diff --git a/CHANGELOG.md b/CHANGELOG.md index c33339f..38b745e 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -4,8 +4,8 @@ - Stop silently dropping `role: "developer"` messages (for example OMP advisor steering notes, reminders, and nudges). `/alpha/generate` only accepts `user`, `assistant`, and `tool` roles, so developer messages are now forwarded as `user` messages with identical content in the same chronological position instead of disappearing from the request. - Add `Qwen/Qwen3.8-Flash` and `z-ai/glm-5.3-flash` with their verified reasoning efforts (`low, medium, xhigh` and `low, high, max`) and display pricing. -- Refresh static model capabilities from `command-code@1.36.0`, adding the free `minimax/minimax-m3-free` model and the `z-ai/glm-5.3-flash` output limit while dropping the retired `stealth/ox-alpha`. -- Refresh display pricing for the current 62-model catalog, adding the free `minimax/minimax-m3-free` and `minimax/minimax-m2.7-free` promotional variants (free through September 5, 2026) and `tencent/hy4-preview`, and removing the retired `stealth/ox-alpha`. +- Refresh static model capabilities from `command-code@1.40.1`, adding `claude-fable-5-1`, `deepseek/deepseek-v4-flash-fast`, and `tencent/hy4-preview` with their reasoning efforts, adding `moonshotai/Kimi-K3` efforts and the `z-ai/glm-5.3-flash` output limit, and dropping the retired `stealth/ox-alpha` and `minimax/minimax-m3-free`. +- Refresh display pricing for the current 62-model catalog, adding `claude-fable-5-1`, `deepseek/deepseek-v4-flash-fast`, and `tencent/hy4-preview`, removing the retired `stealth/ox-alpha`, `minimax/minimax-m3-free`, and `minimax/minimax-m2.7-free`, and ending the expired Claude Sonnet 5 introductory and Gemini 3.7 Flash promotional windows. - Fix `npm run sync:commandcode-catalog` and `npm run check:commandcode-catalog` on Windows by spawning npm through the shell. - Add a `refresh-model-catalog` agent skill with cross-platform helper scripts that snapshot the live model catalog and regenerate the pricing fixture from `MODEL_COSTS`. diff --git a/src/pricing.ts b/src/pricing.ts index e62fbe3..583e294 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 = "2026-08-28" +export const PRICING_LAST_VERIFIED = "2026-09-01" export const ZERO_MODEL_COST: CommandCodeModelCost = { input: 0, @@ -40,8 +40,6 @@ export const ZERO_MODEL_COST: CommandCodeModelCost = { export const MODEL_COSTS: Readonly> = { // Free models "poolside/laguna-s-2.1-free": { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }, - "minimax/minimax-m3-free": { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }, - "minimax/minimax-m2.7-free": { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }, // Open and open-weight models "tencent/hy3-paid": { input: 0.14, output: 0.58, cacheRead: 0.035, cacheWrite: 0 }, @@ -85,6 +83,12 @@ export const MODEL_COSTS: Readonly> = { cacheRead: 0.007, cacheWrite: 0, }, + "deepseek/deepseek-v4-flash-fast": { + input: 0.28, + output: 0.56, + cacheRead: 0.07, + cacheWrite: 0, + }, "Qwen/Qwen3.8-Max": { input: 2, output: 6, cacheRead: 0.25, cacheWrite: 2.5 }, "Qwen/Qwen3.8-27B": { input: 0.4, output: 3, cacheRead: 0.04, cacheWrite: 0 }, "Qwen/Qwen3.8-Flash": { input: 0.16, output: 0.47, cacheRead: 0.016, cacheWrite: 0 }, @@ -162,9 +166,9 @@ export const MODEL_COSTS: Readonly> = { }, // Anthropic - // Introductory pricing through 2026-08-31. "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-5-1": { 