle":"active","contextWindow":400000,"maxOutputTokens":272000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-10-06","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5-pro","displayName":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2024-09-30"}},"gpt-5.1":{"metadata":{"displayName":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2024-09-30","structuredOutput":true,"lastUpdated":"2025-11-13","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.1","displayName":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2024-09-30"}},"gpt-5.2":{"metadata":{"displayName":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.2","displayName":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.2-chat-latest":{"metadata":{"displayName":"GPT-5.2 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.2-chat-latest","displayName":"GPT-5.2 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium"],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.2-pro":{"metadata":{"displayName":"GPT-5.2 Pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":false,"lastUpdated":"2025-12-11","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.2-pro","displayName":"GPT-5.2 Pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.3-chat-latest":{"metadata":{"displayName":"GPT-5.3 Chat (latest)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","lifecycle":"deprecated","contextWindow":128000,"maxOutputTokens":16384,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-03","capabilities":{"vision":true,"reasoning":false,"functionCalling":true},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.3-chat-latest","displayName":"GPT-5.3 Chat (latest)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.3-codex":{"metadata":{"displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-02-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.3-codex","displayName":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.3-codex-spark":{"metadata":{"displayName":"GPT-5.3 Codex Spark","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","lifecycle":"active","contextWindow":128000,"maxOutputTokens":32000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-02-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.3-codex-spark","displayName":"GPT-5.3 Codex Spark","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4":{"metadata":{"displayName":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","lifecycle":"active","contextWindow":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.4","displayName":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":272000,"defaultContextWindow":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4-mini":{"metadata":{"displayName":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","lifecycle":"active","contextWindow":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.4-mini","displayName":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":272000,"defaultContextWindow":272000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4-nano":{"metadata":{"displayName":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","lifecycle":"active","contextWindow":400000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":true,"lastUpdated":"2026-03-17","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.4-nano","displayName":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":400000,"defaultContextWindow":400000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.4-pro":{"metadata":{"displayName":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-08-31","structuredOutput":false,"lastUpdated":"2026-03-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"gpt-5.4-pro","displayName":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2025-08-31"}},"gpt-5.5":{"metadata":{"displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","lifecycle":"active","contextWindow":272000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.5","displayName":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":272000,"defaultContextWindow":272000,"knowledgeCutoff":"2025-12-01"}},"gpt-5.5-pro":{"metadata":{"displayName":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"knowledgeCutoff":"2025-12-01","structuredOutput":true,"lastUpdated":"2026-04-23","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.5-pro","displayName":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["medium","high","xhigh"],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2025-12-01"}},"gpt-5.6":{"metadata":{"displayName":"GPT-5.6","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.6","displayName":"GPT-5.6","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2026-02-16"}},"gpt-5.6-luna":{"metadata":{"displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.6-luna","displayName":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2026-02-16"}},"gpt-5.6-sol":{"metadata":{"displayName":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","lifecycle":"active","contextWindow":372000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.6-sol","displayName":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh"],"contextWindow":372000,"defaultContextWindow":372000,"knowledgeCutoff":"2026-02-16"}},"gpt-5.6-terra":{"metadata":{"displayName":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-02-16","structuredOutput":true,"lastUpdated":"2026-07-09","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["none","low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-5.6-terra","displayName":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["off","low","medium","high","xhigh","max"],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2026-02-16"}},"gpt-6-astra":{"metadata":{"displayName":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","lifecycle":"active","contextWindow":1050000,"maxOutputTokens":128000,"knowledgeCutoff":"2026-04-30","structuredOutput":true,"lastUpdated":"2026-09-04","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"gpt-6-astra","displayName":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high","xhigh","max"],"contextWindow":1050000,"defaultContextWindow":1050000,"knowledgeCutoff":"2026-04-30"}},"gpt-image-1":{"metadata":{"displayName":"gpt-image-1","description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","lifecycle":"deprecated","lastUpdated":"2025-04-24","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["image"]}},"entry":{"id":"gpt-image-1","displayName":"gpt-image-1","description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"gpt-image-1-mini":{"metadata":{"displayName":"gpt-image-1-mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-09-26","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"gpt-image-1-mini","displayName":"gpt-image-1-mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"gpt-image-1.5":{"metadata":{"displayName":"gpt-image-1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2025-11-25","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["text","image"]}},"entry":{"id":"gpt-image-1.5","displayName":"gpt-image-1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"gpt-image-2":{"metadata":{"displayName":"gpt-image-2","description":"Image model for prompt-driven generation, editing, and visual design workflows","lifecycle":"active","lastUpdated":"2026-04-21","capabilities":{"vision":true,"reasoning":false,"functionCalling":false},"modalities":{"input":["text","image"],"output":["image"]}},"entry":{"id":"gpt-image-2","displayName":"gpt-image-2","description":"Image model for prompt-driven generation, editing, and visual design workflows","canUseAsChatDefault":false,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":[]}},"gpt-realtime-2.1":{"metadata":{"displayName":"GPT-Realtime-2.1","description":"Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior","lifecycle":"active","contextWindow":128000,"maxOutputTokens":32000,"knowledgeCutoff":"2024-09-30","structuredOutput":false,"lastUpdated":"2026-07-06","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["minimal","low","medium","high","xhigh"]},"modalities":{"input":["text","audio","image"],"output":["text","audio"]}},"entry":{"id":"gpt-realtime-2.1","displayName":"GPT-Realtime-2.1","description":"Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["minimal","low","medium","high","xhigh"],"contextWindow":128000,"defaultContextWindow":128000,"knowledgeCutoff":"2024-09-30"}},"o1":{"metadata":{"displayName":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2024-12-05","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"o1","displayName":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2023-09"}},"o1-pro":{"metadata":{"displayName":"o1-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2023-09","structuredOutput":true,"lastUpdated":"2025-03-19","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"o1-pro","displayName":"o1-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2023-09"}},"o3":{"metadata":{"displayName":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image","pdf"],"output":["text"]}},"entry":{"id":"o3","displayName":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"o3-mini":{"metadata":{"displayName":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-01-29","capabilities":{"vision":false,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"o3-mini","displayName":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"o3-pro":{"metadata":{"displayName":"o3-pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","lifecycle":"active","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-06-10","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"o3-pro","displayName":"o3-pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"o4-mini":{"metadata":{"displayName":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","lifecycle":"deprecated","contextWindow":200000,"maxOutputTokens":100000,"knowledgeCutoff":"2024-05","structuredOutput":true,"lastUpdated":"2025-04-16","capabilities":{"vision":true,"reasoning":true,"functionCalling":true},"thinkingOptions":{"efforts":["low","medium","high"]},"modalities":{"input":["text","image"],"output":["text"]}},"entry":{"id":"o4-mini","displayName":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","canUseAsChatDefault":true,"isDefault":false,"supportsVision":true,"defaultSupportsVision":true,"thinkingLevels":["low","medium","high"],"contextWindow":200000,"defaultContextWindow":200000,"knowledgeCutoff":"2024-05"}},"text-embedding-3-large":{"metadata":{"displayName":"text-embedding-3-large","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8191,"maxOutputTokens":3072,"knowledgeCutoff":"2024-01","lastUpdated":"2024-01-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"text-embedding-3-large","displayName":"text-embedding-3-large","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8191,"defaultContextWindow":8191,"knowledgeCutoff":"2024-01"}},"text-embedding-3-small":{"metadata":{"displayName":"text-embedding-3-small","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8191,"maxOutputTokens":1536,"knowledgeCutoff":"2024-01","lastUpdated":"2024-01-25","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"text-embedding-3-small","displayName":"text-embedding-3-small","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8191,"defaultContextWindow":8191,"knowledgeCutoff":"2024-01"}},"text-embedding-ada-002":{"metadata":{"displayName":"text-embedding-ada-002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","lifecycle":"active","contextWindow":8192,"maxOutputTokens":1536,"knowledgeCutoff":"2022-12","lastUpdated":"2022-12-15","capabilities":{"vision":false,"reasoning":false,"functionCalling":false},"modalities":{"input":["text"],"output":["text"]}},"entry":{"id":"text-embedding-ada-002","displayName":"text-embedding-ada-002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":[],"contextWindow":8192,"defaultContextWindow":8192,"knowledgeCutoff":"2022-12"}},"gpt-6-sol":{"metadata":{"displayName":"GPT-6 