pi-tokenrouter 1.0.4 → 1.0.5

package/README.md

@@ -2,7 +2,7 @@
 
 A [pi](https://github.com/badlogic/pi-mono) provider extension for [TokenRouter](https://tokenrouter.com).
 
-Dynamically discovers available models from the TokenRouter API and enriches them with pricing, context window, and max output token data from [OpenRouter](https://openrouter.ai) (TokenRouter shares the same pricing).
+Models are derived from TokenRouter's `/v1/models` list and enriched with metadata from [models.dev](https://models.dev) first, then [OpenRouter](https://openrouter.ai).
 
 ## Install
 
@@ -33,12 +33,9 @@ export TOKENROUTER_API_KEY=sk-...
 
 ## How it works
 
-1. On startup, fetches the model list from TokenRouter's `/v1/models` endpoint.
-2. In parallel, fetches pricing data from OpenRouter's public model catalog.
-3. Matches models by ID and fills in cost, context window, and max output tokens.
-4. Caches everything locally for 1 week (`~/.pi/agent/cache/tokenrouter-models.json`).
-
-Models that don't match an OpenRouter entry fall back to zero cost and default context limits.
+1. Registers TokenRouter as an API-key provider, so `/login tokenrouter` is handled under `Use an API key`.
+2. Uses a checked-in snapshot generated from TokenRouter's authenticated `/v1/models` response.
+3. Enriches each model with metadata from `models.dev` when available, then falls back to OpenRouter for pricing, context window, max output tokens, reasoning support, and image support.
 
 ## License
 

package/index.ts

@@ -2,304 +2,23 @@
  * TokenRouter Provider Extension
  *
  * Registers TokenRouter (https://api.tokenrouter.com/v1) as a custom provider.
- * Dynamically fetches available models from the /v1/models endpoint with
- * file-based caching to avoid redundant API calls on startup.
- *
- * Authentication (resolved via AuthStorage with full priority chain):
- *   1. Runtime overrides (CLI --api-key)
- *   2. API key from auth.json (literal, env var name, or shell command)
- *   3. OAuth token from auth.json (from /login tokenrouter)
- *   4. TOKENROUTER_API_KEY environment variable
+ * Models are derived from TokenRouter's /v1/models list, enriched with
+ * metadata from models.dev first and OpenRouter second, so TokenRouter can be
+ * configured through pi's API-key login flow before any TokenRouter auth exists.
  *
  * Usage:
  *   pi -e /path/to/pi-tokenrouter
- *   /login tokenrouter          # stores key in auth.json
+ *   /login tokenrouter
  *   # OR add to ~/.pi/agent/auth.json:
  *   #   "tokenrouter": { "type": "api_key", "key": "sk-..." }
  *   #   "tokenrouter": { "type": "api_key", "key": "TOKENROUTER_API_KEY" }
  *   #   "tokenrouter": { "type": "api_key", "key": "!op read 'op://vault/item/key'" }
  */
 
