fix(models): refresh model pricing

CHANGELOG.md

@@ -2,6 +2,7 @@
 
 ## Unreleased
 
+- Refresh display pricing for the current Command Code model catalog, remove expired Qwen promotional rates, add current free and discounted models, and require review when temporary prices expire.
 - Use the host-provided `pi-ai` and `pi-coding-agent` core packages instead of installing private runtime copies, including for local and out-of-store development checkouts.
 
 ## 0.4.4 - 2026-08-03

index.ts

@@ -20,57 +20,13 @@ import { COMMAND_CODE_CLI_VERSION, createStreamCommandCode, DEFAULT_API_BASE } f
 import { calculateCommandCodeCost } from "./src/cost.ts"
 import { DEFAULT_MODELS_URL, loadCommandCodeModels } from "./src/models.ts"
 import { getApiKey, login, refreshToken } from "./src/oauth.ts"
+import { MODEL_COSTS, ZERO_MODEL_COST } from "./src/pricing.ts"
 
 const API_BASE = process.env.COMMANDCODE_API_BASE ?? DEFAULT_API_BASE
 const MODELS_URL = process.env.COMMANDCODE_MODELS_URL ?? DEFAULT_MODELS_URL
 const MODELS_CACHE_PATH =
   process.env.COMMANDCODE_MODELS_CACHE ?? join(getAgentDir(), "commandcode-models.json")
 
-type CommandCodeModelCost = {
-  input: number
-  output: number
-  cacheRead: number
-  cacheWrite: number
-}
-
-const ZERO_MODEL_COST: CommandCodeModelCost = {
-  input: 0,
-  output: 0,
-  cacheRead: 0,
-  cacheWrite: 0,
-}
-
-// The Provider API supplies the current model list. Keep known display pricing
-// here until the Provider API exposes prices directly.
-const MODEL_COSTS: Record<string, CommandCodeModelCost> = {
-  "claude-opus-4-7": { input: 5, output: 25, cacheRead: 0.5, cacheWrite: 6.25 },
-  "claude-opus-4-6": { input: 5, output: 25, cacheRead: 0.5, cacheWrite: 6.25 },
-  "claude-sonnet-4-6": { input: 3, output: 15, cacheRead: 0.3, cacheWrite: 3.75 },
-  "claude-haiku-4-5-20251001": { input: 1, output: 5, cacheRead: 0.1, cacheWrite: 1.25 },
-  "gpt-5.5": { input: 5, output: 30, cacheRead: 0.5, cacheWrite: 0 },
-  "gpt-5.4": { input: 2.5, output: 15, cacheRead: 0.25, cacheWrite: 0 },
-  "gpt-5.3-codex": { input: 2, output: 8, cacheRead: 0.5, cacheWrite: 0 },
-  "gpt-5.4-mini": { input: 0.75, output: 4.5, cacheRead: 0.075, cacheWrite: 0 },
-  "google/gemini-3.5-flash": { input: 1.5, output: 9, cacheRead: 0.15, cacheWrite: 0 },
-  "google/gemini-3.1-flash-lite": { input: 0.25, output: 1.5, cacheRead: 0.03, cacheWrite: 0 },
-  // 4× usage deal: 75% off (permanent, no expiry)
-  "deepseek/deepseek-v4-pro": { input: 0.435, output: 0.87, cacheRead: 0.003625, cacheWrite: 0 },
-  "deepseek/deepseek-v4-flash": { input: 0.14, output: 0.28, cacheRead: 0.028, cacheWrite: 0 },
-  "moonshotai/Kimi-K2.6": { input: 0.95, output: 4, cacheRead: 0.16, cacheWrite: 0 },
-  "moonshotai/Kimi-K2.5": { input: 0.6, output: 3, cacheRead: 0.1, cacheWrite: 0 },
-  "zai-org/GLM-5.1": { input: 1.4, output: 4.4, cacheRead: 0.26, cacheWrite: 0 },
-  "zai-org/GLM-5": { input: 1, output: 3.2, cacheRead: 0.2, cacheWrite: 0 },
-  "MiniMaxAI/MiniMax-M2.7": { input: 0.3, output: 1.2, cacheRead: 0.06, cacheWrite: 0 },
-  "MiniMaxAI/MiniMax-M2.5": { input: 0.27, output: 0.95, cacheRead: 0.03, cacheWrite: 0 },
-  "Qwen/Qwen3.6-Max-Preview": { input: 1.3, output: 7.8, cacheRead: 0.26, cacheWrite: 1.63 },
-  "Qwen/Qwen3.6-Plus": { input: 0.5, output: 3, cacheRead: 0.1, cacheWrite: 0 },
-  // 2× usage deal: 50% off through June 22, 2026
-  "Qwen/Qwen3.7-Max": { input: 1.25, output: 3.75, cacheRead: 0.25, cacheWrite: 1.56 },
-  "stepfun/Step-3.5-Flash": { input: 0.1, output: 0.3, cacheRead: 0.02, cacheWrite: 0 },
-  "xiaomi/mimo-v2.5-pro": { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
-  "xiaomi/mimo-v2.5": { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
-}
-
 const streamCommandCode = createStreamCommandCode({
   createStream: () => new AssistantMessageEventStream(),
   calculateCost: calculateCommandCodeCost,

