diff --git a/CHANGELOG.md b/CHANGELOG.md index 5a347df..e35c18a 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -2,6 +2,8 @@ ## Unreleased +- Add the live Provider API addition `thinkingmachines/inkling-2-small:free` to the reviewed pricing snapshot at zero cost, free while the free tier lasts with no fixed expiry published, and refresh the 98-model API and pricing snapshots to 2026-11-13. The model is already usable through the live `/provider/v1/models` response with a zero estimate and an unknown-price warning; static capability metadata stays at `command-code@1.88.5`, so it remains text-only without reasoning or effort flags until upstream ships it. + ## 0.8.2 - 2026-11-11 - Price the November Provider API additions per million tokens: `claude-fable-5-2` at $8.00 input / $40.00 output / $0.20 cache read / $10.00 cache write, `google/gemini-4-carbon` at $2.00 / $10.00 / $0.10 with no cache-write charge, and `meta/muse-ember` at $0.10 / $0.50 / $0.004 with no cache-write charge. Remove the retired `stealth/crouton-alpha` and `reflection/beam:free` zero prices, and refresh the 97-model API and pricing snapshots to 2026-11-11. The new models were already usable through the live `/provider/v1/models` response with a zero estimate and an unknown-price warning; static capability metadata stays at `command-code@1.88.5`, so they remain text-only without reasoning or effort flags until upstream ships them. ([#211](https://github.com/patlux/pi-commandcode-provider/pull/211)) diff --git a/src/pricing.ts b/src/pricing.ts index 4412f63..2cd28a8 100644 --- a/src/pricing.ts +++ b/src/pricing.ts @@ -20,7 +20,7 @@ export interface TemporaryPricing { } export const PRICING_SOURCE_URL = "https://commandcode.ai/docs/resources/pricing-limits" -export const PRICING_LAST_VERIFIED = "2026-11-11" +export const PRICING_LAST_VERIFIED = "2026-11-13" export const ZERO_MODEL_COST: CommandCodeModelCost = { input: 0, @@ -41,6 +41,13 @@ export const MODEL_COSTS: Readonly> = { // Free models // Free while the stealth preview lasts; no fixed expiry is published. "stealth/glyph-cluster:free": { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }, + // Free while the free tier lasts; no fixed expiry is published. + "thinkingmachines/inkling-2-small:free": { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, // Open and open-weight models "inclusionai/ling-3.1-flash-1019": { input: 0.3, output: 0.9, cacheRead: 0.06, cacheWrite: 0 }, diff --git a/tests/fixtures/commandcode-model-ids.json b/tests/fixtures/commandcode-model-ids.json index 957b879..2c686ee 100644 --- a/tests/fixtures/commandcode-model-ids.json +++ b/tests/fixtures/commandcode-model-ids.json @@ -1,5 +1,5 @@ { - "fetchedAt": "2026-11-11T21:10:50.031Z", + "fetchedAt": "2026-11-13T07:12:48.985Z", "source": "https://api.commandcode.ai/provider/v1/models", "modelIds": [ "claude-sonnet-5-5", @@ -84,6 +84,7 @@ "nvidia/nemotron-3.5-super-vl", "thinkingmachines/inkling", "thinkingmachines/inkling-small", + "thinkingmachines/inkling-2-small:free", "stealth/glyph-cluster:free", "inclusionai/ling-3.1-flash", "inclusionai/ling-3.1-flash-1019", diff --git a/tests/fixtures/commandcode-pricing.json b/tests/fixtures/commandcode-pricing.json index bea4a59..0287199 100644 --- a/tests/fixtures/commandcode-pricing.json +++ b/tests/fixtures/commandcode-pricing.json @@ -1,5 +1,5 @@ { - "verifiedAt": "2026-11-11", + "verifiedAt": "2026-11-13", "source": "https://commandcode.ai/docs/resources/pricing-limits", "tierPolicy": "Use request-wide input tiers; the highest threshold exceeded by input plus cache tokens applies to the full request.", "tiers": { @@ -23,6 +23,7 @@ }, "costs": { "stealth/glyph-cluster:free": [0, 0, 0, 0], + "thinkingmachines/inkling-2-small:free": [0, 0, 0, 0], "inclusionai/ling-3.1-flash-1019": [0.3, 0.9, 0.06, 0], "ornith/ornith-1.5-122b": [0.16, 0.64, 0.02, 0], "inclusionai/ling-3.1-flash": [0.3, 0.9, 0.06, 0], diff --git a/tests/test-pricing.ts b/tests/test-pricing.ts index 2aea2ee..6270bd1 100644 --- a/tests/test-pricing.ts +++ b/tests/test-pricing.ts @@ -27,7 +27,7 @@ const fixtureUrl = new URL("./fixtures/commandcode-model-ids.json", import.meta. const fixture = JSON.parse(await readFile(fixtureUrl, "utf-8")) as ModelCatalogSnapshot const pricingFixtureUrl = new URL("./fixtures/commandcode-pricing.json", import.meta.url) const pricingFixture = JSON.parse(await readFile(pricingFixtureUrl, "utf-8")) as PricingSnapshot -const freeModels = new Set(["stealth/glyph-cluster:free"]) +const freeModels = new Set(["stealth/glyph-cluster:free", "thinkingmachines/inkling-2-small:free"]) function assertCost( modelId: string, @@ -270,6 +270,21 @@ describe("MODEL_COSTS pricing overlay", () => { }) }) + it("prices Inkling 2 Small free as free during its undated free tier", () => { + assertCost("thinkingmachines/inkling-2-small:free", { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }) + assert.ok( + !TEMPORARY_PRICING.some((pricing) => + pricing.models.includes("thinkingmachines/inkling-2-small:free"), + ), + "the source publishes no fixed expiry for this free tier", + ) + }) + it("uses the documented base rates for context-dependent models", () => { assertCost("Qwen/Qwen3.6-Plus", { input: 0.5, output: 3, cacheRead: 0.1, cacheWrite: 0 }) assert.deepEqual(MODEL_COSTS["Qwen/Qwen3.6-Plus"]?.tiers, [ @@ -448,7 +463,7 @@ describe("MODEL_COSTS pricing overlay", () => { it("tracks pricing provenance", () => { assert.equal(PRICING_SOURCE_URL, "https://commandcode.ai/docs/resources/pricing-limits") - assert.equal(PRICING_LAST_VERIFIED, "2026-11-11") + assert.equal(PRICING_LAST_VERIFIED, "2026-11-13") }) it("fails once temporary pricing needs review", () => {