-import { existsSync, mkdirSync, readFileSync, writeFileSync } from "node:fs";
-import { join } from "node:path";
-import { homedir } from "node:os";
-import type { OAuthCredentials, OAuthLoginCallbacks } from "@mariozechner/pi-ai";
-import { AuthStorage } from "@mariozechner/pi-coding-agent";
 import type { ExtensionAPI } from "@mariozechner/pi-coding-agent";
-
-const BASE_URL = "https://api.tokenrouter.com/v1";
-const PROVIDER_NAME = "tokenrouter";
-const OPENROUTER_MODELS_URL = "https://openrouter.ai/api/v1/models";
-
-const HOME_PI = join(homedir(), ".pi", "agent");
-const CACHE_DIR = join(HOME_PI, "cache");
-const CACHE_FILE = join(CACHE_DIR, "tokenrouter-models.json");
-const CACHE_TTL_MS = 7 * 24 * 60 * 60 * 1000; // 1 week
-
-const DEFAULT_CONTEXT_WINDOW = 128_000;
-const DEFAULT_MAX_TOKENS = 4_096;
-
-// Reasoning model name patterns
-const REASONING_PATTERNS = [
-    /o1\b/i,
-    /o3\b/i,
-    /o4\b/i,
-    /claude.*thinking/i,
-    /deepseek-r/i,
-    /deepseek-prover/i,
-    /gemini.*thinking/i,
-    /qwq/i,
-    /qwen3/i,
-    /reasoning/i,
-];
-
-// Vision model name patterns
-const VISION_PATTERNS = [
-    /vision/i,
-    /claude/i,
-    /gpt-4o/i,
-    /gpt-4-turbo/i,
-    /gemini/i,
-    /llava/i,
-    /qwen.*vl/i,
-    /qwen.*visual/i,
-];
-
-function isReasoningModel(id: string): boolean {
-    return REASONING_PATTERNS.some((p) => p.test(id));
-}
-
-function supportsVision(id: string): boolean {
-    return VISION_PATTERNS.some((p) => p.test(id));
-}
-
-// ---------------------------------------------------------------------------
-// OpenRouter pricing lookup
-// ---------------------------------------------------------------------------
-
-interface OpenRouterModel {
-    id: string;
-    context_length?: number;
-    top_provider?: { max_completion_tokens?: number };
-    pricing?: {
-        prompt?: string;
-        completion?: string;
-        input_cache_read?: string;
-        input_cache_write?: string;
-    };
-}
-
-interface Pricing {
-    input: number;
-    output: number;
-    cacheRead: number;
-    cacheWrite: number;
-    contextWindow: number;
-    maxTokens: number;
-}
-
-function parsePerToken(price?: string): number {
-    const n = parseFloat(price ?? "0");
-    return Number.isFinite(n) ? n * 1_000_000 : 0;
-}
-
-async function fetchOpenRouterPricing(): Promise<Map<string, Pricing>> {
-    const response = await fetch(OPENROUTER_MODELS_URL);
-    if (!response.ok) return new Map();
-
-    const payload = (await response.json()) as { data?: OpenRouterModel[] };
-    const models = payload.data ?? [];
-
-    const map = new Map<string, Pricing>();
-    for (const m of models) {
-        map.set(m.id, {
-            input: parsePerToken(m.pricing?.prompt),
-            output: parsePerToken(m.pricing?.completion),
-            cacheRead: parsePerToken(m.pricing?.input_cache_read),
-            cacheWrite: parsePerToken(m.pricing?.input_cache_write),
-            contextWindow: m.context_length ?? DEFAULT_CONTEXT_WINDOW,
-            maxTokens: m.top_provider?.max_completion_tokens ?? DEFAULT_MAX_TOKENS,
-        });
-    }
-    return map;
-}
-
-// ---------------------------------------------------------------------------
-// Model cache
-// ---------------------------------------------------------------------------
-
-interface CachedModels {
-    fetchedAt: number;
-    models: RawModel[];
-    pricing: Record<string, Pricing>;
-}
-
-interface RawModel {
-    id: string;
-    name?: string;
-    context_window?: number;
-    max_tokens?: number;
-    [key: string]: unknown;
-}
-
-function readCache(): CachedModels | null {
-    try {
-        if (!existsSync(CACHE_FILE)) return null;
-        const raw = readFileSync(CACHE_FILE, "utf-8");
-        const data = JSON.parse(raw) as CachedModels;
-        // Invalidate cache from before pricing was added
-        if (!data.pricing) return null;
-        return data;
-    } catch {
-        return null;
-    }
-}
-
-function writeCache(models: RawModel[], pricing: Map<string, Pricing>): void {
-    try {
-        if (!existsSync(CACHE_DIR)) {
-            mkdirSync(CACHE_DIR, { recursive: true });
-        }
-        // Serialise pricing map to plain object
-        const pricingObj: Record<string, Pricing> = {};
-        for (const [k, v] of pricing) pricingObj[k] = v;
-        const payload: CachedModels = { fetchedAt: Date.now(), models, pricing: pricingObj };
-        writeFileSync(CACHE_FILE, JSON.stringify(payload), "utf-8");
-    } catch {
-        // Cache write failure is non-fatal
-    }
-}
-
-function isCacheFresh(cache: CachedModels): boolean {
-    return Date.now() - cache.fetchedAt < CACHE_TTL_MS;
-}
-
-// ---------------------------------------------------------------------------
-// Model fetching
-// ---------------------------------------------------------------------------
-
-async function fetchModels(apiKey: string): Promise<RawModel[]> {
-    const response = await fetch(`${BASE_URL}/models`, {
-        headers: {
-            Authorization: `Bearer ${apiKey}`,
-            Accept: "application/json",
-        },
-    });
-
-    if (!response.ok) {
-        throw new Error(`TokenRouter /v1/models returned ${response.status}: ${await response.text()}`);
-    }
-
-    const payload = (await response.json()) as {
-        data: Array<Record<string, unknown>>;
-    };
-
-    return payload.data.map((m) => ({
-        id: m.id as string,
-        name: (m.name as string | undefined) ?? (m.id as string),
-        context_window: (m.context_window ?? m.contextWindow ?? undefined) as number | undefined,
-        max_tokens: (m.max_tokens ?? m.maxTokens ?? undefined) as number | undefined,
-    }));
-}
-
-async function getModelsAndPricing(apiKey: string): Promise<{ models: RawModel[]; pricing: Map<string, Pricing> }> {
-    const cache = readCache();
-    if (cache && isCacheFresh(cache)) {
-        const pricingMap = new Map<string, Pricing>(Object.entries(cache.pricing));
-        return { models: cache.models, pricing: pricingMap };
-    }
-
-    try {
-        const [models, pricing] = await Promise.all([
-            fetchModels(apiKey),
-            fetchOpenRouterPricing(),
-        ]);
-        writeCache(models, pricing);
-        return { models, pricing };
-    } catch {
-        if (cache) {
-            const pricingMap = new Map<string, Pricing>(Object.entries(cache.pricing));
-            return { models: cache.models, pricing: pricingMap };
-        }
-        throw new Error(
-            "Failed to fetch models from TokenRouter and no cached data available. " +
-            "Configure authentication via /login tokenrouter, auth.json, or TOKENROUTER_API_KEY.",
-        );
-    }
-}
-
-// ---------------------------------------------------------------------------
-// OAuth (API key prompt flow for /login)
-// ---------------------------------------------------------------------------
-
-async function loginTokenRouter(callbacks: OAuthLoginCallbacks): Promise<OAuthCredentials> {
-    const key = await callbacks.onPrompt({ message: "Enter your TokenRouter API key:" });
-    if (!key || !key.trim()) {
-        throw new Error("No API key provided");
-    }
-    // API keys don't expire — set far-future expiry so pi won't try to refresh
-    const farFuture = Date.now() + 10 * 365 * 24 * 60 * 60 * 1000;
-    return {
-        refresh: key.trim(),
-        access: key.trim(),
-        expires: farFuture,
-    };
-}
-
-async function refreshTokenRouter(credentials: OAuthCredentials): Promise<OAuthCredentials> {
-    // API keys don't expire — return as-is
-    return credentials;
-}
-
-// ---------------------------------------------------------------------------
-// Extension entry point
-// ---------------------------------------------------------------------------
-
-const oauth = {
-    name: "TokenRouter",
-    login: loginTokenRouter,
-    refreshToken: refreshTokenRouter,
-    getApiKey: (cred: OAuthCredentials) => cred.access,
-};
+import { TOKENROUTER_MODELS } from "./models.generated.js";
+import { createTokenRouterProviderConfig, PROVIDER_NAME } from "./provider-config.js";
 