Sol","thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"maxOutputTokens":128000},"entry":{"id":"gpt-6-sol","displayName":"GPT-6 Sol","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high","xhigh","max"]}},"gpt-6-luna":{"metadata":{"displayName":"GPT-6 Luna","thinkingOptions":{"efforts":["low","medium","high","xhigh","max"]},"maxOutputTokens":128000},"entry":{"id":"gpt-6-luna","displayName":"GPT-6 Luna","canUseAsChatDefault":true,"isDefault":false,"supportsVision":false,"defaultSupportsVision":false,"thinkingLevels":["low","medium","high","xhigh","max"]}}}},"zhipu":{"label":"Zhipu AI (China)","baseUrl":"https://open.bigmodel.cn/api/paas/v4","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}},"zhipu-coding-plan":{"label":"Zhipu AI Coding Plan (China)","baseUrl":"https://open.bigmodel.cn/api/coding/paas/v4","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}},"modelscope":{"label":"ModelScope","baseUrl":"https://api-inference.modelscope.cn/v1","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{},"retired":false,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}},"aihubmix":{"label":"AiHubMix","baseUrl":"https://aihubmix.com/v1","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{"openai-responses":{"kind":"openai","apiProtocol":"openai-responses","responses":{"adapter":"openai","reasoningReplay":"none"}}},"retired":false,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}},"tencent-token-plan-enterprise":{"label":"Tencent Cloud Token Plan Enterprise (China)","baseUrl":"https://tokenhub.tencentmaas.com/plan/v3","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{"openai-responses":{"kind":"openai","apiProtocol":"openai-responses","responses":{"adapter":"openai","reasoningReplay":"none"}}},"retired":false,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}},"tencent-token-plan-enterprise-intl":{"label":"Tencent Cloud Token Plan Enterprise (Singapore)","baseUrl":"https://tokenhub-intl.tencentmaas.com/plan/v3","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"provider"},"protocolAdapters":{"openai-responses":{"kind":"openai","apiProtocol":"openai-responses","responses":{"adapter":"openai","reasoningReplay":"none"}}},"retired":false,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}},"sub2api":{"label":"Sub2API","baseUrl":"","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"connection","requireBaseUrl":true},"protocolAdapters":{},"retired":false,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}},"new-api":{"label":"New API","baseUrl":"","authKind":"api_key","runtimeAdapter":{"kind":"openai-compatible","name":"connection","requireBaseUrl":true},"protocolAdapters":{},"retired":false,"modelDiscovery":{"kind":"protocol"},"fallbackModels":[],"models":{}}} diff --git a/plugins/agent/providers/src/api.rs b/plugins/agent/providers/src/api.rs index 168fa4dc609..48ae8ca26cb 100644 --- a/plugins/agent/providers/src/api.rs +++ b/plugins/agent/providers/src/api.rs @@ -254,6 +254,23 @@ impl ApiProvider { } .into() }); + if self.id == "deepseek" + && canonical_endpoint.as_deref() == Some(configuration.base_url.as_str()) + && route.wire == Wire::OpenaiResponses + && let Some(web_search) = self + .facts + .models + .get(&info.id) + .and_then(|model| model.metadata.capabilities) + .and_then(|capabilities| capabilities.web_search) + { + info.capabilities.get_or_insert_default().web_search = request + .overrides + .as_ref() + .and_then(|overrides| overrides.capabilities.as_ref()) + .and_then(|capabilities| capabilities.web_search) + .or(Some(web_search)); + } let model = Model { adapter, protocol: route.kind, diff --git a/plugins/agent/providers/src/api/preferred.rs b/plugins/agent/providers/src/api/preferred.rs index dd08b284623..25a50b95200 100644 --- a/plugins/agent/providers/src/api/preferred.rs +++ b/plugins/agent/providers/src/api/preferred.rs @@ -26,7 +26,10 @@ pub(super) fn resolve(provider: &str, model: &str) -> Wire { if lower.starts_with("gpt-5") || lower.starts_with("gpt-6") || (provider == "deepseek" - && matches!(lower.as_str(), "deepseek-v4-flash" | "deepseek-v4-pro")) + && matches!( + lower.as_str(), + "deepseek-flash" | "deepseek-v4-flash" | "deepseek-v4-pro" + )) || (provider == "opencode-go" && model == "muse-spark-1.2-contributor") || (matches!(provider, "alibaba-token-plan" | "alibaba-token-plan-cn") && model == "qwen3.8-max") diff --git a/plugins/agent/providers/src/codex/provider.rs b/plugins/agent/providers/src/codex/provider.rs index 695698159ba..9ae28d94f89 100644 --- a/plugins/agent/providers/src/codex/provider.rs +++ b/plugins/agent/providers/src/codex/provider.rs @@ -158,8 +158,9 @@ impl Provider for Codex { if summary || level.is_some() { options["openai"]["forceReasoning"] = json!(true); } - info.capabilities.get_or_insert_default().native_compaction = - Some(configuration.server_side_compaction); + let capabilities = info.capabilities.get_or_insert_default(); + capabilities.web_search.get_or_insert(true); + capabilities.native_compaction = Some(configuration.server_side_compaction); let model = Model { main_output_limit: request .overrides diff --git a/plugins/settings/settings/package.ts b/plugins/settings/settings/package.ts index cdc36c0c575..bb05ee770a6 100644 --- a/plugins/settings/settings/package.ts +++ b/plugins/settings/settings/package.ts @@ -39,6 +39,7 @@ export default { setup: one(sdk.contracts.settingsSetup), agent: one(sdk.contracts.agent), skills: { contract: sdk.contracts.skillLibrary, cardinality: { kind: 'optional' } }, + web: { contract: sdk.contracts.workspaceWeb, cardinality: { kind: 'optional' } }, management: one(sdk.contracts.deploymentManager), receipts: one(sdk.contracts.receiptReader), }, @@ -80,6 +81,13 @@ export default { translations: { 'zh-CN': '外部 Agent', 'zh-TW': '外部 Agent' }, }, }, + 'web-search': { + kind: 'settings', + title: { + fallback: 'Web search', + translations: { 'zh-CN': '网页搜索', 'zh-TW': '網頁搜尋' }, + }, + }, network: { kind: 'settings', title: { fallback: 'Network', translations: { 'zh-CN': '网络', 'zh-TW': '網路' } }, diff --git a/plugins/settings/settings/ui.tsx b/plugins/settings/settings/ui.tsx index 76d15c8b424..ceda9a1fc62 100644 --- a/plugins/settings/settings/ui.tsx +++ b/plugins/settings/settings/ui.tsx @@ -30,6 +30,8 @@ import { ModelSettings } from '../../../products/maka/workbench/app/ModelSetting import { ConnectionSettings } from '../../../products/maka/workbench/app/ConnectionSettings'; import { GeneralSettings } from '../../../products/maka/workbench/app/GeneralSettings'; import { NetworkSettings } from '../../../products/maka/workbench/app/NetworkSettings'; +import { WebSearchSettings } from '../../../products/maka/workbench/app/WebSearchSettings'; +import { createWebSearchSettings } from '../../../products/maka/workbench/app/webSearchSettingsState'; import { PluginSettings } from '../../../products/maka/workbench/app/PluginSettings'; import { SkillSettings } from '../../../products/maka/workbench/app/SkillSettings'; import { ExternalAgentSettings } from '../../../products/maka/workbench/app/ExternalAgentSettings'; @@ -115,6 +117,7 @@ export const activate: UiModule['activate'] = (context) => { restored?.general, (locale) => runtime.setLocale(locale), ); + const webSearch = createWebSearchSettings(host, operations, active('web-search')); const network = createNetworkSettings(host, operations, active('network'), restored?.network); const plugins = createPluginSettings( host, @@ -169,6 +172,7 @@ export const activate: UiModule['activate'] = (context) => { ['createPreset', 'updatePreset', 'deletePreset'].includes(original.method) ) await presets.recovered(value); + else if (original.endpoint === 'web') await webSearch.load(); else if (original.endpoint === 'skills') skills.recovered(); else if (original.endpoint === 'agent' && original.method === 'manageMcpServer') mcp.recovered(); @@ -423,6 +427,24 @@ export const activate: UiModule['activate'] = (context) => { () => , ), }, + 'web-search': { + kind: 'settings', + render: (props) => + mountPage( + 'web-search', + webSearch, + props, + { + title: webSearch.title, + nested: () => false, + navigation: webSearch.navigation, + back: webSearch.back, + leave: webSearch.leave, + busy: operations.busy, + }, + () => , + ), + }, network: { kind: 'settings', render: (props) => diff --git a/plugins/workspace/workspace-web/api/src/contract.rs b/plugins/workspace/workspace-web/api/src/contract.rs index d308f162d2a..b6bde96fb6e 100644 --- a/plugins/workspace/workspace-web/api/src/contract.rs +++ b/plugins/workspace/workspace-web/api/src/contract.rs @@ -48,7 +48,7 @@ pub struct Capture { pub basis: Basis, pub available: bool, pub source: crate::settings::Source, - pub credential_configured: bool, + pub custom_available: bool, } #[derive(Deserialize, JsonSchema)] #[serde(deny_unknown_fields)] @@ -76,6 +76,8 @@ pub struct Set { #[schemars(rename = "WebKey")] pub struct Key { pub revision: Option, + #[serde(default, rename = "settingsRevision")] + pub settings_revision: Option, } #[derive(Serialize, JsonSchema)] #[serde(tag = "kind", rename_all = "snake_case", deny_unknown_fields)] @@ -84,6 +86,7 @@ pub enum Update { Updated { snapshot: crate::settings::Snapshot }, Changed, InvalidKey, + InvalidSettings { message: String }, CheckUnavailable, } #[derive(Serialize, Deserialize, JsonSchema)] diff --git a/plugins/workspace/workspace-web/api/src/search.rs b/plugins/workspace/workspace-web/api/src/search.rs index 98bc60a2edd..76fe24d6d0b 100644 --- a/plugins/workspace/workspace-web/api/src/search.rs +++ b/plugins/workspace/workspace-web/api/src/search.rs @@ -26,7 +26,7 @@ pub struct Query { #[schemars(length(min = 1))] pub query: String, #[serde(default = "default_limit")] - // Tavily