From 7cccad0cc2ca1ab765492e85347bd271d436fe1a Mon Sep 17 00:00:00 2001 From: pierreraby Date: Wed, 11 Nov 2026 22:17:20 +0100 Subject: [PATCH] chore(models): price the November catalog additions The Provider API advertised 97 models on 2026-11-11, up from 96 on 2026-11-09. Three additions had no reviewed price, so every request reported a zero estimate and an unknown-price warning, and the daily catalog workflow failed its pricing gate twice (runs 42838424841 and 43037482750), reopening the maintenance incident #207. Add reviewed rates from the official pricing page for claude-fable-5-2 (8.00/40.00/0.20/10.00), google/gemini-4-carbon (2.00/10.00/0.10, no cache-write charge) and meta/muse-ember (0.10/0.50/0.004, no cache-write charge). Drop the zero prices for stealth/crouton-alpha and reflection/beam:free, which the API no longer advertises, and refresh both snapshots to 2026-11-11. Static capability metadata stays at command-code@1.88.5, so the three new models keep text-only input without reasoning or effort flags. --- CHANGELOG.md | 2 ++ src/pricing.ts | 8 ++--- tests/fixtures/commandcode-model-ids.json | 7 +++-- tests/fixtures/commandcode-pricing.json | 7 +++-- tests/test-pricing.ts | 38 +++++++++++++---------- 5 files changed, 36 insertions(+), 26 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index d820435..e1901ec 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -2,6 +2,8 @@ ## Unreleased +- 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. + ## 0.8.1 - 2026-11-09 - Refresh the capability snapshot to `command-code@1.88.5`: advertise image input, reasoning and selectable efforts (`off`/`low`/`high`/`max`) for `deepseek/deepseek-v4.1-flash-ultrafast`, and drop the retired `poolside/laguna-s-2.1-free` reasoning flag, effort defaults and 32,768-token output limit. Add reviewed display pricing for the ultrafast model at $2.40 input / $9.60 output / $0.048 cache read per million tokens, with no cache-write charge and a single published rate, and remove the retired free `poolside/laguna-s-2.1-free` price entry. Refresh the 96-model API and pricing snapshots to 2026-11-09. Endpoint routing defaults are unchanged. ([#209](https://github.com/patlux/pi-commandcode-provider/pull/209)) diff --git a/src/pricing.ts b/src/pricing.ts index 11d1fbe..4412f63 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 = "2026-11-09" +export const PRICING_LAST_VERIFIED = "2026-11-11" export const ZERO_MODEL_COST: CommandCodeModelCost = { input: 0, @@ -40,10 +40,7 @@ export const ZERO_MODEL_COST: CommandCodeModelCost = { export const MODEL_COSTS: Readonly> = { // Free models // Free while the stealth preview lasts; no fixed expiry is published. - "stealth/crouton-alpha": { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }, "stealth/glyph-cluster:free": { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }, - // Free while capacity lasts; no fixed expiry is published. - "reflection/beam: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 }, @@ -209,6 +206,7 @@ export const MODEL_COSTS: Readonly> = { "meta/muse-spark-1.3": { input: 1.25, output: 4.25, cacheRead: 0.15, cacheWrite: 0 }, "meta/muse-spark-open": { input: 1.25, output: 4.25, cacheRead: 0.15, cacheWrite: 0 }, "meta/muse-wonder-1.0": { input: 4, output: 20, cacheRead: 0.2, cacheWrite: 0 }, + "meta/muse-ember": { input: 0.1, output: 0.5, cacheRead: 0.004, cacheWrite: 0 }, "meta/muse-spark-1.2-contributor": { input: 0.1, output: 0.2, @@ -226,6 +224,7 @@ export const MODEL_COSTS: Readonly> = { "claude-sonnet-5-5": { input: 2, output: 10, cacheRead: 0.1, cacheWrite: 2.5 }, "claude-sonnet-5": { input: 2, output: 10, cacheRead: 0.2, cacheWrite: 2.5 }, "claude-sonnet-4-6": { input: 3, output: 15, cacheRead: 0.3, cacheWrite: 3.75 }, + "claude-fable-5-2": { input: 8, output: 40, cacheRead: 0.2, cacheWrite: 10 }, "claude-fable-5-1": { input: 10, output: 50, cacheRead: 0.25, cacheWrite: 12.5 }, "claude-fable-5": { input: 10, output: 50, cacheRead: 1, cacheWrite: 12.5 }, "claude-opus-5-5": { input: 4, output: 20, cacheRead: 0.2, cacheWrite: 5 }, @@ -327,6 +326,7 @@ export const MODEL_COSTS: Readonly> = { cacheRead: 0.15, cacheWrite: 0.08334, }, + "google/gemini-4-carbon": { input: 2, output: 10, cacheRead: 0.1, cacheWrite: 0 }, "google/gemini-4-argon": { input: 2, output: 10, cacheRead: 0.1, cacheWrite: 0 }, "google/gemini-3.8-flash": { input: 1.5, diff --git a/tests/fixtures/commandcode-model-ids.json b/tests/fixtures/commandcode-model-ids.json index 14a048d..957b879 100644 --- a/tests/fixtures/commandcode-model-ids.json +++ b/tests/fixtures/commandcode-model-ids.json @@ -1,10 +1,11 @@ { - "fetchedAt": "2026-11-09T04:35:01.182Z", + "fetchedAt": "2026-11-11T21:10:50.031Z", "source": "https://api.commandcode.ai/provider/v1/models", "modelIds": [ "claude-sonnet-5-5", "claude-sonnet-5", "claude-sonnet-4-6", + "claude-fable-5-2", "claude-fable-5-1", "claude-fable-5", "claude-opus-5-5", @@ -70,6 +71,7 @@ "stepfun/Step-3.5-Flash", "tencent/hy3-paid", "tencent/hy4-preview", + "google/gemini-4-carbon", "google/gemini-4-argon", "google/gemini-3.8-flash", "google/gemini-3.7-flash", @@ -83,8 +85,6 @@ "thinkingmachines/inkling", "thinkingmachines/inkling-small", "stealth/glyph-cluster:free", - "stealth/crouton-alpha", - "reflection/beam:free", "inclusionai/ling-3.1-flash", "inclusionai/ling-3.1-flash-1019", "meta/muse-spark-1.1", @@ -94,6 +94,7 @@ "meta/muse-spark-1.3-contributor", "meta/muse-spark-open", "meta/muse-wonder-1.0", + "meta/muse-ember", "xai/grok-4.5", "xai/grok-4.6", "xai/grok-4.7", diff --git a/tests/fixtures/commandcode-pricing.json b/tests/fixtures/commandcode-pricing.json index 9573738..bea4a59 100644 --- a/tests/fixtures/commandcode-pricing.json +++ b/tests/fixtures/commandcode-pricing.json @@ -1,5 +1,5 @@ { - "verifiedAt": "2026-11-09", + "verifiedAt": "2026-11-11", "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": { @@ -22,9 +22,7 @@ "xai/grok-4.7": [[200000, 4, 12, 1, 0]] }, "costs": { - "stealth/crouton-alpha": [0, 0, 0, 0], "stealth/glyph-cluster:free": [0, 0, 0, 0], - "reflection/beam: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], @@ -83,11 +81,13 @@ "meta/muse-spark-1.3": [1.25, 4.25, 0.15, 0], "meta/muse-spark-open": [1.25, 4.25, 0.15, 0], "meta/muse-wonder-1.0": [4, 20, 0.2, 0], + "meta/muse-ember": [0.1, 0.5, 0.004, 0], "meta/muse-spark-1.2-contributor": [0.1, 0.2, 0.002, 0], "meta/muse-spark-1.3-contributor": [0.1, 0.2, 0.002, 0], "claude-sonnet-5-5": [2, 10, 0.1, 2.5], "claude-sonnet-5": [2, 10, 0.2, 2.5], "claude-sonnet-4-6": [3, 15, 0.3, 3.75], + "claude-fable-5-2": [8, 40, 0.2, 10], "claude-fable-5-1": [10, 50, 0.25, 12.5], "claude-fable-5": [10, 50, 1, 12.5], "claude-opus-5-5": [4, 20, 0.2, 5], @@ -109,6 +109,7 @@ "gpt-5.3-codex": [2, 8, 0.5, 0], "gpt-5.4-mini": [0.75, 4.5, 0.075, 0], "google/gemini-3.7-flash": [1.5, 7.5, 0.15, 0.08334], + "google/gemini-4-carbon": [2, 10, 0.1, 0], "google/gemini-4-argon": [2, 10, 0.1, 0], "google/gemini-3.8-flash": [1.5, 7.5, 0.15, 0], "google/gemini-3.6-flash": [1.5, 7.5, 0.15, 0], diff --git a/tests/test-pricing.ts b/tests/test-pricing.ts index bf59bf3..2aea2ee 100644 --- a/tests/test-pricing.ts +++ b/tests/test-pricing.ts @@ -27,11 +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/crouton-alpha", - "stealth/glyph-cluster:free", - "reflection/beam:free", -]) +const freeModels = new Set(["stealth/glyph-cluster:free"]) function assertCost( modelId: string, @@ -114,16 +110,10 @@ describe("MODEL_COSTS pricing overlay", () => { assert.equal(MODEL_COSTS["ornith/ornith-1.5-122b:free"], undefined) }) - it("prices Crouton Alpha as free during its undated stealth preview", () => { - assertCost("stealth/crouton-alpha", { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }) - assert.ok( - !TEMPORARY_PRICING.some((pricing) => pricing.models.includes("stealth/crouton-alpha")), - "the source publishes no fixed expiry for this preview", - ) - }) - - it("matches reviewed late-October Beam promotion rates", () => { - assertCost("reflection/beam:free", { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }) + it("retires stealth previews that left the API", () => { + // Crouton Alpha and Beam's free pool stopped advertising before 2026-11-11. + assert.equal(MODEL_COSTS["stealth/crouton-alpha"], undefined) + assert.equal(MODEL_COSTS["reflection/beam:free"], undefined) }) it("prices Ling 3.1 Flash 1019 after its free preview ends", () => { @@ -264,6 +254,22 @@ describe("MODEL_COSTS pricing overlay", () => { }) }) + it("uses reviewed rates for the November catalog additions", () => { + assertCost("claude-fable-5-2", { input: 8, output: 40, cacheRead: 0.2, cacheWrite: 10 }) + assertCost("google/gemini-4-carbon", { + input: 2, + output: 10, + cacheRead: 0.1, + cacheWrite: 0, + }) + assertCost("meta/muse-ember", { + input: 0.1, + output: 0.5, + cacheRead: 0.004, + cacheWrite: 0, + }) + }) + 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, [ @@ -442,7 +448,7 @@ 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, "2026-11-09") + assert.equal(PRICING_LAST_VERIFIED, "2026-11-11") }) it("fails once temporary pricing needs review", () => {