 export default async function(pi: ExtensionAPI) {
-    // Resolve API key through AuthStorage with full priority chain:
-    // runtime overrides → auth.json api_key → auth.json oauth → env vars
-    const authStorage = AuthStorage.create();
-    const apiKey = await authStorage.getApiKey(PROVIDER_NAME);
-
-    if (!apiKey) {
-        // Register provider with OAuth only (no models) so /login works.
-        // After /login, user needs /reload to fetch and register models.
-        pi.registerProvider(PROVIDER_NAME, {
-            baseUrl: BASE_URL,
-            api: "openai-completions",
-            authHeader: true,
-            oauth,
-        });
-        return;
-    }
-
-    const { models: rawModels, pricing } = await getModelsAndPricing(apiKey);
-
-    pi.registerProvider(PROVIDER_NAME, {
-        baseUrl: BASE_URL,
-        api: "openai-completions",
-        authHeader: true,
-        models: rawModels.map((m) => {
-            const p = pricing.get(m.id);
-            return {
-                id: m.id,
-                name: m.name ?? m.id,
-                reasoning: isReasoningModel(m.id),
-                input: supportsVision(m.id) ? (["text", "image"] as const) : (["text"] as const),
-                cost: p
-                    ? { input: p.input, output: p.output, cacheRead: p.cacheRead, cacheWrite: p.cacheWrite }
-                    : { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
-                contextWindow: m.context_window ?? p?.contextWindow ?? DEFAULT_CONTEXT_WINDOW,
-                maxTokens: m.max_tokens ?? p?.maxTokens ?? DEFAULT_MAX_TOKENS,
-            };
-        }),
-        oauth,
-    });
+    pi.registerProvider(PROVIDER_NAME, createTokenRouterProviderConfig(TOKENROUTER_MODELS));
 }

