@oh-my-pi/pi-ai 8.0.20 → 8.2.0

package/README.md

@@ -231,7 +231,7 @@ const bookMeetingTool: Tool = {
 Tool results use content blocks and can include both text and images:
 
 ```typescript
-import { readFileSync } from "fs";
+import * as fs from "node:fs";
 
 const context: Context = {
 	messages: [{ role: "user", content: "What is the weather in London?" }],
@@ -260,7 +260,7 @@ for (const block of response.content) {
 }
 
 // Tool results can also include images (for vision-capable models)
-const imageBuffer = readFileSync("chart.png");
+const imageBuffer = fs.readFileSync("chart.png");
 context.messages.push({
 	role: "toolResult",
 	toolCallId: "tool_xyz",
@@ -379,7 +379,7 @@ All streaming events emitted during assistant message generation:
 Models with vision capabilities can process images. You can check if a model supports images via the `input` property. If you pass images to a non-vision model, they are silently ignored.
 
 ```typescript
-import { readFileSync } from "fs";
+import * as fs from "node:fs";
 import { getModel, complete } from "@oh-my-pi/pi-ai";
 
 const model = getModel("openai", "gpt-4o-mini");
@@ -389,7 +389,7 @@ if (model.input.includes("image")) {
 	console.log("Model supports vision");
 }
 
-const imageBuffer = readFileSync("image.png");
+const imageBuffer = fs.readFileSync("image.png");
 const base64Image = imageBuffer.toString("base64");
 
 const response = await complete(model, {
@@ -551,10 +551,9 @@ The abort signal allows you to cancel in-progress requests. Aborted requests hav
 import { getModel, stream } from "@oh-my-pi/pi-ai";
 
 const model = getModel("openai", "gpt-4o-mini");
-const controller = new AbortController();
 
 // Abort after 2 seconds
-setTimeout(() => controller.abort(), 2000);
+const signal = AbortSignal.timeout(2000);
 
 const s = stream(
 	model,
@@ -562,7 +561,7 @@ const s = stream(
 		messages: [{ role: "user", content: "Write a long story" }],
 	},
 	{
-		signal: controller.signal,
+		signal,
 	},
 );
 
@@ -1022,7 +1021,7 @@ await loginOpenAICodex({
 
 ```typescript
 import { loginGitHubCopilot } from "@oh-my-pi/pi-ai";
-import { writeFileSync } from "fs";
+import * as fs from "node:fs";
 
 const credentials = await loginGitHubCopilot({
 	onAuth: (url, instructions) => {
@@ -1037,7 +1036,7 @@ const credentials = await loginGitHubCopilot({
 
 // Store credentials yourself
 const auth = { "github-copilot": { type: "oauth", ...credentials } };
-writeFileSync("auth.json", JSON.stringify(auth, null, 2));
+fs.writeFileSync("auth.json", JSON.stringify(auth, null, 2));
 ```
 