Search API supports max_results from 0 through 20. + // Presets share a 20-result request limit. #[schemars(range(min = 1, max = 20))] pub limit: usize, } diff --git a/plugins/workspace/workspace-web/api/src/settings.rs b/plugins/workspace/workspace-web/api/src/settings.rs index e80fefcc5ad..ac74768883e 100644 --- a/plugins/workspace/workspace-web/api/src/settings.rs +++ b/plugins/workspace/workspace-web/api/src/settings.rs @@ -18,7 +18,7 @@ */ use serde::{Deserialize, Serialize}; -pub const KEY: &str = "tavily"; +use std::collections::BTreeMap; #[derive( Clone, Copy, Default, Debug, Deserialize, Serialize, PartialEq, Eq, schemars::JsonSchema, @@ -28,14 +28,126 @@ pub const KEY: &str = "tavily"; pub enum Source { #[default] Model, - Tavily, + #[serde(alias = "tavily")] + Custom, } + #[derive(Clone, Default, Debug, Deserialize, Serialize, PartialEq, Eq, schemars::JsonSchema)] +#[serde(tag = "kind", rename_all = "snake_case", deny_unknown_fields)] +#[schemars(rename = "WebBackend")] +pub enum Backend { + #[default] + Tavily, + Brave, + Exa, + Serper, + Custom { + endpoint: Endpoint, + }, +} + +impl Backend { + pub fn preset_id(&self) -> Option<&'static str> { + match self { + Self::Tavily => Some("tavily"), + Self::Brave => Some("brave"), + Self::Exa => Some("exa"), + Self::Serper => Some("serper"), + Self::Custom { .. } => None, + } + } +} + +#[derive(Clone, Debug, Deserialize, Serialize, PartialEq, Eq, schemars::JsonSchema)] +#[serde(rename_all = "camelCase", deny_unknown_fields)] +#[schemars(rename = "WebSearchEndpoint")] +pub struct Endpoint { + pub url: String, + pub method: Method, + pub query: Parameter, + pub limit: Option, + pub url_parameters: BTreeMap, + pub body: serde_json::Map, + pub auth: Option, + pub results: ResultsMapping, +} + +#[derive(Clone, Copy, Debug, Deserialize, Serialize, PartialEq, Eq, schemars::JsonSchema)] +#[serde(rename_all = "snake_case")] +#[schemars(rename = "WebSearchMethod")] +pub enum Method { + Get, + Post, +} + +#[derive(Clone, Copy, Debug, Deserialize, Serialize, PartialEq, Eq, schemars::JsonSchema)] +#[serde(rename_all = "snake_case")] +#[schemars(rename = "WebParameterLocation")] +pub enum ParameterLocation { + Query, + Body, +} + +#[derive(Clone, Debug, Deserialize, Serialize, PartialEq, Eq, schemars::JsonSchema)] +#[serde(deny_unknown_fields)] +#[schemars(rename = "WebParameter")] +pub struct Parameter { + pub location: ParameterLocation, + pub name: String, +} + +#[derive(Clone, Copy, Debug, Deserialize, Serialize, PartialEq, Eq, schemars::JsonSchema)] +#[serde(rename_all = "snake_case")] +#[schemars(rename = "WebAuthLocation")] +pub enum AuthLocation { + Header, + Query, + Body, +} + +#[derive(Clone, Debug, Deserialize, Serialize, PartialEq, Eq, schemars::JsonSchema)] +#[serde(deny_unknown_fields)] +#[schemars(rename = "WebAuth")] +pub struct Auth { + pub location: AuthLocation, + pub name: String, + pub prefix: String, +} + +/// JSON pointers, with an empty list pointer selecting the response root. +#[derive(Clone, Debug, Deserialize, Serialize, PartialEq, Eq, schemars::JsonSchema)] +#[serde(deny_unknown_fields)] +#[schemars(rename = "WebResultMapping")] +pub struct ResultsMapping { + pub list: String, + pub title: Option, + pub url: String, + pub snippet: Option, +} + +#[derive(Serialize, schemars::JsonSchema)] +#[schemars(rename = "WebSearchPreset")] +pub struct Preset { + pub id: &'static str, + pub endpoint: Endpoint, +} +#[derive(Clone, Debug, Deserialize, Serialize, PartialEq, Eq, schemars::JsonSchema)] #[schemars(rename = "WebSettings")] #[serde(deny_unknown_fields)] pub struct Settings { pub enabled: bool, pub source: Source, + #[serde(default)] + pub backend: Backend, +} +impl Default for Settings { + fn default() -> Self { + Self { + enabled: true, + source: Source::Model, + backend: Backend::default(), + } + } } #[derive(Serialize, schemars::JsonSchema)] #[schemars(rename = "WebSnapshot")] @@ -43,6 +155,7 @@ pub struct Snapshot { pub revision: Option, pub settings: Settings, pub credential: Credential, + pub presets: &'static [Preset], } #[derive(Serialize, schemars::JsonSchema)] #[schemars(rename = "WebCredential")] @@ -55,7 +168,9 @@ pub struct Credential { #[schemars(rename = "WebCheck")] #[serde(deny_unknown_fields)] pub struct Check { - pub credential_revision: u64, + pub credential_revision: Option, + #[serde(default)] + pub settings_revision: Option, pub outcome: CheckOutcome, } #[derive(Clone, Copy, Deserialize, Serialize, schemars::JsonSchema)] diff --git a/plugins/workspace/workspace-web/native/src/host.rs b/plugins/workspace/workspace-web/native/src/host.rs index b6d52b956a2..251a92d37eb 100644 --- a/plugins/workspace/workspace-web/native/src/host.rs +++ b/plugins/workspace/workspace-web/native/src/host.rs @@ -121,25 +121,20 @@ impl Web { })) } async fn capture(&self) -> Result { - let snapshot = self.repository.snapshot().await.map_err(message)?; + let current = self.repository.search_settings().await.map_err(message)?; Ok(Capture { basis: Basis { - revision: snapshot.revision, - credential_revision: snapshot.credential.revision, + revision: current.revision, + credential_revision: current.credential_revision(), }, - available: snapshot.settings.enabled, - source: snapshot.settings.source, - credential_configured: snapshot.credential.configured, + available: current.settings.enabled, + source: current.settings.source, + custom_available: current.available(), }) } - async fn current(&self, basis: &Basis, search: bool) -> Result { - let capture = self.capture().await?; - Ok(capture.available - && capture.basis.revision == basis.revision - && (!search - || (capture.source == maka_web_api::settings::Source::Tavily - && capture.basis.credential_revision == basis.credential_revision - && capture.credential_configured))) + async fn fetch_is_current(&self, basis: &Basis) -> Result { + let (revision, settings) = self.repository.settings().await.map_err(message)?; + Ok(settings.enabled && revision == basis.revision) } } struct Service(Arc); @@ -171,6 +166,13 @@ impl Handler for Service { match name.as_str() { "save" => { let input: Set = serde_json::from_value(input).map_err(message)?; + if let Err(message) = + crate::search::SearchEndpoint::resolve(&input.settings.backend) + { + return encode(Update::InvalidSettings { + message: message.into(), + }); + } match owner.repository.save(input.revision, input.settings).await { Ok(_) => encode(Update::Updated { snapshot: owner.repository.snapshot().await.map_err(message)?, @@ -211,6 +213,15 @@ impl Handler for Service { } "saveKey" | "deleteKey" => { let input: Key = serde_json::from_value(input).map_err(message)?; + let current = owner.repository.search_settings().await.map_err(message)?; + if current.revision != input.settings_revision + || current.credential_revision() != input.revision + { + return encode(Update::Changed); + } + let Some(key) = current.key else { + return encode(Update::InvalidKey); + }; let secret = if name == "saveKey" { let resource = context .attachments() @@ -235,7 +246,7 @@ impl Handler for Service { .repository .credentials .write(maka_capabilities::credentials::Write { - key: maka_web_api::settings::KEY.into(), + key, expected_revision: input.revision, secret, }) @@ -254,21 +265,47 @@ impl Handler for Service { } "fetch" | "search" => { let call: Call = serde_json::from_value(input).map_err(message)?; - if !owner.current(&call.basis, name == "search").await? { - return encode(ResultValue::Failed { message: "Web settings changed or access is disabled; request a new model step".into() }); - } - let input = call.input; + let (purpose, search) = if name == "search" { + let current = owner.repository.search_settings().await.map_err(message)?; + if !current.matches(&call.basis) { + return encode(ResultValue::Failed { message: "Web settings changed or access is disabled; request a new model step".into() }); + } + ( + network::Purpose::Search { + basis: call.basis, + key: current.key.clone(), + }, + Some(current), + ) + } else { + if !owner.fetch_is_current(&call.basis).await? { + return encode(ResultValue::Failed { message: "Web settings changed or access is disabled; request a new model step".into() }); + } + (network::Purpose::Fetch { basis: call.basis }, None) + }; let authority = network::Access::new( owner.clone(), context.scope(), native.ok_or("web_requires_native_call")?, - call.basis, - name == "search", + purpose, failure.clone(), )?; let client = Arc::new(maka_host_runtime::http::Http::new(Arc::new(authority))); - let result = if name == "fetch" { - let input: Fetch = serde_json::from_value(input).map_err(message)?; + let result = if let Some(current) = search { + let input: maka_web_api::search::Query = + serde_json::from_value(call.input).map_err(message)?; + crate::search::Search::new(client) + .query(context.scope(), ¤t.endpoint, current.secret(), &input) + .await + .map(|results| { + serde_json::to_value(results).expect("Web search results") + }) + .map_err(|error| match error { + crate::search::Error::Settlement(error) => error, + error => maka_agent_facts::tools::ToolError::Failed(message(error)), + }) + } else { + let input: Fetch = serde_json::from_value(call.input).map_err(message)?; crate::fetch::Fetcher::new(client) .fetch(context.scope(), &input.url) .await @@ -282,33 +319,6 @@ impl Handler for Service { ), error => maka_agent_facts::tools::ToolError::Failed(message(error)), }) - } else { - let input: maka_web_api::search::Query = - serde_json::from_value(input).map_err(message)?; - let (_, settings) = owner.repository.settings().await.map_err(message)?; - if settings.source != maka_web_api::settings::Source::Tavily { - return encode(ResultValue::Failed { - message: "Search is supplied by the selected model".into(), - }); - } - let key = owner - .repository - .credentials - .read(maka_web_api::settings::KEY.into()) - .await - .map_err(message)? - .and_then(|r| r.secret) - .ok_or("web_search_key_missing")?; - crate::search::Search::new(client) - .query(context.scope(), &key, &input) - .await - .map(|results| { - serde_json::to_value(results).expect("Web search results") - }) - .map_err(|error| match error { - crate::search::Error::Settlement(error) => error, - error => maka_agent_facts::tools::ToolError::Failed(message(error)), - }) }; if let Err(error) = &result { failure.observe(error); diff --git a/plugins/workspace/workspace-web/native/src/host/check.rs b/plugins/workspace/workspace-web/native/src/host/check.rs index 39f2dac9f82..6e3783df477 100644 --- a/plugins/workspace/workspace-web/native/src/host/check.rs +++ b/plugins/workspace/workspace-web/native/src/host/check.rs @@ -28,32 +28,33 @@ pub(super) async fn run( failure: network::Failure, ) -> Result { let input: Key = serde_json::from_value(input).map_err(message)?; - let credential = owner - .repository - .credentials - .read(settings::KEY.into()) - .await - .map_err(message)?; - if credential.as_ref().map(|value| value.revision) != input.revision { + let current = owner.repository.search_settings().await.map_err(message)?; + if current.revision != input.settings_revision + || current.credential_revision() != input.revision + { return encode(Update::Changed); } - let Some(credential) = credential else { - return encode(Update::CheckUnavailable); - }; - let Some(secret) = credential.secret else { + if current.key.is_some() && current.secret().is_none() { return encode(Update::CheckUnavailable); + } + let basis = Basis { + revision: current.revision, + credential_revision: current.credential_revision(), }; let authority = network::CredentialCheck { owner: owner.clone(), caller: context.scope().clone(), - revision: credential.revision, + basis, + key: current.key.clone(), + destination: current.endpoint.destination.clone(), failure: failure.clone(), }; let http = Arc::new(maka_host_runtime::http::Http::new(Arc::new(authority))); let result = search::Search::new(http) .query( context.scope(), - &secret, + ¤t.endpoint, + current.secret(), &Query { query: "Maka AI assistant".into(), limit: 1, @@ -79,25 +80,21 @@ pub(super) async fn run( | search::Error::Cancelled, ) => return encode(Update::CheckUnavailable), }; - if owner + if !owner .repository - .snapshot() + .record_check( + settings::Check { + settings_revision: current.revision, + credential_revision: current.credential_revision(), + outcome, + }, + current.key.as_deref(), + ) .await .map_err(message)? - .credential - .revision - != input.revision { return encode(Update::Changed); } - owner - .repository - .record_check(settings::Check { - credential_revision: credential.revision, - outcome, - }) - .await - .map_err(message)?; encode(Update::Updated { snapshot: owner.repository.snapshot().await.map_err(message)?, }) diff --git a/plugins/workspace/workspace-web/native/src/host/network.rs b/plugins/workspace/workspace-web/native/src/host/network.rs index fa2837615f3..0d053468481 100644 --- a/plugins/workspace/workspace-web/native/src/host/network.rs +++ b/plugins/workspace/workspace-web/native/src/host/network.rs @@ -98,8 +98,9 @@ pub(super) async fn native_call( } #[derive(Clone)] -enum Purpose { - Retrieval { basis: Basis, search: bool }, +pub(super) enum Purpose { + Fetch { basis: Basis }, + Search { basis: Basis, key: Option }, Health, } #[derive(Clone)] @@ -115,17 +116,16 @@ impl Access { owner: Arc, scope: &Scope, native: Arc, - basis: Basis, - search: bool, + purpose: Purpose, failure: Failure, ) -> Result { - Self::for_purpose( + Ok(Self { owner, - scope, native, - Purpose::Retrieval { basis, search }, + caller: scope.clone(), + purpose, failure, - ) + }) } pub fn health( owner: Arc, @@ -133,22 +133,7 @@ impl Access { native: Arc, failure: Failure, ) -> Result { - Self::for_purpose(owner, scope, native, Purpose::Health, failure) - } - fn for_purpose( - owner: Arc, - scope: &Scope, - native: Arc, - purpose: Purpose, - failure: Failure, - ) -> Result { - Ok(Self { - owner, - native, - caller: scope.clone(), - purpose, - failure, - }) + Self::new(owner, scope, native, Purpose::Health, failure) } async fn current( &self, @@ -157,7 +142,13 @@ impl Access { ) -> Result<(maka_agent_api::session::ResolvedConfiguration, bool), Error> { let _lease = self.admit(call)?; let available = match &self.purpose { - Purpose::Retrieval { basis, search } => self.owner.current(basis, *search).await, + Purpose::Fetch { basis } => self.owner.fetch_is_current(basis).await, + Purpose::Search { basis, key } => self + .owner + .repository + .search_is_current(basis, key.as_deref()) + .await + .map_err(message), Purpose::Health => Ok(true), } .map_err(Error::Failed)?; @@ -233,7 +224,9 @@ impl Access { PermissionRequest { reason: match self.purpose { Purpose::Health => format!("Allow health check access to {origin}"), - Purpose::Retrieval { .. } => format!("Allow Web access to {origin}"), + Purpose::Fetch { .. } | Purpose::Search { .. } => { + format!("Allow Web access to {origin}") + } }, command: None, permissions: maka_sandbox::grant::Permissions { @@ -387,7 +380,9 @@ fn spawn(owner: &Web, worker: Worker) -> Result<(), Error> { pub(super) struct CredentialCheck { pub owner: Arc, pub caller: Scope, - pub revision: u64, + pub basis: Basis, + pub key: Option, + pub destination: Destination, pub failure: Failure, } impl Authority for CredentialCheck { @@ -431,22 +426,19 @@ impl Authority for CredentialCheck { ) -> BoxFuture<'a, Result<(), Error>> { Box::pin(async move { let _lease = self.admit(call)?; - if destination.host() != "api.tavily.com" - || destination.port() != 443 + if *destination != self.destination || !self.owner.network.allows(destination) || !floor_network(call.sandbox_floor()).allows(destination) || !floor_network(self.caller.sandbox_floor()).allows(destination) { return Err(Error::Denied); } - let snapshot = self + if !self .owner .repository - .snapshot() + .search_is_current(&self.basis, self.key.as_deref()) .await - .map_err(|e| Error::Failed(e.to_string()))?; - if snapshot.credential.revision != Some(self.revision) - || !snapshot.credential.configured + .map_err(|error| Error::Failed(error.to_string()))? { return Err(Error::Denied); } diff --git a/plugins/workspace/workspace-web/native/src/search.rs b/plugins/workspace/workspace-web/native/src/search.rs index 7e23e674ce3..89fc67c015f 100644 --- a/plugins/workspace/workspace-web/native/src/search.rs +++ b/plugins/workspace/workspace-web/native/src/search.rs @@ -19,12 +19,19 @@ use maka_capabilities::call; use maka_capabilities::http; -use maka_plugin_core::http::Method; -use serde::{Deserialize, Serialize}; +use serde_json::Value; use std::sync::Arc; use url::Url; -use maka_web_api::search::{Query, Results, Row}; +use maka_web_api::{ + search::{Query, Results, Row}, + settings::ResultsMapping, +}; + +mod endpoint; +#[cfg(test)] +mod tests; +pub(crate) use endpoint::{SearchEndpoint, presets}; #[derive(Debug, thiserror::Error)] pub enum Error { @@ -51,7 +58,7 @@ pub enum Error { } #[derive(Clone)] -pub struct Search { +pub(crate) struct Search { http: Arc, } impl Search { @@ -62,21 +69,19 @@ impl Search { pub async fn query( &self, parent: &call::Scope, - key: &str, + endpoint: &SearchEndpoint, + key: Option<&str>, input: &Query, ) -> Result { if !input.is_valid() { return Err(Error::Input); } - if key.trim().is_empty() { - return Err(Error::NotConfigured); - } let owned = call::Owned::new(parent.child()?); let scope = owned.scope(); let result = tokio::select! { biased; _ = scope.cancellation.cancelled() => Err(Error::Cancelled), - result = self.request(&scope, key, input) => result, + result = self.request(&scope, endpoint, key, input) => result, }; owned.finish().await?; result @@ -85,34 +90,13 @@ impl Search { async fn request( &self, scope: &call::Scope, - key: &str, + endpoint: &SearchEndpoint, + key: Option<&str>, input: &Query, ) -> Result { - #[derive(Serialize)] - struct Request<'a> { - api_key: &'a str, - query: &'a str, - max_results: usize, - search_depth: &'static str, - } let response = self .http - .request( - scope.clone(), - http::Request { - url: "https://api.tavily.com/search".into(), - method: Method::Post, - headers: vec![("Content-Type".into(), "application/json".into())], - body: serde_json::to_vec(&Request { - api_key: key, - query: &input.query, - max_results: input.limit, - search_depth: "basic", - }) - .map_err(|_| Error::Input)? - .into(), - }, - ) + .request(scope.clone(), endpoint.request(key, input)?) .await .map_err(network_error)?; let result = async { @@ -126,7 +110,7 @@ impl Search { while let Some(chunk) = response.body.next().await.map_err(network_error)? { bytes.extend_from_slice(&chunk); } - decode(&bytes, input) + decode(&bytes, input, &endpoint.config.results) } .await; // Never follow redirects with a search credential. @@ -146,42 +130,38 @@ fn network_error(error: http::Error) -> Error { } } -fn decode(bytes: &[u8], input: &Query) -> Result { - #[derive(Deserialize)] - struct Response { - results: Vec, - } - #[derive(Deserialize)] - struct Entry { - title: String, - url: String, - #[serde(default)] - content: String, - } - let response: Response = serde_json::from_slice(bytes).map_err(|_| Error::Response)?; - let total = response.results.len(); - let rows = response - .results - .into_iter() +fn decode(bytes: &[u8], input: &Query, mapping: &ResultsMapping) -> Result { + let response: Value = serde_json::from_slice(bytes).map_err(|_| Error::Response)?; + let entries = response.pointer(&mapping.list).ok_or(Error::Response)?; + let entries = if entries.is_null() { + &[][..] + } else { + entries.as_array().ok_or(Error::Response)?.as_slice() + }; + let rows = entries + .iter() .filter_map(|entry| { - let entry: Entry = serde_json::from_value(entry).ok()?; - let url = Url::parse(&entry.url).ok()?; + let url = Url::parse(entry.pointer(&mapping.url)?.as_str()?).ok()?; if !matches!(url.scheme(), "http" | "https") || !url.username().is_empty() || url.password().is_some() { return None; } - let title = entry.title; - let snippet = entry.content; + let field = |path: &Option| { + path.as_deref() + .and_then(|path| entry.pointer(path)) + .and_then(Value::as_str) + }; Some(Row { - title, - snippet, - url: url.to_string(), + title: field(&mapping.title).unwrap_or(url.as_str()).into(), + snippet: field(&mapping.snippet).unwrap_or_default().into(), + url: url.into(), }) }) .take(input.limit) .collect::>(); + let total = entries.len(); let omitted_results = total - rows.len(); Ok(Results { query: input.query.clone(), @@ -191,7 +171,7 @@ fn decode(bytes: &[u8], input: &Query) -> Result { }) } -pub fn native( +fn native( model: &maka_agent_facts::tools::ModelToolContext, ) -> Option { use maka_agent_facts::tools::ProviderTool; @@ -205,9 +185,39 @@ pub fn native( id: "openai.web_search".into(), args: serde_json::json!({"searchContextSize":"medium"}), }, + ProviderToolProtocol::DeepseekResponses => ProviderTool { + id: match model.model.as_str() { + "deepseek-v4-pro" => "deepseek.web_search", + "deepseek-flash" | "deepseek-v4-flash" => "deepseek.deepseek_web_search", + _ => return None, + } + .into(), + args: serde_json::json!({}), + }, ProviderToolProtocol::AnthropicMessages => ProviderTool { id: "anthropic.web_search_20250305".into(), args: serde_json::json!