package/models.generated.ts

@@ -0,0 +1,1003 @@
+import type { TokenRouterProviderModel } from "./provider-config.js";
+
+// Derived from TokenRouter /v1/models and enriched with models.dev, then OpenRouter metadata.
+// Generated on 2026-05-07T03:18:45.215Z.
+export const TOKENROUTER_MODELS: TokenRouterProviderModel[] = [
+    {
+        "id": "claude-haiku-4-5",
+        "name": "Claude Haiku 4.5 (latest)",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 1,
+            "output": 5,
+            "cacheRead": 0.1,
+            "cacheWrite": 1.25
+        },
+        "contextWindow": 200000,
+        "maxTokens": 64000
+    },
+    {
+        "id": "qwen/qwen3.5-9b",
+        "name": "Qwen3.5 9B",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 0.1,
+            "output": 0.4,
+            "cacheRead": 0,
+            "cacheWrite": 0
+        },
+        "contextWindow": 262144,
+        "maxTokens": 262144
+    },
+    {
+        "id": "xiaomi/mimo-v2.5-pro",
+        "name": "MiMo V2.5 Pro",
+        "reasoning": true,
+        "input": [
+            "text"
+        ],
+        "cost": {
+            "input": 1,
+            "output": 3,
+            "cacheRead": 0.19999999999999998,
+            "cacheWrite": 0
+        },
+        "contextWindow": 1050000,
+        "maxTokens": 131000
+    },
+    {
+        "id": "minimax/minimax-m2.7-highspeed",
+        "name": "MiniMax M2.7 High Speed",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 0.6,
+            "output": 2.4,
+            "cacheRead": 0.06,
+            "cacheWrite": 0.375
+        },
+        "contextWindow": 204800,
+        "maxTokens": 131100
+    },
+    {
+        "id": "deepseek/deepseek-v4-pro",
+        "name": "DeepSeek V4 Pro",
+        "reasoning": true,
+        "input": [
+            "text"
+        ],
+        "cost": {
+            "input": 1.74,
+            "output": 3.48,
+            "cacheRead": 0.145,
+            "cacheWrite": 0
+        },
+        "contextWindow": 1000000,
+        "maxTokens": 384000
+    },
+    {
+        "id": "minimax/minimax-m2.7",
+        "name": "Minimax M2.7",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 0.3,
+            "output": 1.2,
+            "cacheRead": 0.06,
+            "cacheWrite": 0.375
+        },
+        "contextWindow": 204800,
+        "maxTokens": 131000
+    },
+    {
+        "id": "qwen/qwen3.5-122b-a10b",
+        "name": "Qwen3.5 122B A10B",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 0.4,
+            "output": 3.2,
+            "cacheRead": 0,
+            "cacheWrite": 0
+        },
+        "contextWindow": 262144,
+        "maxTokens": 262144
+    },
+    {
+        "id": "xiaomi/mimo-v2.5",
+        "name": "MiMo M2.5",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 0.39999999999999997,
+            "output": 2,
+            "cacheRead": 0.08,
+            "cacheWrite": 0
+        },
+        "contextWindow": 1050000,
+        "maxTokens": 131100
+    },
+    {
+        "id": "qwen/qwen3.5-plus-02-15",
+        "name": "Qwen: Qwen3.5 Plus 2026-02-15",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 0.26,
+            "output": 1.56,
+            "cacheRead": 0,
+            "cacheWrite": 0.325
+        },
+        "contextWindow": 1000000,
+        "maxTokens": 65536
+    },
+    {
+        "id": "x-ai/grok-4.20-beta",
+        "name": "Grok 4.20 Beta",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 2,
+            "output": 6,
+            "cacheRead": 0.2,
+            "cacheWrite": 0
+        },
+        "contextWindow": 2000000,
+        "maxTokens": 30000
+    },
+    {
+        "id": "deepseek/deepseek-v3.2",
+        "name": "DeepSeek V3.2",
+        "reasoning": true,
+        "input": [
+            "text"
+        ],
+        "cost": {
+            "input": 0.27,
+            "output": 0.4,
+            "cacheRead": 0.22,
+            "cacheWrite": 0
+        },
+        "contextWindow": 163842,
+        "maxTokens": 8000
+    },
+    {
+        "id": "openai/gpt-5.2",
+        "name": "GPT-5.2",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 1.75,
+            "output": 14,
+            "cacheRead": 0.18,
+            "cacheWrite": 0
+        },
+        "contextWindow": 400000,
+        "maxTokens": 128000
+    },
+    {
+        "id": "anthropic/claude-opus-4.7",
+        "name": "Claude Opus 4.7",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 5,
+            "output": 25,
+            "cacheRead": 0.5,
+            "cacheWrite": 6.25
+        },
+        "contextWindow": 1000000,
+        "maxTokens": 128000
+    },
+    {
+        "id": "qwen/qwen3.5-35b-a3b",
+        "name": "Qwen3.5 35B A3B",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 0.25,
+            "output": 1.3,
+            "cacheRead": 0.049999999999999996,
+            "cacheWrite": 0
+        },
+        "contextWindow": 262144,
+        "maxTokens": 262144
+    },
+    {
+        "id": "anthropic/claude-sonnet-4.5",
+        "name": "Claude Sonnet 4.5",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 3,
+            "output": 15,
+            "cacheRead": 0.3,
+            "cacheWrite": 3.75
+        },
+        "contextWindow": 200000,
+        "maxTokens": 64000