 ### Using OAuth Tokens
@@ -1046,10 +1045,10 @@ Use `getOAuthApiKey()` to get an API key, automatically refreshing if expired:
 
 ```typescript
 import { getModel, complete, getOAuthApiKey } from "@oh-my-pi/pi-ai";
-import { readFileSync, writeFileSync } from "fs";
+import * as fs from "node:fs";
 
 // Load your stored credentials
-const auth = JSON.parse(readFileSync("auth.json", "utf-8"));
+const auth = JSON.parse(fs.readFileSync("auth.json", "utf-8"));
 
 // Get API key (refreshes if expired)
 const result = await getOAuthApiKey("github-copilot", auth);
@@ -1057,7 +1056,7 @@ if (!result) throw new Error("Not logged in");
 
 // Save refreshed credentials
 auth["github-copilot"] = { type: "oauth", ...result.newCredentials };
-writeFileSync("auth.json", JSON.stringify(auth, null, 2));
+fs.writeFileSync("auth.json", JSON.stringify(auth, null, 2));
 
 // Use the API key
 const model = getModel("github-copilot", "gpt-4o");

package/package.json

@@ -1,38 +1,75 @@
 {
 	"name": "@oh-my-pi/pi-ai",
-	"version": "8.0.20",
+	"version": "8.2.0",
 	"description": "Unified LLM API with automatic model discovery and provider configuration",
 	"type": "module",
 	"main": "./src/index.ts",
 	"types": "./src/index.ts",
+	"exports": {
+		".": {
+			"types": "./src/index.ts",
+			"import": "./src/index.ts"
+		},
+		"./models": {
+			"types": "./src/models.ts",
+			"import": "./src/models.ts"
+		},
+		"./models.generated": {
+			"types": "./src/models.generated.ts",
+			"import": "./src/models.generated.ts"
+		},
+		"./stream": {
+			"types": "./src/stream.ts",
+			"import": "./src/stream.ts"
+		},
+		"./types": {
+			"types": "./src/types.ts",
+			"import": "./src/types.ts"
+		},
+		"./usage": {
+			"types": "./src/usage.ts",
+			"import": "./src/usage.ts"
+		},
+		"./storage": {
+			"types": "./src/storage.ts",
+			"import": "./src/storage.ts"
+		},
+		"./providers/*": {
+			"types": "./src/providers/*.ts",
+			"import": "./src/providers/*.ts"
+		},
+		"./utils/*": {
+			"types": "./src/utils/*.ts",
+			"import": "./src/utils/*.ts"
+		}
+	},
 	"bin": {
 		"pi-ai": "./src/cli.ts"
 	},
 	"files": [
 		"src",
-		"README.md",
-		"tsconfig.json"
+		"README.md"
 	],
 	"scripts": {
+		"check": "tsgo -p tsconfig.json",
 		"generate-models": "bun scripts/generate-models.ts",
-		"test": "bun test",
-		"prepublishOnly": "cp tsconfig.publish.json tsconfig.json"
+		"test": "bun test"
 	},
 	"dependencies": {
-		"@oh-my-pi/pi-utils": "8.0.20",
-		"@anthropic-ai/sdk": "0.71.2",
-		"@aws-sdk/client-bedrock-runtime": "^3.968.0",
+		"@oh-my-pi/pi-utils": "8.2.0",
+		"@anthropic-ai/sdk": "^0.71.2",
+		"@aws-sdk/client-bedrock-runtime": "^3.975.0",
 		"@bufbuild/protobuf": "^2.10.2",
 		"@connectrpc/connect": "^2.1.1",
 		"@connectrpc/connect-node": "^2.1.1",
-		"@google/genai": "1.34.0",
-		"@mistralai/mistralai": "1.10.0",
+		"@google/genai": "^1.38.0",
+		"@mistralai/mistralai": "^1.13.0",
 		"@sinclair/typebox": "^0.34.41",
 		"ajv": "^8.17.1",
 		"ajv-formats": "^3.0.1",
 		"chalk": "^5.6.2",
 		"json5": "^2.2.3",
-		"openai": "6.10.0",
+		"openai": "^6.16.0",
 		"partial-json": "^0.1.7",
 		"zod-to-json-schema": "^3.24.6"
 	},
@@ -56,20 +93,6 @@
 		"bun": ">=1.0.0"
 	},
 	"devDependencies": {
-		"@types/node": "^24.3.0"
-	},
-	"exports": {
-		".": {
-			"types": "./src/index.ts",
-			"import": "./src/index.ts"
-		},
-		"./utils/*": {
-			"types": "./src/utils/*.ts",
-			"import": "./src/utils/*.ts"
-		},
-		"./*": {
-			"types": "./src/*",
-			"import": "./src/*"
-		}
+		"@types/node": "^25.0.10"
 	}
 }

package/src/cli.ts

@@ -2,12 +2,12 @@
 import { createInterface } from "readline";
 import { CliAuthStorage } from "./storage";
 import "./utils/migrate-env";
+import { getOAuthProviders } from "./utils/oauth";
 import { loginAnthropic } from "./utils/oauth/anthropic";
 import { loginCursor } from "./utils/oauth/cursor";
 import { loginGitHubCopilot } from "./utils/oauth/github-copilot";
 import { loginAntigravity } from "./utils/oauth/google-antigravity";
 import { loginGeminiCli } from "./utils/oauth/google-gemini-cli";