src/cost.ts

@@ -10,10 +10,22 @@
 import type { ModelLike, Usage } from "./types.ts"
 
 export function calculateCommandCodeCost(model: ModelLike, usage: Usage): void {
-  usage.cost.input = (model.cost.input / 1_000_000) * usage.input
-  usage.cost.output = (model.cost.output / 1_000_000) * usage.output
-  usage.cost.cacheRead = (model.cost.cacheRead / 1_000_000) * usage.cacheRead
-  usage.cost.cacheWrite = (model.cost.cacheWrite * usage.cacheWrite) / 1_000_000
+  const inputTokens = usage.input + usage.cacheRead + usage.cacheWrite
+  let rates = model.cost
+  let matchedThreshold = -1
+  for (const tier of model.cost.tiers ?? []) {
+    if (inputTokens > tier.inputTokensAbove && tier.inputTokensAbove > matchedThreshold) {
+      rates = tier
+      matchedThreshold = tier.inputTokensAbove
+    }
+  }
+
+  const longWrite = usage.cacheWrite1h ?? 0
+  const shortWrite = usage.cacheWrite - longWrite
+  usage.cost.input = (rates.input / 1_000_000) * usage.input
+  usage.cost.output = (rates.output / 1_000_000) * usage.output
+  usage.cost.cacheRead = (rates.cacheRead / 1_000_000) * usage.cacheRead
+  usage.cost.cacheWrite = (rates.cacheWrite * shortWrite + rates.input * 2 * longWrite) / 1_000_000
   usage.cost.total =
     usage.cost.input + usage.cost.output + usage.cost.cacheRead + usage.cost.cacheWrite
 }