({"maxUses":8}), }, }) } + +pub enum Selection { + Provider(maka_agent_facts::tools::ProviderTool), + Custom, +} + +pub fn select( + capture: &maka_web_api::contract::Capture, + model: Option<&maka_agent_facts::tools::ModelToolContext>, +) -> Option { + if !capture.available { + return None; + } + if capture.source == maka_web_api::settings::Source::Custom && capture.custom_available { + return Some(Selection::Custom); + } + model + .and_then(native) + .map(Selection::Provider) + .or_else(|| capture.custom_available.then_some(Selection::Custom)) +} diff --git a/plugins/workspace/workspace-web/native/src/search/endpoint.rs b/plugins/workspace/workspace-web/native/src/search/endpoint.rs new file mode 100644 index 00000000000..f86e1dbff67 --- /dev/null +++ b/plugins/workspace/workspace-web/native/src/search/endpoint.rs @@ -0,0 +1,320 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, + * software distributed under the License is distributed on an + * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + * KIND, either express or implied. See the License for the + * specific language governing permissions and limitations + * under the License. + */ + +use maka_web_api::{search::Query, settings::*}; +use serde_json::{Value, json}; +use url::Url; + +pub(crate) fn presets() -> &'static [Preset] { + static PRESETS: std::sync::LazyLock> = std::sync::LazyLock::new(build_presets); + &PRESETS +} + +fn build_presets() -> Vec { + [ + ( + Backend::Tavily, + "https://api.tavily.com/search", + Method::Post, + "query", + "max_results", + "Authorization", + "Bearer ", + "/results", + "/url", + "/content", + json!({"search_depth":"basic"}), + ), + ( + Backend::Brave, + "https://api.search.brave.com/res/v1/web/search", + Method::Get, + "q", + "count", + "X-Subscription-Token", + "", + "/web/results", + "/url", + "/description", + json!({}), + ), + ( + Backend::Exa, + "https://api.exa.ai/search", + Method::Post, + "query", + "numResults", + "x-api-key", + "", + "/results", + "/url", + "/highlights/0", + json!({"contents":{"highlights":true}}), + ), + ( + Backend::Serper, + "https://google.serper.dev/search", + Method::Post, + "q", + "num", + "X-API-KEY", + "", + "/organic", + "/link", + "/snippet", + json!({}), + ), + ] + .into_iter() + .map( + |(backend, url, method, query, limit, header, prefix, list, result_url, snippet, body)| { + let location = match method { + Method::Get => ParameterLocation::Query, + Method::Post => ParameterLocation::Body, + }; + Preset { + id: backend.preset_id().expect("preset backend"), + endpoint: Endpoint { + url: url.into(), + method, + query: Parameter { + location, + name: query.into(), + }, + limit: Some(Parameter { + location, + name: limit.into(), + }), + url_parameters: Default::default(), + body: body.as_object().expect("preset JSON body").clone(), + auth: Some(Auth { + location: AuthLocation::Header, + name: header.into(), + prefix: prefix.into(), + }), + results: ResultsMapping { + list: list.into(), + title: Some("/title".into()), + url: result_url.into(), + snippet: Some(snippet.into()), + }, + }, + } + }, + ) + .collect() +} + +#[derive(Clone)] +pub(crate) struct SearchEndpoint { + pub config: Endpoint, + url: Url, + pub destination: maka_sandbox::Destination, +} + +impl SearchEndpoint { + pub fn resolve(backend: &Backend) -> Result { + let config = match backend { + Backend::Custom { endpoint } => endpoint.clone(), + preset => presets() + .iter() + .find(|item| Some(item.id) == preset.preset_id()) + .expect("known search preset") + .endpoint + .clone(), + }; + let url = Url::parse(&config.url).map_err(|_| "Enter a valid HTTP or HTTPS search URL.")?; + if !matches!(url.scheme(), "http" | "https") + || url.host_str().is_none() + || !url.username().is_empty() + || url.password().is_some() + || url.fragment().is_some() + { + return Err("Enter an HTTP or HTTPS search URL without credentials or a fragment."); + } + let mut query = url + .query_pairs() + .map(|(name, _)| name.into_owned()) + .chain(config.url_parameters.keys().cloned()) + .collect::>(); + let mut body = config + .body + .keys() + .cloned() + .collect::>(); + for (location, name) in std::iter::once(&config.query) + .chain(config.limit.as_ref()) + .map(|parameter| (parameter.location, parameter.name.as_str())) + .chain(config.auth.iter().filter_map(|auth| { + let location = match auth.location { + AuthLocation::Header => return None, + AuthLocation::Query => ParameterLocation::Query, + AuthLocation::Body => ParameterLocation::Body, + }; + Some((location, auth.name.as_str())) + })) + { + let names = match location { + ParameterLocation::Query => &mut query, + ParameterLocation::Body => &mut body, + }; + if name.trim().is_empty() + || name.chars().any(char::is_control) + || !names.insert(name.into()) + { + return Err( + "Query, result limit, and authentication parameters must have distinct names in each location.", + ); + } + } + if config.method == Method::Get && !body.is_empty() { + return Err("GET search requests cannot have a JSON body."); + } + if let Some(auth) = &config.auth + && auth.location == AuthLocation::Header + && (auth.name.is_empty() + || !auth + .name + .bytes() + .all(|byte| byte.is_ascii_alphanumeric() || b"!#$%&'*+-.^`_|~".contains(&byte)) + || matches!( + auth.name.to_ascii_lowercase().as_str(), + "host" + | "connection" + | "content-length" + | "transfer-encoding" + | "upgrade" + | "proxy-authorization" + | "proxy-connection" + | "content-type" + | "accept" + ) + || auth.prefix.bytes().any(|byte| byte.is_ascii_control())) + { + return Err("Enter a valid authentication header name and prefix."); + } + let pointer = |value: &str| value.is_empty() || value.starts_with('/'); + if !pointer(&config.results.list) + || config.results.url.is_empty() + || !pointer(&config.results.url) + || config + .results + .title + .as_deref() + .is_some_and(|value| !pointer(value)) + || config + .results + .snippet + .as_deref() + .is_some_and(|value| !pointer(value)) + { + return Err("Use JSON pointers such as /results and /url for the result fields."); + } + let destination = maka_sandbox::Destination::new( + url.host_str().expect("validated search host"), + url.port_or_known_default().expect("validated search port"), + ) + .map_err(|_| "Enter a valid search host and port.")?; + Ok(Self { + config, + url, + destination, + }) + } + + pub fn credential_key(&self, backend: &Backend) -> Option { + let auth = self.config.auth.as_ref()?; + Some(match backend.preset_id() { + Some(id) => id.into(), + None => maka_agent_facts::artifact::content_digest( + &serde_json::to_vec(&(self.url.as_str(), auth)) + .expect("search credential identity"), + ), + }) + } + + pub fn request( + &self, + secret: Option<&str>, + input: &Query, + ) -> Result { + let mut url = self.url.clone(); + if !self.config.url_parameters.is_empty() { + url.query_pairs_mut() + .extend_pairs(&self.config.url_parameters); + } + let mut body = self.config.body.clone(); + let mut headers = vec![("Accept".into(), "application/json".into())]; + let mut add_parameter = |location, name: &str, value: Value| match location { + ParameterLocation::Query => { + let serialized; + let text = if let Some(value) = value.as_str() { + value + } else { + serialized = value.to_string(); + &serialized + }; + url.query_pairs_mut().append_pair(name, text); + } + ParameterLocation::Body => { + body.insert(name.into(), value); + } + }; + add_parameter( + self.config.query.location, + &self.config.query.name, + json!(input.query), + ); + if let Some(limit) = &self.config.limit { + add_parameter(limit.location, &limit.name, json!(input.limit)); + } + if let Some(auth) = &self.config.auth { + let value = format!( + "{}{}", + auth.prefix, + secret.ok_or(super::Error::NotConfigured)? + ); + match auth.location { + AuthLocation::Header => headers.push((auth.name.clone(), value)), + AuthLocation::Query => { + add_parameter(ParameterLocation::Query, &auth.name, json!(value)) + } + AuthLocation::Body => { + add_parameter(ParameterLocation::Body, &auth.name, json!(value)) + } + } + } + let (method, body) = match self.config.method { + Method::Get => (maka_plugin_core::http::Method::Get, Vec::new()), + Method::Post => { + headers.push(("Content-Type".into(), "application/json".into())); + ( + maka_plugin_core::http::Method::Post, + serde_json::to_vec(&body).expect("JSON search body"), + ) + } + }; + Ok(maka_capabilities::http::Request { + url: url.into(), + method, + headers, + body: body.into(), + }) + } +} diff --git a/plugins/workspace/workspace-web/native/src/search/tests.rs b/plugins/workspace/workspace-web/native/src/search/tests.rs new file mode 100644 index 00000000000..61b8cfb8fe5 --- /dev/null +++ b/plugins/workspace/workspace-web/native/src/search/tests.rs @@ -0,0 +1,217 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, + * software distributed under the License is distributed on an + * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + * KIND, either express or implied. See the License for the + * specific language governing permissions and limitations + * under the License. + */ + +use super::*; +use maka_agent_facts::tools::{ModelToolContext, ProviderToolProtocol}; +use maka_web_api::{ + contract::{Basis, Capture}, + settings::{Auth, AuthLocation, Backend, Source}, +}; +use serde_json::json; + +#[test] +fn saved_tavily_preference_keeps_the_tavily_credential() { + let settings: maka_web_api::settings::Settings = + serde_json::from_value(json!({"enabled":true,"source":"tavily"})).unwrap(); + assert_eq!(settings.source, Source::Custom); + assert_eq!( + SearchEndpoint::resolve(&settings.backend) + .unwrap() + .credential_key(&settings.backend) + .as_deref(), + Some("tavily") + ); +} + +#[test] +fn search_uses_first_available_source() { + let model = ModelToolContext { + model: "test".into(), + capabilities: maka_agent_facts::configuration::ModelCapabilities { + web_search: Some(true), + ..Default::default() + }, + provider_tools: Some(ProviderToolProtocol::OpenaiResponses), + }; + let mut capture = Capture { + basis: Basis { + revision: None, + credential_revision: None, + }, + available: true, + source: Source::Model, + custom_available: true, + }; + assert!( + matches!(select(&capture, Some(&model)), Some(Selection::Provider(tool)) if tool.id == "openai.web_search") + ); + assert!(matches!(select(&capture, None), Some(Selection::Custom))); + capture.source = Source::Custom; + assert!(matches!( + select(&capture, Some(&model)), + Some(Selection::Custom) + )); + capture.custom_available = false; + assert!(matches!( + select(&capture, Some(&model)), + Some(Selection::Provider(_)) + )); + assert!(select(&capture, None).is_none()); + capture.available = false; + assert!(select(&capture, Some(&model)).is_none()); +} + +#[test] +fn presets_encode_provider_requests_and_read_results() { + let search = Query { + query: "rust + web".into(), + limit: 3, + }; + for (backend, endpoint_url, header, credential, params, response) in [ + ( + Backend::Tavily, + "https://api.tavily.com/search", + "Authorization", + "Bearer token", + json!({"query":"rust + web","max_results":3,"search_depth":"basic"}), + json!({"results":[{"title":"Rust","url":"https://rust-lang.org/","content":"A language"}]}), + ), + ( + Backend::Brave, + "https://api.search.brave.com/res/v1/web/search?q=rust+%2B+web&count=3", + "X-Subscription-Token", + "token", + Value::Null, + json!