-import { getOAuthProviders } from "./utils/oauth/index";
 import { loginOpenAICodex } from "./utils/oauth/openai-codex";
 import type { OAuthCredentials, OAuthProvider } from "./utils/oauth/types";
 
@@ -23,7 +23,7 @@ async function login(provider: OAuthProvider): Promise<void> {
 	const rl = createInterface({ input: process.stdin, output: process.stdout });
 
 	const promptFn = (msg: string) => prompt(rl, `${msg} `);
-	const storage = new CliAuthStorage();
+	const storage = await CliAuthStorage.create();
 
 	try {
 		let credentials: OAuthCredentials;
@@ -91,7 +91,7 @@ async function login(provider: OAuthProvider): Promise<void> {
 
 			case "cursor":
 				credentials = await loginCursor(
-					(url) => {
+					url => {
 						console.log(`\nOpen this URL in your browser:\n${url}\n`);
 					},
 					() => {
@@ -145,7 +145,7 @@ Examples:
 	}
 
 	if (command === "status") {
-		const storage = new CliAuthStorage();
+		const storage = await CliAuthStorage.create();
 		try {
 			const providers = storage.listProviders();
 			if (providers.length === 0) {
@@ -179,7 +179,7 @@ Examples:
 
 	if (command === "logout") {
 		let provider = args[1] as OAuthProvider | undefined;
-		const storage = new CliAuthStorage();
+		const storage = await CliAuthStorage.create();
 
 		try {
 			if (!provider) {
@@ -243,7 +243,7 @@ Examples:
 			provider = PROVIDERS[index].id;
 		}
 
-		if (!PROVIDERS.some((p) => p.id === provider)) {
+		if (!PROVIDERS.some(p => p.id === provider)) {
 			console.error(`Unknown provider: ${provider}`);
 			console.error(`Use 'bunx @oh-my-pi/pi-ai list' to see available providers`);
 			process.exit(1);
@@ -259,7 +259,7 @@ Examples:
 	process.exit(1);
 }
 
-main().catch((err) => {
+main().catch(err => {
 	console.error("Error:", err.message);
 	process.exit(1);
 });

package/src/index.ts

@@ -18,7 +18,8 @@ export * from "./usage/google-antigravity";
 export * from "./usage/openai-codex";
 export * from "./usage/zai";
 export * from "./utils/event-stream";
-export * from "./utils/oauth/index";
+export * from "./utils/oauth";
 export * from "./utils/overflow";
+export * from "./utils/retry";
 export * from "./utils/typebox-helpers";
 export * from "./utils/validation";

package/src/models.generated.ts

@@ -1726,7 +1726,7 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
+			contextWindow: 64000,
 			maxTokens: 16384,
 		} satisfies Model<"openai-completions">,
 		"gpt-4o": {
@@ -1766,24 +1766,6 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 128000,
 		} satisfies Model<"openai-responses">,
-		"gpt-5-codex": {
-			id: "gpt-5-codex",
-			name: "GPT-5-Codex",
-			api: "openai-responses",
-			provider: "github-copilot",
-			baseUrl: "https://api.individual.githubcopilot.com",
-			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-responses">,
 		"gpt-5-mini": {
 			id: "gpt-5-mini",
 			name: "GPT-5-mini",
@@ -3641,7 +3623,7 @@ export const MODELS = {
 			cost: {
 				input: 1.25,
 				output: 10,
-				cacheRead: 0.13,
+				cacheRead: 0.125,
 				cacheWrite: 0,
 			},
 			contextWindow: 400000,
@@ -3692,7 +3674,7 @@ export const MODELS = {
 			cost: {
 				input: 0.25,
 				output: 2,
-				cacheRead: 0.03,
+				cacheRead: 0.025,
 				cacheWrite: 0,
 			},
 			contextWindow: 400000,
@@ -3709,7 +3691,7 @@ export const MODELS = {
 			cost: {
 				input: 0.05,
 				output: 0.4,
-				cacheRead: 0.01,
+				cacheRead: 0.005,
 				cacheWrite: 0,
 			},
 			contextWindow: 400000,
@@ -4314,6 +4296,23 @@ export const MODELS = {
 			contextWindow: 204800,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
+		"glm-4.7": {
+			id: "glm-4.7",
+			name: "GLM-4.7",
+			api: "openai-completions",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.6,
+				output: 2.2,
+				cacheRead: 0.1,
+				cacheWrite: 0,
+			},
+			contextWindow: 204800,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
 		"glm-4.7-free": {
 			id: "glm-4.7-free",
 			name: "GLM-4.7",
@@ -4615,7 +4614,7 @@ export const MODELS = {
 			input: ["text"],
 			cost: {
 				input: 0.09,
-				output: 0.39999999999999997,