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": { input: 5, output: 25, cacheRead: 0.5, cacheWrite: 6.25 }, "claude-opus-4-8": { input: 5, output: 25, cacheRead: 0.5, cacheWrite: 6.25 }, @@ -187,10 +191,10 @@ export const MODEL_COSTS: Readonly> = { // Google and xAI "google/gemini-3.7-flash": { - input: 0.75, - output: 3.75, - cacheRead: 0.075, - cacheWrite: 0.04167, + input: 1.5, + output: 7.5, + cacheRead: 0.15, + cacheWrite: 0.08334, }, "google/gemini-3.6-flash": { input: 1.5, output: 7.5, cacheRead: 0.15, cacheWrite: 0 }, "google/gemini-3.5-flash": { input: 1.5, output: 9, cacheRead: 0.15, cacheWrite: 0 }, @@ -224,20 +228,4 @@ export const MODEL_COSTS: Readonly> = { }, } -export const TEMPORARY_PRICING: readonly TemporaryPricing[] = [ - { - models: ["claude-sonnet-5"], - expiresOn: "2026-08-31", - description: "introductory pricing", - }, - { - models: ["google/gemini-3.7-flash"], - expiresOn: "2026-12-31", - description: "50% promotional pricing", - }, - { - models: ["minimax/minimax-m3-free", "minimax/minimax-m2.7-free"], - expiresOn: "2026-09-05", - description: "free promotional pricing", - }, -] +export const TEMPORARY_PRICING: readonly TemporaryPricing[] = [] diff --git a/tests/fixtures/commandcode-model-ids.json b/tests/fixtures/commandcode-model-ids.json index bced74b..a6f9aa7 100644 --- a/tests/fixtures/commandcode-model-ids.json +++ b/tests/fixtures/commandcode-model-ids.json @@ -1,9 +1,10 @@ { - "fetchedAt": "2026-08-28T09:27:52.554Z", + "fetchedAt": "2026-09-01T21:28:23.974Z", "source": "https://api.commandcode.ai/provider/v1/models", "modelIds": [ "claude-sonnet-5", "claude-sonnet-4-6", + "claude-fable-5-1", "claude-fable-5", "claude-opus-5", "claude-opus-4-8", @@ -19,6 +20,7 @@ "deepseek/deepseek-v4-pro", "deepseek/deepseek-v4-flash", "deepseek/deepseek-v4-flash-vision-exp", + "deepseek/deepseek-v4-flash-fast", "moonshotai/Kimi-K3", "moonshotai/Kimi-K2.7-Code", "moonshotai/Kimi-K2.7-Code-Highspeed", @@ -32,8 +34,6 @@ "zai-org/GLM-5", "MiniMaxAI/MiniMax-M3", "MiniMaxAI/MiniMax-M2.7", - "minimax/minimax-m3-free", - "minimax/minimax-m2.7-free", "MiniMaxAI/MiniMax-M2.5", "xiaomi/mimo-v2.5-pro", "xiaomi/mimo-v2.5", diff --git a/tests/fixtures/commandcode-pricing.json b/tests/fixtures/commandcode-pricing.json index 0d2d453..0fe4534 100644 --- a/tests/fixtures/commandcode-pricing.json +++ b/tests/fixtures/commandcode-pricing.json @@ -1,5 +1,5 @@ { - "verifiedAt": "2026-08-28", + "verifiedAt": "2026-09-01", "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": { @@ -11,9 +11,9 @@ "xai/grok-4.6": [[200000, 4, 12, 1, 0]] }, "costs": { - "deepseek/deepseek-v4-pro": [0.66, 1.98, 0.022, 0], - "deepseek/deepseek-v4-flash": [0.22, 0.66, 0.007, 0], - "deepseek/deepseek-v4-flash-vision-exp": [0.22, 0.66, 0.007, 0], + "poolside/laguna-s-2.1-free": [0, 0, 0, 0], + "tencent/hy3-paid": [0.14, 0.58, 0.035, 0], + "tencent/hy4-preview": [0.834, 2.501, 0.042, 0], "moonshotai/Kimi-K3": [3, 15, 0.3, 0], "moonshotai/Kimi-K2.7-Code": [0.95, 4, 0.19, 0], "moonshotai/Kimi-K2.7-Code-Highspeed": [1.9, 8, 0.38, 0], @@ -28,8 +28,10 @@ "MiniMaxAI/MiniMax-M3": [0.3, 1.2, 0.06, 0], "MiniMaxAI/MiniMax-M2.7": [0.3, 1.2, 0.06, 0], "MiniMaxAI/MiniMax-M2.5": [0.3, 1.2, 0.03, 0], - "xiaomi/mimo-v2.5-pro": [0.435, 0.87, 0.0036, 0], - "xiaomi/mimo-v2.5": [0.14, 0.28, 0.0028, 0], + "deepseek/deepseek-v4-pro": [0.66, 1.98, 0.022, 0], + "deepseek/deepseek-v4-flash": [0.22, 0.66, 0.007, 0], + "deepseek/deepseek-v4-flash-vision-exp": [0.22, 