src/pricing.ts

@@ -0,0 +1,226 @@
+export interface CommandCodeModelCostRates {
+  input: number
+  output: number
+  cacheRead: number
+  cacheWrite: number
+}
+
+export interface CommandCodeModelCostTier extends CommandCodeModelCostRates {
+  inputTokensAbove: number
+}
+
+export interface CommandCodeModelCost extends CommandCodeModelCostRates {
+  tiers?: readonly CommandCodeModelCostTier[]
+}
+
+export interface TemporaryPricing {
+  models: readonly string[]
+  expiresOn: string
+  description: string
+}
+
+export const PRICING_SOURCE_URL = "https://commandcode.ai/docs/resources/pricing-limits"
+export const PRICING_LAST_VERIFIED = "2026-08-04"
+
+export const ZERO_MODEL_COST: CommandCodeModelCost = {
+  input: 0,
+  output: 0,
+  cacheRead: 0,
+  cacheWrite: 0,
+}
+
+/**
+ * Display prices in USD per million tokens.
+ *
+ * Context-dependent rates use pi's request-wide input pricing tiers. The
+ * highest threshold exceeded by input + cache reads + cache writes applies to
+ * the full request. The Command Code usage page remains authoritative for the
+ * amount billed for an individual request.
+ */
+export const MODEL_COSTS: Readonly<Record<string, CommandCodeModelCost>> = {
+  // Free models
+  "poolside/laguna-s-2.1-free": { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+  "inclusionai/ling-3.0-flash-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 },
+  "moonshotai/Kimi-K3": { input: 3, output: 15, cacheRead: 0.3, cacheWrite: 0 },
+  "moonshotai/Kimi-K2.7-Code": { input: 0.95, output: 4, cacheRead: 0.19, cacheWrite: 0 },
+  "moonshotai/Kimi-K2.7-Code-Highspeed": {
+    input: 1.9,
+    output: 8,
+    cacheRead: 0.38,
+    cacheWrite: 0,
+  },
+  "moonshotai/Kimi-K2.6": { input: 0.95, output: 4, cacheRead: 0.16, cacheWrite: 0 },
+  "moonshotai/Kimi-K2.5": { input: 0.6, output: 3, cacheRead: 0.1, cacheWrite: 0 },
+  "zai-org/GLM-5.2": { input: 1.4, output: 4.4, cacheRead: 0.26, cacheWrite: 0 },
+  "zai-org/GLM-5.2-Fast": { input: 3, output: 10.25, cacheRead: 0.5, cacheWrite: 0 },
+  "zai-org/GLM-5.1": { input: 1.4, output: 4.4, cacheRead: 0.26, cacheWrite: 0 },
+  "zai-org/GLM-5": { input: 1, output: 3.2, cacheRead: 0.2, cacheWrite: 0 },
+  "MiniMaxAI/MiniMax-M3": { input: 0.3, output: 1.2, cacheRead: 0.06, cacheWrite: 0 },
+  "MiniMaxAI/MiniMax-M2.7": { input: 0.3, output: 1.2, cacheRead: 0.06, cacheWrite: 0 },
+  "MiniMaxAI/MiniMax-M2.5": { input: 0.3, output: 1.2, cacheRead: 0.03, cacheWrite: 0 },
+  // Permanent 75% discount.
+  "deepseek/deepseek-v4-pro": {
+    input: 0.435,
+    output: 0.87,
+    cacheRead: 0.003625,
+    cacheWrite: 0,
+  },
+  "deepseek/deepseek-v4-flash": {
+    input: 0.14,
+    output: 0.28,
+    cacheRead: 0.0028,
+    cacheWrite: 0,
+  },
+  "Qwen/Qwen3.8-Max": { input: 2, output: 6, cacheRead: 0.25, cacheWrite: 2.5 },
+  "Qwen/Qwen3.7-Max": { input: 2.5, output: 7.5, cacheRead: 0.5, cacheWrite: 3.13 },
+  "Qwen/Qwen3.7-Plus": {
+    input: 0.4,
+    output: 1.6,
+    cacheRead: 0.08,
+    cacheWrite: 0.5,
+    tiers: [
+      {
+        inputTokensAbove: 256_000,
+        input: 1.2,
+        output: 4.8,
+        cacheRead: 0.24,
+        cacheWrite: 1.5,
+      },
+    ],
+  },
+  "Qwen/Qwen3.7-Flash": {
+    input: 0.03,
+    output: 0.13,
+    cacheRead: 0.006,
+    cacheWrite: 0.038,
+    tiers: [
+      {
+        inputTokensAbove: 32_000,
+        input: 0.1,
+        output: 0.4,
+        cacheRead: 0.02,
+        cacheWrite: 0.125,
+      },
+      {
+        inputTokensAbove: 256_000,
+        input: 0.2,
+        output: 0.8,
+        cacheRead: 0.04,
+        cacheWrite: 0.25,
+      },
+    ],
+  },
+  "Qwen/Qwen3.6-Max-Preview": {
+    input: 1.3,
+    output: 7.8,
+    cacheRead: 0.26,