+				output: 0.44999999999999996,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -5028,7 +5027,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
-			maxTokens: 16384,
+			maxTokens: 32768,
 		} satisfies Model<"openai-completions">,
 		"cohere/command-r-08-2024": {
 			id: "cohere/command-r-08-2024",
@@ -5297,7 +5296,7 @@ export const MODELS = {
 				input: 0.09999999999999999,
 				output: 0.39999999999999997,
 				cacheRead: 0.024999999999999998,
-				cacheWrite: 0.0833,
+				cacheWrite: 0.08333333333333333,
 			},
 			contextWindow: 1048576,
 			maxTokens: 8192,
@@ -5311,10 +5310,10 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text", "image"],
 			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
+				input: 0.09999999999999999,
+				output: 0.39999999999999997,
+				cacheRead: 0.024999999999999998,
+				cacheWrite: 0.08333333333333333,
 			},
 			contextWindow: 1048576,
 			maxTokens: 8192,
@@ -5348,7 +5347,7 @@ export const MODELS = {
 				input: 0.3,
 				output: 2.5,
 				cacheRead: 0.03,
-				cacheWrite: 0.08333333333333334,
+				cacheWrite: 0.08333333333333333,
 			},
 			contextWindow: 1048576,
 			maxTokens: 65535,
@@ -5365,7 +5364,7 @@ export const MODELS = {
 				input: 0.09999999999999999,
 				output: 0.39999999999999997,
 				cacheRead: 0.01,
-				cacheWrite: 0.0833,
+				cacheWrite: 0.08333333333333333,
 			},
 			contextWindow: 1048576,
 			maxTokens: 65535,
@@ -5382,10 +5381,10 @@ export const MODELS = {
 				input: 0.09999999999999999,
 				output: 0.39999999999999997,
 				cacheRead: 0.01,
-				cacheWrite: 0.0833,
+				cacheWrite: 0.08333333333333333,
 			},
 			contextWindow: 1048576,
-			maxTokens: 65536,
+			maxTokens: 65535,
 		} satisfies Model<"openai-completions">,
 		"google/gemini-2.5-flash-preview-09-2025": {
 			id: "google/gemini-2.5-flash-preview-09-2025",
@@ -5398,8 +5397,8 @@ export const MODELS = {
 			cost: {
 				input: 0.3,
 				output: 2.5,
-				cacheRead: 0.075,
-				cacheWrite: 0.0833,
+				cacheRead: 0.03,
+				cacheWrite: 0.08333333333333333,
 			},
 			contextWindow: 1048576,
 			maxTokens: 65535,
@@ -5432,7 +5431,7 @@ export const MODELS = {
 			cost: {
 				input: 1.25,
 				output: 10,
-				cacheRead: 0.31,
+				cacheRead: 0.125,
 				cacheWrite: 0.375,
 			},
 			contextWindow: 1048576,
@@ -5449,7 +5448,7 @@ export const MODELS = {
 			cost: {
 				input: 1.25,
 				output: 10,
-				cacheRead: 0.31,
+				cacheRead: 0.125,
 				cacheWrite: 0.375,
 			},
 			contextWindow: 1048576,
@@ -5467,7 +5466,7 @@ export const MODELS = {
 				input: 0.5,
 				output: 3,
 				cacheRead: 0.049999999999999996,
-				cacheWrite: 0,
+				cacheWrite: 0.08333333333333333,
 			},
 			contextWindow: 1048576,
 			maxTokens: 65535,
@@ -5754,12 +5753,12 @@ export const MODELS = {
 			input: ["text"],
 			cost: {
 				input: 0.27,
-				output: 1.12,
+				output: 1.1,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 196608,
-			maxTokens: 65536,
+			maxTokens: 196608,
 		} satisfies Model<"openai-completions">,
 		"mistralai/codestral-2508": {
 			id: "mistralai/codestral-2508",
@@ -6048,7 +6047,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
-			maxTokens: 131072,
+			maxTokens: 16384,
 		} satisfies Model<"openai-completions">,
 		"mistralai/mistral-saba": {
 			id: "mistralai/mistral-saba",
@@ -7869,6 +7868,23 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
+		"qwen/qwen3-vl-235b-a22b-thinking": {
+			id: "qwen/qwen3-vl-235b-a22b-thinking",
+			name: "Qwen: Qwen3 VL 235B A22B Thinking",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.44999999999999996,
+				output: 3.5,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
 		"qwen/qwen3-vl-30b-a3b-instruct": {
 			id: "qwen/qwen3-vl-30b-a3b-instruct",
 			name: "Qwen: Qwen3 VL 30B A3B Instruct",
@@ -8430,6 +8446,23 @@ export const MODELS = {
 			contextWindow: 202752,
 			maxTokens: 65535,
 		} satisfies Model<"openai-completions">,
+		"z-ai/glm-4.7-flash": {
+			id: "z-ai/glm-4.7-flash",
+			name: "Z.AI: GLM 4.7 Flash",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.07,