({"web":{"results":[{"title":"Rust","url":"https://rust-lang.org/","description":"A language"}]}}), + ), + ( + Backend::Exa, + "https://api.exa.ai/search", + "x-api-key", + "token", + json!({"query":"rust + web","numResults":3,"contents":{"highlights":true}}), + json!({"results":[{"title":"Rust","url":"https://rust-lang.org/","highlights":["A language"]}]}), + ), + ( + Backend::Serper, + "https://google.serper.dev/search", + "X-API-KEY", + "token", + json!({"q":"rust + web","num":3}), + json!({"organic":[{"title":"Rust","link":"https://rust-lang.org/","snippet":"A language"}]}), + ), + ] { + let endpoint = SearchEndpoint::resolve(&backend).unwrap(); + let request = endpoint.request(Some("token"), &search).unwrap(); + assert_eq!(request.url, endpoint_url); + assert!( + request + .headers + .contains(&(header.into(), credential.into())) + ); + if params.is_null() { + assert!(matches!( + request.method, + maka_plugin_core::http::Method::Get + )); + assert_eq!(request.body.length(), Some(0)); + } else { + assert!(matches!( + request.method, + maka_plugin_core::http::Method::Post + )); + assert_eq!(body(request.body), params); + } + let result = decode( + &serde_json::to_vec(&response).unwrap(), + &search, + &endpoint.config.results, + ) + .unwrap(); + assert_eq!( + serde_json::to_value(&result.rows).unwrap(), + json!([{"title":"Rust","url":"https://rust-lang.org/","snippet":"A language"}]) + ); + } +} + +#[test] +fn custom_search_injects_credentials_in_configured_location_only() { + let mut config = presets()[0].endpoint.clone(); + config.url = "https://search.example/query".into(); + config.url_parameters.insert("region".into(), "cn".into()); + let search = Query { + query: "a & b".into(), + limit: 2, + }; + for location in [AuthLocation::Query, AuthLocation::Body] { + config.auth = Some(Auth { + location, + name: "key".into(), + prefix: "".into(), + }); + let endpoint = SearchEndpoint::resolve(&Backend::Custom { + endpoint: config.clone(), + }) + .unwrap(); + let request = endpoint.request(Some("secret/word"), &search).unwrap(); + assert!( + request + .headers + .iter() + .all(|(_, value)| !value.contains("secret")) + ); + let body = body(request.body); + assert_eq!(body["query"], "a & b"); + if location == AuthLocation::Query { + assert_eq!( + request.url, + "https://search.example/query?region=cn&key=secret%2Fword" + ); + assert!(body.get("key").is_none()); + } else { + assert_eq!(request.url, "https://search.example/query?region=cn"); + assert_eq!(body["key"], "secret/word"); + } + } + config.auth = None; + let backend = Backend::Custom { endpoint: config }; + let endpoint = SearchEndpoint::resolve(&backend).unwrap(); + assert!(endpoint.credential_key(&backend).is_none()); + assert!(endpoint.request(None, &search).is_ok()); +} + +fn body(body: http::RequestBody) -> Value { + let runtime = tokio::runtime::Builder::new_current_thread() + .build() + .unwrap(); + runtime.block_on(async move { + let bytes = futures_util::TryStreamExt::try_fold( + body.into_stream(), + Vec::new(), + |mut bytes, chunk| async move { + bytes.extend_from_slice(&chunk); + Ok(bytes) + }, + ) + .await + .unwrap(); + serde_json::from_slice(&bytes).unwrap() + }) +} diff --git a/plugins/workspace/workspace-web/native/src/settings.rs b/plugins/workspace/workspace-web/native/src/settings.rs index 2fe038258c7..3f911fc0d11 100644 --- a/plugins/workspace/workspace-web/native/src/settings.rs +++ b/plugins/workspace/workspace-web/native/src/settings.rs @@ -17,8 +17,10 @@ * under the License. */ +use crate::search::{SearchEndpoint, presets}; use maka_capabilities::credentials; use maka_plugin_core::storage; +use maka_web_api::contract::Basis; use std::sync::Arc; const SETTINGS: &str = "settings"; @@ -41,14 +43,56 @@ impl Repository { }; Ok((revision, settings)) } - pub async fn snapshot(&self) -> Result { + pub(crate) async fn search_settings(&self) -> Result { let (revision, settings) = self.settings().await?; - let credential = self.credentials.read(KEY.into()).await?; - let key_revision = credential.as_ref().map(|record| record.revision); - let configured = credential - .as_ref() - .and_then(|record| record.secret.as_ref()) - .is_some_and(|secret| !secret.trim().is_empty()); + let endpoint = SearchEndpoint::resolve(&settings.backend) + .map_err(|error| storage::StoreError::Unavailable(error.into()))?; + let key = endpoint.credential_key(&settings.backend); + let credential = match &key { + Some(key) => self.credentials.read(key.clone()).await?, + None => None, + }; + Ok(SearchSettings { + revision, + settings, + endpoint, + key, + credential, + }) + } + + pub(crate) async fn search_is_current( + &self, + basis: &Basis, + key: Option<&str>, + ) -> Result { + let revision = self + .store + .read(SETTINGS.into()) + .await? + .map(|record| record.revision); + if revision != basis.revision { + return Ok(false); + } + match key { + Some(key) => Ok(self + .credentials + .read(key.to_owned()) + .await? + .is_some_and(|record| { + Some(record.revision) == basis.credential_revision + && record + .secret + .is_some_and(|secret| !secret.trim().is_empty()) + })), + None => Ok(true), + } + } + + pub async fn snapshot(&self) -> Result { + let current = self.search_settings().await?; + let key_revision = current.credential_revision(); + let configured = current.secret().is_some(); let check = self .store .read(CHECK.into()) @@ -57,15 +101,20 @@ impl Repository { .map(serde_json::from_value::) .transpose() .map_err(encoding)? - .filter(|check| configured && Some(check.credential_revision) == key_revision); + .filter(|check| { + (current.key.is_none() || configured) + && check.settings_revision == current.revision + && check.credential_revision == key_revision + }); Ok(Snapshot { - revision, - settings, + revision: current.revision, + settings: current.settings, credential: Credential { revision: key_revision, configured, check, }, + presets: presets(), }) } pub async fn save( @@ -83,14 +132,18 @@ impl Repository { .pop() .ok_or_else(|| storage::StoreError::Unavailable("settings receipt is missing".into())) } - pub async fn record_check(&self, check: Check) -> Result<(), storage::StoreError> { + pub async fn record_check( + &self, + check: Check, + key: Option<&str>, + ) -> Result { let previous = self.store.read(CHECK.into()).await?; - if let Some(value) = previous.as_ref().and_then(|record| record.data.value()) { - let previous: Check = serde_json::from_value(value.clone()).map_err(encoding)?; - // A slow check for an old key cannot replace a newer key's status. - if previous.credential_revision > check.credential_revision { - return Ok(()); - } + let basis = Basis { + revision: check.settings_revision, + credential_revision: check.credential_revision, + }; + if !self.search_is_current(&basis, key).await? { + return Ok(false); } match self .store @@ -101,11 +154,39 @@ impl Repository { }]) .await { - Ok(_) | Err(storage::StoreError::Conflict { .. }) => Ok(()), + Ok(_) | Err(storage::StoreError::Conflict { .. }) => Ok(true), Err(error) => Err(error), } } } +pub(crate) struct SearchSettings { + pub revision: Option, + pub settings: Settings, + pub endpoint: SearchEndpoint, + pub key: Option, + credential: Option, +} +impl SearchSettings { + pub fn credential_revision(&self) -> Option { + self.credential.as_ref().map(|value| value.revision) + } + pub fn secret(&self) -> Option<&str> { + self.credential + .as_ref()? + .secret + .as_deref() + .filter(|secret| !secret.trim().is_empty()) + } + pub fn available(&self) -> bool { + self.settings.enabled && (self.key.is_none() || self.secret().is_some()) + } + pub fn matches(&self, basis: &Basis) -> bool { + self.available() + && self.revision == basis.revision + && self.credential_revision() == basis.credential_revision + } +} + fn encoding(error: serde_json::Error) -> storage::StoreError { storage::StoreError::Unavailable(error.to_string()) } diff --git a/products/maka/bundle/src/composition.ts b/products/maka/bundle/src/composition.ts index e679b58f2d7..aaf71335c58 100644 --- a/products/maka/bundle/src/composition.ts +++ b/products/maka/bundle/src/composition.ts @@ -177,6 +177,7 @@ const settingsUiImports = [ 'management', 'receipts', 'skills', + 'web', ]; const workspaceUiImports = ['agent', 'terminal']; diff --git a/products/maka/bundle/src/installation.ts b/products/maka/bundle/src/installation.ts index b78f1000f5e..15da5a735a7 100644 --- a/products/maka/bundle/src/installation.ts +++ b/products/maka/bundle/src/installation.ts @@ -67,7 +67,12 @@ export function installation( add('processes', 'writeStdin', 'ProcessInput', 'Send input to a previously started command.'); add('processes', 'stop', 'ProcessStop', 'Stop a previously started command.'); add('web', 'fetch', 'WebFetch', 'Read a web page. Network destinations require permission.'); - add('web', 'search', 'WebSearch', 'Search using the selected model or Tavily.'); + add( + 'web', + 'search', + 'WebSearch', + 'Search using the selected model or a configured search service.', + ); add( 'computer', 'evaluate', diff --git a/products/maka/client/src/journal.rs b/products/maka/client/src/journal.rs index 23246f8b0d4..27389565f92 100644 --- a/products/maka/client/src/journal.rs +++ b/products/maka/client/src/journal.rs @@ -38,7 +38,7 @@ use uuid::Uuid; // Keep admission and pending observations on the same immutable Settings owner. macro_rules! settings_owner_sql { () => { - "draft_owner IS NULL AND json_type(context,'$.draft')='null' AND json_type(context,'$.sessionId')='null' AND json_type(context,'$.correlation')='object' AND json_extract(context,'$.correlation') IN (SELECT value FROM json_each(?)) AND ((json_extract(context,'$.endpoint')='settings' AND json_extract(context,'$.method') IN (SELECT value FROM json_each(?))) OR (json_extract(context,'$.endpoint')='agent' AND json_extract(context,'$.method') IN ('updateGlobalInstructions','selectWorkspace','manageMcpServer','createPreset','updatePreset','deletePreset')) OR (json_extract(context,'$.endpoint')='skills' AND json_extract(context,'$.method') IN ('install','update','delete')) OR (json_extract(context,'$.endpoint')='setup' AND json_extract(context,'$.method')='discoverModels') OR (json_extract(context,'$.endpoint')='management' AND json_extract(context,'$.method') IN ('setEnabled','configure','configureBatch')) OR (json_extract(context,'$.endpoint')='authentication' AND json_extract(context,'$.method')='loginCredential'))" + "draft_owner IS NULL AND json_type(context,'$.draft')='null' AND json_type(context,'$.sessionId')='null' AND json_type(context,'$.correlation')='object' AND json_extract(context,'$.correlation') IN (SELECT value FROM json_each(?)) AND ((json_extract(context,'$.endpoint')='settings' AND json_extract(context,'$.method') IN (SELECT value FROM json_each(?))) OR (json_extract(context,'$.endpoint')='agent' AND json_extract(context,'$.method') IN ('updateGlobalInstructions','selectWorkspace','manageMcpServer','createPreset','updatePreset','deletePreset')) OR (json_extract(context,'$.endpoint')='skills' AND json_extract(context,'$.method') IN ('install','update','delete')) OR (json_extract(context,'$.endpoint')='setup' AND json_extract(context,'$.method')='discoverModels') OR (json_extract(context,'$.endpoint')='management' AND json_extract(context,'$.method') IN ('setEnabled','configure','configureBatch')) OR (json_extract(context,'$.endpoint')='authentication' AND json_extract(context,'$.method')='loginCredential') OR (json_extract(context,'$.endpoint')='web' AND json_extract(context,'$.method') IN ('save','saveKey','deleteKey','checkKey')))" }; } diff --git a/products/maka/client/src/lib.rs b/products/maka/client/src/lib.rs index 98dbc7e2c30..a6bfe38991c 100644 --- a/products/maka/client/src/lib.rs +++ b/products/maka/client/src/lib.rs @@ -77,13 +77,14 @@ const CONTROL_KIND: &str = "agent-control"; const SETTINGS_KIND: &str = "settings"; const TERMINAL_KIND: &str = "terminal"; const TERMINAL_METHODS: [&str; 4] = ["start", "stop", "control", "release"]; -const SETTINGS_ENDPOINTS: [&str; 6] = [ +const SETTINGS_ENDPOINTS: [&str; 7] = [ "settings", "agent", "skills", "setup", "management", "authentication", + "web", ]; #[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)] @@ -132,6 +133,7 @@ fn settings_route(endpoint: &str, method: &str) -> bool { || (endpoint == "management" && matches!