+    cacheWrite: 1.63,
+  },
+  "Qwen/Qwen3.6-Plus": { input: 0.5, output: 3, cacheRead: 0.1, cacheWrite: 0 },
+  "stepfun/Step-3.7-Flash": { input: 0.2, output: 1.15, cacheRead: 0.04, cacheWrite: 0 },
+  "stepfun/Step-3.5-Flash": { input: 0.1, output: 0.3, cacheRead: 0.02, cacheWrite: 0 },
+  // Permanent discounted rates.
+  "xiaomi/mimo-v2.5-pro": { input: 0.435, output: 0.87, cacheRead: 0.0036, cacheWrite: 0 },
+  "xiaomi/mimo-v2.5": { input: 0.14, output: 0.28, cacheRead: 0.0028, cacheWrite: 0 },
+  "nvidia/nemotron-3-ultra-550b-a55b": {
+    input: 0.6,
+    output: 2.4,
+    cacheRead: 0.12,
+    cacheWrite: 0,
+  },
+  "sakana/fugu-ultra": { input: 5, output: 30, cacheRead: 0.5, cacheWrite: 0 },
+  "thinkingmachines/inkling": { input: 1, output: 4.05, cacheRead: 0.17, cacheWrite: 0 },
+  "thinkingmachines/inkling-small": {
+    input: 0.5,
+    output: 1.2,
+    cacheRead: 0.1,
+    cacheWrite: 0,
+  },
+  "meta/muse-spark-1.1": { input: 1.25, output: 4.25, cacheRead: 0.15, cacheWrite: 0 },
+
+  // 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": { 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 },
+  "claude-opus-4-7": { input: 5, output: 25, cacheRead: 0.5, cacheWrite: 6.25 },
+  "claude-haiku-4-5-20251001": {
+    input: 1,
+    output: 5,
+    cacheRead: 0.1,
+    cacheWrite: 1.25,
+  },
+
+  // OpenAI
+  "gpt-5.6-sol": { input: 5, output: 30, cacheRead: 0.5, cacheWrite: 6.25 },
+  // Discounted rates through 2026-08-14.
+  "gpt-5.6-terra": {
+    input: 1,
+    output: 6,
+    cacheRead: 0.1,
+    cacheWrite: 1.25,
+    tiers: [
+      {
+        inputTokensAbove: 272_000,
+        input: 2,
+        output: 9,
+        cacheRead: 0.2,
+        cacheWrite: 2.5,
+      },
+    ],
+  },
+  "gpt-5.6-luna": {
+    input: 0.1,
+    output: 0.6,
+    cacheRead: 0.01,
+    cacheWrite: 0.125,
+    tiers: [
+      {
+        inputTokensAbove: 272_000,
+        input: 0.2,
+        output: 0.9,
+        cacheRead: 0.02,
+        cacheWrite: 0.25,
+      },
+    ],
+  },
+  "gpt-5.5": { input: 5, output: 30, cacheRead: 0.5, cacheWrite: 0 },
+  "gpt-5.4": { input: 2.5, output: 15, cacheRead: 0.25, cacheWrite: 0 },
+  "gpt-5.3-codex": { input: 2, output: 8, cacheRead: 0.5, cacheWrite: 0 },
+  "gpt-5.4-mini": { input: 0.75, output: 4.5, cacheRead: 0.075, cacheWrite: 0 },
+
+  // Google and xAI
+  "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 },
+  "google/gemini-3.5-flash-lite": {
+    input: 0.3,
+    output: 2.5,
+    cacheRead: 0.03,
+    cacheWrite: 0,
+  },
+  "google/gemini-3.1-flash-lite": {
+    input: 0.25,
+    output: 1.5,
+    cacheRead: 0.03,
+    cacheWrite: 0,
+  },
+  "xai/grok-4.5": { input: 2, output: 6, cacheRead: 0.5, cacheWrite: 0 },
+}
+
+export const TEMPORARY_PRICING: readonly TemporaryPricing[] = [
+  {
+    models: ["gpt-5.6-terra", "gpt-5.6-luna"],
+    expiresOn: "2026-08-14",
+    description: "50% promotional rates",
+  },
+  {
+    models: ["claude-sonnet-5"],
+    expiresOn: "2026-08-31",
+    description: "introductory pricing",
+  },
+]

src/types.ts

@@ -15,6 +15,7 @@ export interface Usage {
   output: number
   cacheRead: number
   cacheWrite: number
+  cacheWrite1h?: number
   totalTokens: number
   cost: UsageCost
 }
@@ -50,13 +51,21 @@ export interface AssistantMessageLike {
   timestamp: number
 }
 
-export interface ModelCost {
+export interface ModelCostRates {
   input: number
   output: number
   cacheRead: number
   cacheWrite: number
 }
 
+export interface ModelCostTier extends ModelCostRates {
+  inputTokensAbove: number
+}
+
+export interface ModelCost extends ModelCostRates {
+  tiers?: readonly ModelCostTier[]
+}
+
 export interface ModelLike {
   id: string
   api: unknown