+    },
+    {
+        "id": "stepfun/step-3.5-flash",
+        "name": "StepFun: Step 3.5 Flash",
+        "reasoning": true,
+        "input": [
+            "text"
+        ],
+        "cost": {
+            "input": 0.1,
+            "output": 0.3,
+            "cacheRead": 0.02,
+            "cacheWrite": 0
+        },
+        "contextWindow": 256000,
+        "maxTokens": 256000
+    },
+    {
+        "id": "google/gemini-3-flash-preview",
+        "name": "Gemini 3 Flash",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 0.5,
+            "output": 3,
+            "cacheRead": 0.05,
+            "cacheWrite": 1
+        },
+        "contextWindow": 1048576,
+        "maxTokens": 65536
+    },
+    {
+        "id": "z-ai/glm-5-turbo",
+        "name": "Z.ai: GLM 5 Turbo",
+        "reasoning": true,
+        "input": [
+            "text"
+        ],
+        "cost": {
+            "input": 1.2,
+            "output": 4,
+            "cacheRead": 0.24,
+            "cacheWrite": 0
+        },
+        "contextWindow": 202752,
+        "maxTokens": 131072
+    },
+    {
+        "id": "openai/gpt-5.4-pro",
+        "name": "GPT 5.4 Pro",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 30,
+            "output": 180,
+            "cacheRead": 0,
+            "cacheWrite": 0
+        },
+        "contextWindow": 1050000,
+        "maxTokens": 128000
+    },
+    {
+        "id": "qwen/qwen3.5-397b-a17b",
+        "name": "Qwen3.5-397B-A17B",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 0,
+            "output": 0,
+            "cacheRead": 0.195,
+            "cacheWrite": 0
+        },
+        "contextWindow": 262144,
+        "maxTokens": 8192
+    },
+    {
+        "id": "anthropic/claude-opus-4.5",
+        "name": "Claude Opus 4.5",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 5,
+            "output": 25,
+            "cacheRead": 0.5,
+            "cacheWrite": 18.75
+        },
+        "contextWindow": 200000,
+        "maxTokens": 64000
+    },
+    {
+        "id": "mistralai/devstral-2512",
+        "name": "Mistral: Devstral 2 2512",
+        "reasoning": false,
+        "input": [
+            "text"
+        ],
+        "cost": {
+            "input": 0.4,
+            "output": 2,
+            "cacheRead": 0.025,
+            "cacheWrite": 0
+        },
+        "contextWindow": 262144,
+        "maxTokens": 65536
+    },
+    {
+        "id": "anthropic/claude-sonnet-4",
+        "name": "Claude Sonnet 4",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 3,
+            "output": 15,
+            "cacheRead": 0.3,
+            "cacheWrite": 3.75
+        },
+        "contextWindow": 200000,
+        "maxTokens": 64000
+    },
+    {
+        "id": "x-ai/grok-4.3",
+        "name": "xAI: Grok 4.3",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 1.25,
+            "output": 2.5,
+            "cacheRead": 0.2,
+            "cacheWrite": 0
+        },
+        "contextWindow": 1000000,
+        "maxTokens": 4096
+    },
+    {
+        "id": "deepseek-v4-flash",
+        "name": "DeepSeek V4 Flash",
+        "reasoning": true,
+        "input": [
+            "text"
+        ],
+        "cost": {
+            "input": 0.14,
+            "output": 0.28,
+            "cacheRead": 0.028,
+            "cacheWrite": 0
+        },
+        "contextWindow": 1000000,
+        "maxTokens": 384000
+    },
+    {
+        "id": "z-ai/glm-5.1",
+        "name": "GLM-5.1",
+        "reasoning": true,
+        "input": [
+            "text"
+        ],
+        "cost": {
+            "input": 0,
+            "output": 0,
+            "cacheRead": 0.5249999999999999,
+            "cacheWrite": 0
+        },
+        "contextWindow": 131072,
+        "maxTokens": 131072
+    },
+    {
+        "id": "anthropic/claude-sonnet-4.6",
+        "name": "Claude Sonnet 4.6",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 3,
+            "output": 15,
+            "cacheRead": 0.3,
+            "cacheWrite": 3.75
+        },
+        "contextWindow": 1000000,
+        "maxTokens": 128000
+    },
+    {
+        "id": "anthropic/claude-haiku-4.5",
+        "name": "Claude Haiku 4.5",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 1,
+            "output": 5,
+            "cacheRead": 0.1,
+            "cacheWrite": 1.25
+        },
+        "contextWindow": 200000,
+        "maxTokens": 64000
+    },
+    {
+        "id": "openai/gpt-5.4",
+        "name": "GPT 5.4",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 2.5,
+            "output": 15,
+            "cacheRead": 0.25,
+            "cacheWrite": 0
+        },
+        "contextWindow": 1050000,
+        "maxTokens": 128000
+    },
+    {
+        "id": "xiaomi/mimo-v2-pro",
+        "name": "MiMo V2 Pro",
+        "reasoning": true,
+        "input": [
+            "text"
+        ],
+        "cost": {
+            "input": 1,
+            "output": 3,
+            "cacheRead": 0.19999999999999998,
+            "cacheWrite": 0
+        },
+        "contextWindow": 1000000,
+        "maxTokens": 128000
+    },
+    {
+        "id": "z-ai/glm-4.6v",
+        "name": "Z.ai: GLM 4.6V",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 0.3,
+            "output": 0.9,