(method, "setEnabled" | "configure" | "configureBatch")) || (endpoint == "authentication" && method == "loginCredential") + || (endpoint == "web" && matches!(method, "save" | "saveKey" | "deleteKey" | "checkKey")) } fn settings_owner(operation: &Operation, owner: &ServiceOwner) -> bool { operation.draft.is_none() @@ -675,7 +677,9 @@ impl Client { if !settings_route(endpoint, method) { return Err("unsupported settings mutation method".into()); } - if endpoint == "settings" && matches!(method, "saveCredential" | "saveUsageCredential") { + if (endpoint == "settings" && matches!(method, "saveCredential" | "saveUsageCredential")) + || (endpoint == "web" && method == "saveKey") + { if resources.len() != 1 || !resources.get("secret").is_some_and(|secret| { secret.resource_type() == text_resource_type() diff --git a/products/maka/workbench/app/WebSearchSettings.tsx b/products/maka/workbench/app/WebSearchSettings.tsx new file mode 100644 index 00000000000..dcfcf59afa9 --- /dev/null +++ b/products/maka/workbench/app/WebSearchSettings.tsx @@ -0,0 +1,364 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, + * software distributed under the License is distributed on an + * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + * KIND, either express or implied. See the License for the + * specific language governing permissions and limitations + * under the License. + */ + +import { inputAction, type JSX } from 'nsh'; +import type { + WebAuthLocation, + WebBackend, + WebParameter, + WebParameterLocation, + WebSearchEndpoint, + WebSearchMethod, +} from '../../../../packages/plugin-sdk/src/generated/runtime'; +import { LoadingIndicator } from './Loading'; +import { tr } from './locale'; +import { + SettingsBody, + SettingsButton, + SettingsDiscard, + SettingsInput, + SettingsProblem, + SettingsRow, + SettingsSection, + SettingsSelect, + SettingsSwitch, + SettingsTextArea, +} from './SettingsPage'; +import type { WebSearchSettingsOwner } from './webSearchSettingsState'; + +const backendChoices = [ + { value: 'tavily', title: 'Tavily' }, + { value: 'brave', title: 'Brave Search' }, + { value: 'exa', title: 'Exa' }, + { value: 'serper', title: 'Serper' }, +] as const; + +export function WebSearchSettings({ owner }: { owner: WebSearchSettingsOwner }) { + return ( + } + > + + + } + > + + + + } + > + + + + ); +} + +function WebSearchForm({ owner }: { owner: WebSearchSettingsOwner }) { + const value = () => owner.draft()!; + const saved = () => owner.snapshot()!; + const backend = () => value().backend; + const endpoint = () => { + const selected = backend(); + return selected.kind === 'custom' + ? selected.endpoint + : saved().presets.find((preset) => preset.id === selected.kind)!.endpoint; + }; + const editEndpoint = ( + field: K, + result: WebSearchEndpoint[K], + ) => { + const current = backend(); + if (current.kind === 'custom') + owner.edit('backend', { kind: 'custom', endpoint: { ...current.endpoint, [field]: result } }); + }; + const keyDisabled = () => owner.disabled() || owner.dirty(); + const checks = () => { + switch (saved().credential.check?.outcome) { + case 'valid': + return tr('Search connection verified.'); + case 'invalid_credentials': + return tr('The search provider rejected the API key.'); + case 'rate_limited': + return tr('The search provider rate limited the request.'); + case 'network_error': + case 'timeout': + return tr('The search connection test failed.'); + default: + return undefined; + } + }; + const disabled = () => owner.disabled(); + return ( + + } + > + + owner.edit('enabled', !value().enabled)} + /> + owner.edit('source', source as WebSettingsSource)} + /> + owner.selectBackend(kind as WebBackend['kind'])} + /> + + + + + + + + + + { + if (!keyDisabled()) owner.secret.set(secret); + }} + /> + + + + + + + + + ); +} + +type WebSettingsSource = NonNullable>['source']; + +function EndpointForm(props: { + endpoint(): WebSearchEndpoint; + edit(field: K, value: WebSearchEndpoint[K]): void; + owner: WebSearchSettingsOwner; +}) { + const endpoint = props.endpoint; + const disabled = () => props.owner.disabled(); + const locations = () => [ + { value: 'query', title: tr('URL query') }, + ...(endpoint().method === 'post' ? [{ value: 'body', title: tr('JSON body') }] : []), + ]; + const parameter = (field: 'query' | 'limit', label: string): JSX.Element => { + const value = () => endpoint()[field] ?? { name: '', location: 'query' as const }; + const edit = (parameter: WebParameter) => + props.edit(field, field === 'limit' && !parameter.name ? null : parameter); + return ( + <> + edit({ ...value(), name })} + /> + + edit({ ...value(), location: location as WebParameterLocation })} + /> + + + ); + }; + const editMethod = (method: WebSearchMethod) => { + const current = endpoint(); + if (method === 'get') { + const query = { ...current.query, location: 'query' as const }; + const limit = current.limit ? { ...current.limit, location: 'query' as const } : null; + const auth = + current.auth?.location === 'body' + ? { ...current.auth, location: 'header' as const } + : current.auth; + props.owner.edit('backend', { + kind: 'custom', + endpoint: { ...current, method, query, limit, auth, body: {} }, + }); + props.owner.parameters.set({ ...props.owner.parameters(), body: '{}' }); + } else { + props.edit('method', method); + } + }; + const resultField = (field: keyof WebSearchEndpoint['results'], label: string) => ( + + props.edit('results', { + ...endpoint().results, + [field]: field === 'title' || field === 'snippet' ? path || null : path, + }) + } + /> + ); + return ( + <> + + props.edit('url', url)} + /> + editMethod(method as WebSearchMethod)} + /> + {parameter('query', tr('Search query parameter'))} + {parameter('limit', tr('Result limit parameter (optional)'))} + props.owner.parameters.set({ ...props.owner.parameters(), url })} + disabled={disabled()} + lines={3} + monospace + /> + + props.owner.parameters.set({ ...props.owner.parameters(), body })} + disabled={disabled()} + lines={3} + monospace + /> + + + + + props.edit( + 'auth', + location === 'none' + ? null + : { + name: endpoint().auth?.name ?? '', + prefix: endpoint().auth?.prefix ?? '', + location: location as WebAuthLocation, + }, + ) + } + /> + + props.edit('auth', { ...endpoint().auth!, name })} + /> + props.edit('auth', { ...endpoint().auth!, prefix })} + /> + + + + {resultField('list', tr('Results array path'))} + {resultField('url', tr('Result URL path'))} + {resultField('title', tr('Result title path (optional)'))} + {resultField('snippet', tr('Result snippet path (optional)'))} + + + ); +} diff --git a/products/maka/workbench/app/host.ts b/products/maka/workbench/app/host.ts index c6c59fe9914..fb29f1929a5 100644 --- a/products/maka/workbench/app/host.ts +++ b/products/maka/workbench/app/host.ts @@ -44,6 +44,7 @@ type Services = { authentication: ServiceMethods['settingsAuthentication']; setup: ServiceMethods['settingsSetup']; management: ServiceMethods['deploymentManager']; + web: ServiceMethods['workspaceWeb']; terminal: ServiceMethods['terminal']; }; type Endpoint = keyof Services; diff --git a/products/maka/workbench/app/locale-settings.ts b/products/maka/workbench/app/locale-settings.ts index 200d2071667..5fcb62217ed 100644 --- a/products/maka/workbench/app/locale-settings.ts +++ b/products/maka/workbench/app/locale-settings.ts @@ -56,6 +56,130 @@ import { } from '../../../../plugins/shared/tui-messages.js'; export const settingsMessages = { + 'Save key': ['Save key', '保存密钥', '儲存金鑰'], + 'Web search': ['Web search', '网页搜索', '網頁搜尋'], + 'Loading web search settings…': [ + 'Loading web search settings…', + '正在加载网页搜索设置…', + '正在載入網頁搜尋設定…', + ], + 'Web search is unavailable on this Host.': [ + 'Web search is unavailable on this Host.', + '此 Host 未提供网页搜索。', + '此 Host 未提供網頁搜尋。', + ], + 'Save web search settings': ['Save web search settings', '保存网页搜索设置', '儲存網頁搜尋設定'], + 'Web tools': ['Web tools', '网页工具', '網頁工具'], + 'Preferred search source': ['Preferred search source', '首选搜索来源', '首選搜尋來源'], + 'Maka uses the other source when the preferred one is unavailable.': [ + 'Maka uses the other source when the preferred one is unavailable.', + '首选来源不可用时，Maka 会使用另一个来源。', + '首選來源無法使用時，Maka 會使用另一個來源。', + ], + 'Model provider first': ['Model provider first', '优先使用模型原生搜索', '優先使用模型原生搜尋'], + 'Custom search first': ['Custom search first', '优先使用自定义搜索', '優先使用自訂搜尋'], + 'Custom search provider': ['Custom search provider', '自定义搜索提供商', '自訂搜尋供應商'], + 'Custom endpoint': ['Custom endpoint', '自定义端点', '自訂端點'], + 'Search endpoint': ['Search endpoint', '搜索端点', '搜尋端點'], + 'Search connection': ['Search connection', '搜索连接', '搜尋連線'], + 'Search connection verified.': [ + 'Search connection verified.', + '搜索连接验证通过。', + '搜尋連線驗證通過。', + ], + 'The search provider rejected the API key.': [ + 'The search provider rejected the API key.', + '搜索提供商拒绝了 API 密钥。', + '搜尋供應商拒絕了 API 金鑰。', + ], + 'The search provider rate limited the request.': [ + 'The search provider rate limited the request.', + '搜索提供商限制了请求频率。', + '搜尋供應商限制了請求頻率。', + ], + 'The search connection test failed.': [ + 'The search connection test failed.', + '搜索连接测试失败。', + '搜尋連線測試失敗。', + ], + 'Stored API key': ['Stored API key', '已存储的 API 密钥', '已儲存的 API 金鑰'], + 'Remove API key': ['Remove API key', '移除 API 密钥', '移除 