0.66, 0.007, 0], + "deepseek/deepseek-v4-flash-fast": [0.28, 0.56, 0.07, 0], "Qwen/Qwen3.8-Max": [2, 6, 0.25, 2.5], "Qwen/Qwen3.8-27B": [0.4, 3, 0.04, 0], "Qwen/Qwen3.8-Flash": [0.16, 0.47, 0.016, 0], @@ -40,16 +42,18 @@ "Qwen/Qwen3.6-Plus": [0.5, 3, 0.1, 0], "stepfun/Step-3.7-Flash": [0.2, 1.15, 0.04, 0], "stepfun/Step-3.5-Flash": [0.1, 0.3, 0.02, 0], - "minimax/minimax-m3-free": [0, 0, 0, 0], - "minimax/minimax-m2.7-free": [0, 0, 0, 0], - "tencent/hy3-paid": [0.14, 0.58, 0.035, 0], - "tencent/hy4-preview": [0.834, 2.501, 0.042, 0], + "xiaomi/mimo-v2.5-pro": [0.435, 0.87, 0.0036, 0], + "xiaomi/mimo-v2.5": [0.14, 0.28, 0.0028, 0], "nvidia/nemotron-3-ultra-550b-a55b": [0.6, 2.4, 0.12, 0], + "sakana/fugu-ultra": [5, 30, 0.5, 0], "thinkingmachines/inkling": [1, 4.05, 0.17, 0], "thinkingmachines/inkling-small": [0.5, 1.2, 0.1, 0], - "poolside/laguna-s-2.1-free": [0, 0, 0, 0], + "meta/muse-spark-1.1": [1.25, 4.25, 0.15, 0], + "meta/muse-spark-1.2": [1.25, 4.25, 0.15, 0], + "meta/muse-spark-1.2-contributor": [0.1, 0.2, 0.002, 0], "claude-sonnet-5": [2, 10, 0.2, 2.5], "claude-sonnet-4-6": [3, 15, 0.3, 3.75], + "claude-fable-5-1": [10, 50, 0.25, 12.5], "claude-fable-5": [10, 50, 1, 12.5], "claude-opus-5": [5, 25, 0.5, 6.25], "claude-opus-4-8": [5, 25, 0.5, 6.25], @@ -62,15 +66,11 @@ "gpt-5.4": [2.5, 15, 0.25, 0], "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": [0.75, 3.75, 0.075, 0.04167], + "google/gemini-3.7-flash": [1.5, 7.5, 0.15, 0.08334], "google/gemini-3.6-flash": [1.5, 7.5, 0.15, 0], "google/gemini-3.5-flash": [1.5, 9, 0.15, 0], "google/gemini-3.5-flash-lite": [0.3, 2.5, 0.03, 0], "google/gemini-3.1-flash-lite": [0.25, 1.5, 0.03, 0], - "sakana/fugu-ultra": [5, 30, 0.5, 0], - "meta/muse-spark-1.1": [1.25, 4.25, 0.15, 0], - "meta/muse-spark-1.2": [1.25, 4.25, 0.15, 0], - "meta/muse-spark-1.2-contributor": [0.1, 0.2, 0.002, 0], "xai/grok-4.5": [2, 6, 0.5, 0], "xai/grok-4.6": [2, 6, 0.5, 0] } diff --git a/tests/test-pricing.ts b/tests/test-pricing.ts index 0ec3341..73b8b75 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([ - "poolside/laguna-s-2.1-free", - "minimax/minimax-m3-free", - "minimax/minimax-m2.7-free", -]) +const freeModels = new Set(["poolside/laguna-s-2.1-free"]) function assertCost( modelId: string, @@ -54,7 +50,7 @@ function assertCost( describe("MODEL_COSTS pricing overlay", () => { it("covers the current Command Code model catalog snapshot", () => { assert.equal(fixture.source, "https://api.commandcode.ai/provider/v1/models") - assert.match(fixture.fetchedAt, /^2026-08-28T/) + assert.match(fixture.fetchedAt, /^2026-09-01T/) const catalogIds = [...fixture.modelIds].sort() const pricedIds = Object.keys(MODEL_COSTS).sort() @@ -167,10 +163,22 @@ describe("MODEL_COSTS pricing overlay", () => { cacheWrite: 0, }) assertCost("google/gemini-3.7-flash", { - input: 0.75, - output: 3.75, - cacheRead: 0.075, - cacheWrite: 0.04167, + input: 1.5, + output: 7.5, + cacheRead: 0.15, + cacheWrite: 0.08334, + }) + assertCost("claude-fable-5-1", { + input: 10, + output: 50, + cacheRead: 0.25, + cacheWrite: 12.5, + }) + assertCost("deepseek/deepseek-v4-flash-fast", { + input: 0.28, + output: 0.56, + cacheRead: 0.07, + cacheWrite: 0, }) assertCost("meta/muse-spark-1.2-contributor", { input: 0.1, @@ -218,7 +226,7 @@ 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, "2026-08-28") + assert.equal(PRICING_LAST_VERIFIED, "2026-09-01") }) it("fails once temporary pricing needs review", () => {