+				output: 0.39999999999999997,
+				cacheRead: 0.01,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
 	},
 	"vercel-ai-gateway": {
 		"alibaba/qwen-3-14b": {
@@ -8562,7 +8595,7 @@ export const MODELS = {
 			cost: {
 				input: 1,
 				output: 5,
-				cacheRead: 0,
+				cacheRead: 0.19999999999999998,
 				cacheWrite: 0,
 			},
 			contextWindow: 1000000,
@@ -8619,23 +8652,6 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 4096,
 		} satisfies Model<"anthropic-messages">,
-		"anthropic/claude-3-opus": {
-			id: "anthropic/claude-3-opus",
-			name: "Claude 3 Opus",
-			api: "anthropic-messages",
-			provider: "vercel-ai-gateway",
-			baseUrl: "https://ai-gateway.vercel.sh",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 15,
-				output: 75,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 8192,
-		} satisfies Model<"anthropic-messages">,
 		"anthropic/claude-3.5-haiku": {
 			id: "anthropic/claude-3.5-haiku",
 			name: "Claude 3.5 Haiku",
@@ -8786,7 +8802,7 @@ export const MODELS = {
 				cacheRead: 0.3,
 				cacheWrite: 3.75,
 			},
-			contextWindow: 200000,
+			contextWindow: 1000000,
 			maxTokens: 64000,
 		} satisfies Model<"anthropic-messages">,
 		"anthropic/claude-sonnet-4.5": {
@@ -8803,7 +8819,7 @@ export const MODELS = {
 				cacheRead: 0.3,
 				cacheWrite: 3.75,
 			},
-			contextWindow: 200000,
+			contextWindow: 1000000,
 			maxTokens: 64000,
 		} satisfies Model<"anthropic-messages">,
 		"bytedance/seed-1.6": {
@@ -8925,40 +8941,6 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 64000,
 		} satisfies Model<"anthropic-messages">,
-		"google/gemini-2.0-flash": {
-			id: "google/gemini-2.0-flash",
-			name: "Gemini 2.0 Flash",
-			api: "anthropic-messages",
-			provider: "vercel-ai-gateway",
-			baseUrl: "https://ai-gateway.vercel.sh",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.09999999999999999,
-				output: 0.39999999999999997,
-				cacheRead: 0.024999999999999998,
-				cacheWrite: 0,
-			},
-			contextWindow: 1000000,
-			maxTokens: 8192,
-		} satisfies Model<"anthropic-messages">,
-		"google/gemini-2.0-flash-lite": {
-			id: "google/gemini-2.0-flash-lite",
-			name: "Gemini 2.0 Flash Lite",
-			api: "anthropic-messages",
-			provider: "vercel-ai-gateway",
-			baseUrl: "https://ai-gateway.vercel.sh",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.075,
-				output: 0.3,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 8192,
-		} satisfies Model<"anthropic-messages">,
 		"google/gemini-2.5-flash": {
 			id: "google/gemini-2.5-flash",
 			name: "Gemini 2.5 Flash",
@@ -8966,15 +8948,15 @@ export const MODELS = {
 			provider: "vercel-ai-gateway",
 			baseUrl: "https://ai-gateway.vercel.sh",
 			reasoning: true,
-			input: ["text", "image"],
+			input: ["text"],
 			cost: {
 				input: 0.3,
 				output: 2.5,
-				cacheRead: 0.03,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 1000000,
-			maxTokens: 64000,
+			maxTokens: 65536,
 		} satisfies Model<"anthropic-messages">,
 		"google/gemini-2.5-flash-lite": {
 			id: "google/gemini-2.5-flash-lite",
@@ -9034,11 +9016,11 @@ export const MODELS = {
 			provider: "vercel-ai-gateway",
 			baseUrl: "https://ai-gateway.vercel.sh",
 			reasoning: true,
-			input: ["text", "image"],
+			input: ["text"],
 			cost: {
 				input: 1.25,
 				output: 10,
-				cacheRead: 0.125,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 1048576,
@@ -10449,7 +10431,7 @@ export const MODELS = {
 			cost: {
 				input: 0.19999999999999998,
 				output: 1.1,
-				cacheRead: 0,
+				cacheRead: 0.03,
 				cacheWrite: 0,
 			},
 			contextWindow: 128000,
@@ -10540,6 +10522,23 @@ export const MODELS = {
 			contextWindow: 202752,
 			maxTokens: 120000,
 		} satisfies Model<"anthropic-messages">,
+		"zai/glm-4.7-flashx": {
+			id: "zai/glm-4.7-flashx",
+			name: "GLM 4.7 FlashX",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.06,
+				output: 0.39999999999999997,
+				cacheRead: 0.01,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 128000,
+		} satisfies Model<"anthropic-messages">,
 	},
 	"xai": {
 		"grok-2": {