API 金鑰'], + 'Test search connection': ['Test search connection', '测试搜索连接', '測試搜尋連線'], + 'URL query': ['URL query', 'URL 查询参数', 'URL 查詢參數'], + 'JSON body': ['JSON body', 'JSON 请求体', 'JSON 請求本文'], + 'Search query location': ['Search query location', '搜索词存放位置', '搜尋詞存放位置'], + 'Result limit location': ['Result limit location', '结果数量参数位置', '結果數量參數位置'], + 'Search request': ['Search request', '搜索请求', '搜尋請求'], + 'HTTP method': ['HTTP method', 'HTTP 方法', 'HTTP 方法'], + 'Search query parameter': ['Search query parameter', '搜索词参数', '搜尋詞參數'], + 'Result limit parameter (optional)': [ + 'Result limit parameter (optional)', + '结果数量参数（选填）', + '結果數量參數（選填）', + ], + 'Extra URL parameters (JSON)': [ + 'Extra URL parameters (JSON)', + '额外 URL 参数（JSON）', + '額外 URL 參數（JSON）', + ], + 'Extra JSON body fields': [ + 'Extra JSON body fields', + '额外 JSON 请求体字段', + '額外 JSON 請求本文欄位', + ], + 'Search authentication': ['Search authentication', '搜索认证', '搜尋驗證'], + 'Authentication location': ['Authentication location', '认证参数位置', '驗證參數位置'], + 'No authentication': ['No authentication', '无需认证', '無需驗證'], + 'HTTP header': ['HTTP header', 'HTTP 请求头', 'HTTP 請求標頭'], + 'Authentication field name': ['Authentication field name', '认证字段名', '驗證欄位名稱'], + 'Authentication value prefix (optional)': [ + 'Authentication value prefix (optional)', + '认证值前缀（选填）', + '驗證值前綴（選填）', + ], + 'Search result mapping': ['Search result mapping', '搜索结果字段映射', '搜尋結果欄位對應'], + 'Use JSON pointers such as /results and /url. Leave the list path blank for a top-level array.': [ + 'Use JSON pointers such as /results and /url. Leave the list path blank for a top-level array.', + '使用 /results、/url 等 JSON Pointer。响应根节点是数组时，列表路径留空。', + '使用 /results、/url 等 JSON Pointer。回應根節點是陣列時，清單路徑留空。', + ], + 'Results array path': ['Results array path', '结果数组路径', '結果陣列路徑'], + 'Result URL path': ['Result URL path', '结果 URL 路径', '結果 URL 路徑'], + 'Result title path (optional)': [ + 'Result title path (optional)', + '结果标题路径（选填）', + '結果標題路徑（選填）', + ], + 'Result snippet path (optional)': [ + 'Result snippet path (optional)', + '结果摘要路径（选填）', + '結果摘要路徑（選填）', + ], + 'Web search settings changed. Reload and try again.': [ + 'Web search settings changed. Reload and try again.', + '网页搜索设置已更改，请重新加载后再试。', + '網頁搜尋設定已變更，請重新載入後再試。', + ], + 'Enter a valid search API key.': [ + 'Enter a valid search API key.', + '请输入有效的搜索 API 密钥。', + '請輸入有效的搜尋 API 金鑰。', + ], + 'Web search connection test is unavailable.': [ + 'Web search connection test is unavailable.', + '无法测试网页搜索连接。', + '無法測試網頁搜尋連線。', + ], + 'Enter a valid JSON object for the search parameters.': [ + 'Enter a valid JSON object for the search parameters.', + '搜索参数必须是有效的 JSON 对象。', + '搜尋參數必須是有效的 JSON 物件。', + ], + 'URL parameter values must be strings.': [ + 'URL parameter values must be strings.', + 'URL 参数值必须是字符串。', + 'URL 參數值必須是字串。', + ], 'Checking whether the interface changed…': [ 'Checking whether the interface changed…', '正在确认界面是否已切换…', diff --git a/products/maka/workbench/app/settingsOperations.ts b/products/maka/workbench/app/settingsOperations.ts index 5b3df20b2ba..8aa55c27bbc 100644 --- a/products/maka/workbench/app/settingsOperations.ts +++ b/products/maka/workbench/app/settingsOperations.ts @@ -100,13 +100,13 @@ export function createSettingsOperations(host: Host) { input: Input, ): Promise>; function mutate( - endpoint: 'settings' | 'setup' | 'authentication' | 'management', + endpoint: 'settings' | 'setup' | 'authentication' | 'management' | 'web', method: string, input: unknown, secret?: string | null, ): Promise; async function mutate( - endpoint: 'settings' | 'setup' | 'authentication' | 'management' | 'agent' | 'skills', + endpoint: 'settings' | 'setup' | 'authentication' | 'management' | 'web' | 'agent' | 'skills', method: string, input: unknown, secret: string | null = null, diff --git a/products/maka/workbench/app/webSearchSettingsState.ts b/products/maka/workbench/app/webSearchSettingsState.ts new file mode 100644 index 00000000000..6214f0a4400 --- /dev/null +++ b/products/maka/workbench/app/webSearchSettingsState.ts @@ -0,0 +1,228 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, + * software distributed under the License is distributed on an + * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + * KIND, either express or implied. See the License for the + * specific language governing permissions and limitations + * under the License. + */ + +import { cleanup, signal } from 'nsh'; +import type { + WebBackend, + WebSettings, + WebSnapshot, + WebUpdate, +} from '../../../../packages/plugin-sdk/src/generated/runtime'; +import { sameValue } from '../../../../plugins/shared/value'; +import type { Host } from './host'; +import { tr } from './locale'; +import { UiError } from './text'; +import { createSettingsDiscard } from './settingsDiscard'; +import type { SettingsOperations } from './settingsOperations'; + +type SettingsDraft = WebSettings & { backend: WebBackend }; + +export function createWebSearchSettings( + host: Host, + operations: SettingsOperations, + active: () => boolean, +) { + const snapshot = signal(null); + const draft = signal(null); + const parameters = signal({ url: '', body: '' }); + const secret = signal(''); + const loading = signal(false); + const supported = signal(true); + let generation = 0; + cleanup(() => { + generation += 1; + secret.set(''); + }); + const setDraft = (settings: WebSettings | null) => { + const backend: WebBackend = settings?.backend ?? { kind: 'tavily' }; + draft.set(settings ? { ...settings, backend } : null); + const endpoint = backend.kind === 'custom' ? backend.endpoint : null; + parameters.set({ + url: JSON.stringify(endpoint?.urlParameters ?? {}, null, 2), + body: JSON.stringify(endpoint?.body ?? {}, null, 2), + }); + }; + const accept = (value: WebSnapshot) => { + snapshot.set(value); + setDraft(value.settings); + }; + const load = async () => { + if (!active()) return; + const request = ++generation; + loading.set(true); + try { + const available = await host.hasService('web'); + if (generation !== request) return; + supported.set(available); + if (!available) return; + const value = await host.query('web', 'snapshot', {}); + if (generation === request) accept(value); + } catch (reason) { + if (generation === request) operations.report(reason); + } finally { + if (generation === request) loading.set(false); + } + }; + const dirty = () => { + const saved = snapshot()?.settings; + const value = draft(); + if (!saved || !value) return false; + const backend = value.backend; + return ( + !sameValue({ ...saved, backend: saved.backend ?? { kind: 'tavily' } }, value) || + (backend.kind === 'custom' && + (parameters().url !== JSON.stringify(backend.endpoint.urlParameters, null, 2) || + parameters().body !== JSON.stringify(backend.endpoint.body, null, 2))) + ); + }; + const disabled = () => + loading() || operations.busy() || !operations.pendingKnown() || operations.pending().length > 0; + const discarding = createSettingsDiscard( + () => dirty() || !!secret(), + () => { + setDraft(snapshot()?.settings ?? null); + secret.set(''); + }, + ); + const req = async ( + method: 'save' | 'saveKey' | 'deleteKey' | 'checkKey', + input: unknown, + key?: string, + ) => { + const result: WebUpdate = await operations.mutate('web', method, input, key); + switch (result.kind) { + case 'updated': + accept(result.snapshot); + return; + case 'changed': + throw new UiError('Web search settings changed. Reload and try again.'); + case 'invalid_key': + throw new UiError('Enter a valid search API key.'); + case 'invalid_settings': + throw new Error(result.message); + case 'check_unavailable': + throw new UiError('Web search connection test is unavailable.'); + } + }; + const edit = (name: K, value: SettingsDraft[K]) => { + const current = draft(); + if (current && !disabled()) draft.set({ ...current, [name]: value }); + }; + const selectBackend = (kind: WebBackend['kind']) => { + const current = draft(); + if (!current || disabled() || current.backend.kind === kind) return; + const starter = + snapshot()?.presets.find((preset) => preset.id === current.backend.kind) ?? + snapshot()?.presets[0]; + if (kind === 'custom' && !starter) return; + setDraft({ + ...current, + backend: kind === 'custom' ? { kind, endpoint: starter!.endpoint } : { kind }, + }); + secret.set(''); + }; + const readObject = (text: string): Record => { + let parsed: unknown; + try { + parsed = JSON.parse(text); + } catch { + throw new UiError('Enter a valid JSON object for the search parameters.'); + } + if (!parsed || typeof parsed !== 'object' || Array.isArray(parsed)) + throw new UiError('Enter a valid JSON object for the search parameters.'); + return parsed as Record; + }; + const save = () => + operations.run(async () => { + const current = snapshot(); + const value = draft(); + if (!current || !value || !dirty()) return; + const backend = value.backend; + let settings = value; + if (backend.kind === 'custom') { + const urlParameters = readObject(parameters().url); + if (Object.values(urlParameters).some((entry) => typeof entry !== 'string')) + throw new UiError('URL parameter values must be strings.'); + settings = { + ...value, + backend: { + ...backend, + endpoint: { + ...backend.endpoint, + url: backend.endpoint.url.trim(), + urlParameters: urlParameters as Record, + body: readObject(parameters().body), + }, + }, + }; + } + await req('save', { revision: current.revision, settings }); + }); + const credential = (method: 'saveKey' | 'deleteKey' | 'checkKey') => + operations.run(async () => { + const current = snapshot(); + if (!current || dirty()) return; + await req( + method, + { settingsRevision: current.revision, revision: current.credential.revision }, + method === 'saveKey' ? secret() : undefined, + ); + if (method !== 'checkKey') secret.set(''); + }); + return { + snapshot, + draft, + parameters, + secret, + loading, + supported, + disabled, + dirty, + discarding, + edit, + selectBackend, + save, + credential, + load, + activate: () => { + void load(); + }, + deactivate: () => { + generation += 1; + loading.set(false); + snapshot.set(null); + setDraft(null); + secret.set(''); + discarding.clear(); + }, + refresh: () => { + if (!dirty() && !secret() && !operations.busy()) void load(); + }, + title: () => tr('Web search'), + navigation: () => String(snapshot()?.revision ?? ''), + back() { + if (!discarding.asking()) return true; + discarding.keep(); + return false; + }, + leave: discarding.leave, + }; +} + +export type WebSearchSettingsOwner = ReturnType; diff --git a/tools/schema/src/lib.rs b/tools/schema/src/lib.rs index 772f40b11dd..f9afb50a3a7 100644 --- a/tools/schema/src/lib.rs +++ b/tools/schema/src/lib.rs @@ -96,6 +96,7 @@ pub fn catalog() -> Value { root::(&mut g), root::(&mut g), root::(&mut g), + root::(&mut g), root::(&mut g), root::(&mut g), root::(&mut g),