+            "cacheRead": 0.049999999999999996,
+            "cacheWrite": 0
+        },
+        "contextWindow": 131072,
+        "maxTokens": 131072
+    },
+    {
+        "id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
+        "name": "NVIDIA: Nemotron 3 Nano Omni (free)",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 0,
+            "output": 0,
+            "cacheRead": 0,
+            "cacheWrite": 0
+        },
+        "contextWindow": 256000,
+        "maxTokens": 65536
+    },
+    {
+        "id": "deepseek/deepseek-v4-flash",
+        "name": "DeepSeek V4 Flash",
+        "reasoning": true,
+        "input": [
+            "text"
+        ],
+        "cost": {
+            "input": 0.14,
+            "output": 0.28,
+            "cacheRead": 0.028,
+            "cacheWrite": 0
+        },
+        "contextWindow": 1000000,
+        "maxTokens": 384000
+    },
+    {
+        "id": "google/gemini-3-pro-image-preview",
+        "name": "Google: Nano Banana Pro (Gemini 3 Pro Image Preview)",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 2,
+            "output": 12,
+            "cacheRead": 0.19999999999999998,
+            "cacheWrite": 0.375
+        },
+        "contextWindow": 65536,
+        "maxTokens": 32768
+    },
+    {
+        "id": "google/gemini-3.1-flash-image-preview",
+        "name": "Gemini 3.1 Flash Image Preview (Nano Banana 2)",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 0.5,
+            "output": 3,
+            "cacheRead": 0,
+            "cacheWrite": 0
+        },
+        "contextWindow": 131072,
+        "maxTokens": 32768
+    },
+    {
+        "id": "openai/gpt-4o-mini",
+        "name": "GPT-4o mini",
+        "reasoning": false,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 0,
+            "output": 0,
+            "cacheRead": 0.075,
+            "cacheWrite": 0
+        },
+        "contextWindow": 128000,
+        "maxTokens": 16384
+    },
+    {
+        "id": "z-ai/glm-4.6",
+        "name": "Z.ai: GLM 4.6",
+        "reasoning": true,
+        "input": [
+            "text"
+        ],
+        "cost": {
+            "input": 0.39,
+            "output": 1.9,
+            "cacheRead": 0.175,
+            "cacheWrite": 0
+        },
+        "contextWindow": 204800,
+        "maxTokens": 204800
+    },
+    {
+        "id": "openai/gpt-5.5",
+        "name": "GPT 5.5",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 5,
+            "output": 30,
+            "cacheRead": 0.5,
+            "cacheWrite": 0
+        },
+        "contextWindow": 1000000,
+        "maxTokens": 128000
+    },
+    {
+        "id": "anthropic/claude-opus-4.6",
+        "name": "Claude Opus 4.6",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 5,
+            "output": 25,
+            "cacheRead": 0.5,
+            "cacheWrite": 6.25
+        },
+        "contextWindow": 1000000,
+        "maxTokens": 128000
+    },
+    {
+        "id": "z-ai/glm-4.7",
+        "name": "Z.ai: GLM 4.7",
+        "reasoning": true,
+        "input": [
+            "text"
+        ],
+        "cost": {
+            "input": 0.38,
+            "output": 1.98,
+            "cacheRead": 0.2,
+            "cacheWrite": 0
+        },
+        "contextWindow": 202752,
+        "maxTokens": 65535
+    },
+    {
+        "id": "x-ai/grok-4.1-fast",
+        "name": "xAI: Grok 4.1 Fast",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 0.2,
+            "output": 0.5,
+            "cacheRead": 0.05,
+            "cacheWrite": 0
+        },
+        "contextWindow": 2000000,
+        "maxTokens": 30000
+    },
+    {
+        "id": "qwen/qwen3-coder-next",
+        "name": "Qwen: Qwen3 Coder Next",
+        "reasoning": false,
+        "input": [
+            "text"
+        ],
+        "cost": {
+            "input": 0.12,
+            "output": 0.75,
+            "cacheRead": 0.035,
+            "cacheWrite": 0
+        },
+        "contextWindow": 262144,
+        "maxTokens": 65536
+    },
+    {
+        "id": "deepseek-v3.2",
+        "name": "DeepSeek-V3.2",
+        "reasoning": true,
+        "input": [
+            "text"
+        ],
+        "cost": {
+            "input": 0.58,
+            "output": 1.68,
+            "cacheRead": 0,
+            "cacheWrite": 0
+        },
+        "contextWindow": 128000,
+        "maxTokens": 128000
+    },
+    {
+        "id": "google/gemini-3.1-pro-preview",
+        "name": "Gemini 3.1 Pro Preview",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 2,
+            "output": 12,
+            "cacheRead": 0.2,
+            "cacheWrite": 0.375
+        },
+        "contextWindow": 1000000,
+        "maxTokens": 64000
+    },
+    {
+        "id": "xiaomi/mimo-v2-flash",
+        "name": "MiMo V2 Flash",
+        "reasoning": true,
+        "input": [
+            "text"
+        ],
+        "cost": {
+            "input": 0.1,
+            "output": 0.29,
+            "cacheRead": 0.045,
+            "cacheWrite": 0
+        },
+        "contextWindow": 262144,
+        "maxTokens": 32000
+    },
+    {
+        "id": "moonshotai/kimi-k2.6",
+        "name": "Kimi K2.6",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 0.95,
+            "output": 4,
+            "cacheRead": 0.16,
+            "cacheWrite": 0
+        },
+        "contextWindow": 262000,
+        "maxTokens": 262000
+    },
+    {
+        "id": "google/gemini-2.5-flash-image",
+        "name": "Nano Banana (Gemini 2.5 Flash Image)",
+        "reasoning": false,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 0.3,
+            "output": 2.5,
+            "cacheRead": 0.03,
+            "cacheWrite": 0.08333333333333334
+        },
+        "contextWindow": 32768,
+        "maxTokens": 32768
+    },
+    {
+        "id": "deepseek-v4-pro",
+        "name": "DeepSeek V4 Pro",
+        "reasoning": true,
+        "input": [
+            "text"
+        ],
+        "cost": {
+            "input": 1.74,
+            "output": 3.48,
+            "cacheRead": 0.145,
+            "cacheWrite": 0
+        },
+        "contextWindow": 1000000,
+        "maxTokens": 384000
+    },
+    {
+        "id": "qwen/qwen3.5-flash",
+        "name": "Qwen3.5 Flash",
+        "reasoning": false,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 0.1,
+            "output": 0.4,
+            "cacheRead": 0,
+            "cacheWrite": 0
+        },
+        "contextWindow": 1020000,
+        "maxTokens": 1020000
+    },
+    {
+        "id": "moonshotai/kimi-k2.5",
+        "name": "Kimi K2.5",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 0.21,
+            "output": 1,
+            "cacheRead": 0.03,
+            "cacheWrite": 0
+        },
+        "contextWindow": 262144,
+        "maxTokens": 262144
+    },
+    {
+        "id": "z-ai/glm-4.5-air",
+        "name": "Z.ai: GLM 4.5 Air",
+        "reasoning": true,
+        "input": [
+            "text"
+        ],
+        "cost": {
+            "input": 0.13,
+            "output": 0.85,
+            "cacheRead": 0.025,
+            "cacheWrite": 0
+        },
+        "contextWindow": 131072,
+        "maxTokens": 98304
+    },
+    {
+        "id": "minimax/minimax-m2.5",
+        "name": "MiniMax M2.5",
+        "reasoning": true,
+        "input": [
+            "text"
+        ],
+        "cost": {
+            "input": 0.14,
+            "output": 0.56,
+            "cacheRead": 0.014,
+            "cacheWrite": 0
+        },
+        "contextWindow": 1000000,
+        "maxTokens": 131072
+    },
+    {
+        "id": "qwen/qwen3.6-plus",
+        "name": "Qwen: Qwen3.6 Plus",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 0.325,
+            "output": 1.95,
+            "cacheRead": 0.0325,
+            "cacheWrite": 0.40625
+        },
+        "contextWindow": 1000000,
+        "maxTokens": 65536
+    },
+    {
+        "id": "xiaomi/mimo-v2-omni",
+        "name": "Xiaomi: MiMo-V2-Omni",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 0.4,
+            "output": 2,
+            "cacheRead": 0.08,
+            "cacheWrite": 0
+        },
+        "contextWindow": 262144,
+        "maxTokens": 65536
+    },
+    {
+        "id": "openai/gpt-5-mini",
+        "name": "GPT-5 Mini",
+        "reasoning": true,
+        "input": [
+            "text",
+            "image"
+        ],
+        "cost": {
+            "input": 0.25,
+            "output": 2,
+            "cacheRead": 0.025,
+            "cacheWrite": 0
+        },
+        "contextWindow": 400000,
+        "maxTokens": 128000
+    },
+    {
+        "id": "nvidia/nemotron-3-super-120b-a12b",
+        "name": "NVIDIA Nemotron 3 Super 120B A12B",
+        "reasoning": true,
+        "input": [
+            "text"
+        ],
+        "cost": {
+            "input": 0.15,
+            "output": 0.65,
+            "cacheRead": 0,
+            "cacheWrite": 0
+        },
+        "contextWindow": 256000,
+        "maxTokens": 32000
+    },
+    {
+        "id": "minimax/minimax-m2-her",
+        "name": "MiniMax: MiniMax M2-her",
+        "reasoning": false,
+        "input": [
+            "text"
+        ],
+        "cost": {
+            "input": 0.3,
+            "output": 1.2,
+            "cacheRead": 0.03,
+            "cacheWrite": 0
+        },
+        "contextWindow": 65536,
+        "maxTokens": 2048
+    },
+    {
+        "id": "minimax/minimax-m2.1",
+        "name": "MiniMax M2.1",
+        "reasoning": true,
+        "input": [
+            "text"
+        ],
+        "cost": {
+            "input": 0.3,
+            "output": 1.2,
+            "cacheRead": 0.03,
+            "cacheWrite": 0.38
+        },
+        "contextWindow": 204800,
+        "maxTokens": 131072
+    },
+    {
+        "id": "minimax/minimax-m2.1-highspeed",
+        "name": "minimax/minimax-m2.1-highspeed",
+        "reasoning": false,
+        "input": [
+            "text"
+        ],
+        "cost": {
+            "input": 0,
+            "output": 0,
+            "cacheRead": 0,
+            "cacheWrite": 0
+        },
+        "contextWindow": 4096,
+        "maxTokens": 4096
+    },
+    {
+        "id": "z-ai/glm-5",
+        "name": "GLM-5",
+        "reasoning": true,
+        "input": [
+            "text"
+        ],
+        "cost": {
+            "input": 0.95,
+            "output": 3.15,
+            "cacheRead": 0.12,
+            "cacheWrite": 0
+        },
+        "contextWindow": 204800,
+        "maxTokens": 131072
+    }
+];

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-tokenrouter",
-  "version": "1.0.4",
+  "version": "1.0.5",
   "description": "TokenRouter provider extension for pi — dynamic model discovery with OpenRouter-compatible pricing",
   "type": "module",
   "license": "MIT",
@@ -19,9 +19,14 @@
   },
   "files": [
     "index.ts",
+    "models.generated.ts",
+    "provider-config.ts",
     "README.md",
     "LICENSE"
   ],
+  "scripts": {
+    "generate-models": "node scripts/generate-models.mjs"
+  },
   "pi": {
     "extensions": [
       "./index.ts"

package/provider-config.ts

@@ -0,0 +1,30 @@
+export const BASE_URL = "https://api.tokenrouter.com/v1";
+export const PROVIDER_NAME = "tokenrouter";
+export const PROVIDER_DISPLAY_NAME = "TokenRouter";
+export const PROVIDER_API_KEY_ENV = "TOKENROUTER_API_KEY";
+
+export type TokenRouterProviderModel = {
+    id: string;
+    name: string;
+    reasoning: boolean;
+    input: ("text" | "image")[];
+    cost: {
+        input: number;
+        output: number;
+        cacheRead: number;
+        cacheWrite: number;
+    };
+    contextWindow: number;
+    maxTokens: number;
+};
+
+export function createTokenRouterProviderConfig(models: TokenRouterProviderModel[]) {
+    return {
+        name: PROVIDER_DISPLAY_NAME,
+        baseUrl: BASE_URL,
+        api: "openai-completions" as const,
+        apiKey: PROVIDER_API_KEY_ENV,
+        authHeader: true,
+        models,
+    };
+}