diff --git a/packages/pi-ai/scripts/generate-models.ts b/packages/pi-ai/scripts/generate-models.ts
new file mode 100644
index 000000000..839428bcb
--- /dev/null
+++ b/packages/pi-ai/scripts/generate-models.ts
@@ -0,0 +1,1543 @@
+#!/usr/bin/env tsx
+
+import { writeFileSync } from "fs";
+import { join, dirname } from "path";
+import { fileURLToPath } from "url";
+import { Api, KnownProvider, Model } from "../src/types.js";
+
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = dirname(__filename);
+const packageRoot = join(__dirname, "..");
+
+interface ModelsDevModel {
+	id: string;
+	name: string;
+	tool_call?: boolean;
+	reasoning?: boolean;
+	limit?: {
+		context?: number;
+		output?: number;
+	};
+	cost?: {
+		input?: number;
+		output?: number;
+		cache_read?: number;
+		cache_write?: number;
+	};
+	modalities?: {
+		input?: string[];
+	};
+	provider?: {
+		npm?: string;
+	};
+}
+
+interface AiGatewayModel {
+	id: string;
+	name?: string;
+	context_window?: number;
+	max_tokens?: number;
+	tags?: string[];
+	pricing?: {
+		input?: string | number;
+		output?: string | number;
+		input_cache_read?: string | number;
+		input_cache_write?: string | number;
+	};
+}
+
+const COPILOT_STATIC_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",
+} as const;
+
+const AI_GATEWAY_MODELS_URL = "https://ai-gateway.vercel.sh/v1";
+const AI_GATEWAY_BASE_URL = "https://ai-gateway.vercel.sh";
+
+async function fetchOpenRouterModels(): Promise<Model<any>[]> {
+	try {
+		console.log("Fetching models from OpenRouter API...");
+		const response = await fetch("https://openrouter.ai/api/v1/models");
+		const data = await response.json();
+
+		const models: Model<any>[] = [];
+
+		for (const model of data.data) {
+			// Only include models that support tools
+			if (!model.supported_parameters?.includes("tools")) continue;
+
+			// Parse provider from model ID
+			let provider: KnownProvider = "openrouter";
+			let modelKey = model.id;
+
+			modelKey = model.id; // Keep full ID for OpenRouter
+
+			// Parse input modalities
+			const input: ("text" | "image")[] = ["text"];
+			if (model.architecture?.modality?.includes("image")) {
+				input.push("image");
+			}
+
+			// Convert pricing from $/token to $/million tokens
+			const inputCost = parseFloat(model.pricing?.prompt || "0") * 1_000_000;
+			const outputCost = parseFloat(model.pricing?.completion || "0") * 1_000_000;
+			const cacheReadCost = parseFloat(model.pricing?.input_cache_read || "0") * 1_000_000;
+			const cacheWriteCost = parseFloat(model.pricing?.input_cache_write || "0") * 1_000_000;
+
+			const normalizedModel: Model<any> = {
+				id: modelKey,
+				name: model.name,
+				api: "openai-completions",
+				baseUrl: "https://openrouter.ai/api/v1",
+				provider,
+				reasoning: model.supported_parameters?.includes("reasoning") || false,
+				input,
+				cost: {
+					input: inputCost,
+					output: outputCost,
+					cacheRead: cacheReadCost,
+					cacheWrite: cacheWriteCost,
+				},
+				contextWindow: model.context_length || 4096,
+				maxTokens: model.top_provider?.max_completion_tokens || 4096,
+			};
+			models.push(normalizedModel);
+		}
+
+		console.log(`Fetched ${models.length} tool-capable models from OpenRouter`);
+		return models;
+	} catch (error) {
+		console.error("Failed to fetch OpenRouter models:", error);
+		return [];
+	}
+}
+
+async function fetchAiGatewayModels(): Promise<Model<any>[]> {
+	try {
+		console.log("Fetching models from Vercel AI Gateway API...");
+		const response = await fetch(`${AI_GATEWAY_MODELS_URL}/models`);
+		const data = await response.json();
+		const models: Model<any>[] = [];
+
+		const toNumber = (value: string | number | undefined): number => {
+			if (typeof value === "number") {
+				return Number.isFinite(value) ? value : 0;
+			}
+			const parsed = parseFloat(value ?? "0");
+			return Number.isFinite(parsed) ? parsed : 0;
+		};
+
+		const items = Array.isArray(data.data) ? (data.data as AiGatewayModel[]) : [];
+		for (const model of items) {
+			const tags = Array.isArray(model.tags) ? model.tags : [];
+			// Only include models that support tools
+			if (!tags.includes("tool-use")) continue;
+
+			const input: ("text" | "image")[] = ["text"];
+			if (tags.includes("vision")) {
+				input.push("image");
+			}
+
+			const inputCost = toNumber(model.pricing?.input) * 1_000_000;
+			const outputCost = toNumber(model.pricing?.output) * 1_000_000;
+			const cacheReadCost = toNumber(model.pricing?.input_cache_read) * 1_000_000;
+			const cacheWriteCost = toNumber(model.pricing?.input_cache_write) * 1_000_000;
+
+			models.push({
+				id: model.id,
+				name: model.name || model.id,
+				api: "anthropic-messages",
+				baseUrl: AI_GATEWAY_BASE_URL,
+				provider: "vercel-ai-gateway",
+				reasoning: tags.includes("reasoning"),
+				input,
+				cost: {
+					input: inputCost,
+					output: outputCost,
+					cacheRead: cacheReadCost,
+					cacheWrite: cacheWriteCost,
+				},
+				contextWindow: model.context_window || 4096,
+				maxTokens: model.max_tokens || 4096,
+			});
+		}
+
+		console.log(`Fetched ${models.length} tool-capable models from Vercel AI Gateway`);
+		return models;
+	} catch (error) {
+		console.error("Failed to fetch Vercel AI Gateway models:", error);
+		return [];
+	}
+}
+
+async function loadModelsDevData(): Promise<Model<any>[]> {
+	try {
+		console.log("Fetching models from models.dev API...");
+		const response = await fetch("https://models.dev/api.json");
+		const data = await response.json();
+
+		const models: Model<any>[] = [];
+
+		// Process Amazon Bedrock models
+		if (data["amazon-bedrock"]?.models) {
+			for (const [modelId, model] of Object.entries(data["amazon-bedrock"].models)) {
+				const m = model as ModelsDevModel;
+				if (m.tool_call !== true) continue;
+
+				let id = modelId;
+
+				if (id.startsWith("ai21.jamba")) {
+					// These models doesn't support tool use in streaming mode
+					continue;
+				}
+
+				if (id.startsWith("mistral.mistral-7b-instruct-v0")) {
+					// These models doesn't support system messages
+					continue;
+				}
+
+				models.push({
+					id,
+					name: m.name || id,
+					api: "bedrock-converse-stream" as const,
+					provider: "amazon-bedrock" as const,
+					baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+					reasoning: m.reasoning === true,
+					input: (m.modalities?.input?.includes("image") ? ["text", "image"] : ["text"]) as ("text" | "image")[],
+					cost: {
+						input: m.cost?.input || 0,
+						output: m.cost?.output || 0,
+						cacheRead: m.cost?.cache_read || 0,
+						cacheWrite: m.cost?.cache_write || 0,
+					},
+					contextWindow: m.limit?.context || 4096,
+					maxTokens: m.limit?.output || 4096,
+				});
+			}
+		}
+
+		// Process Anthropic models
+		if (data.anthropic?.models) {
+			for (const [modelId, model] of Object.entries(data.anthropic.models)) {
+				const m = model as ModelsDevModel;
+				if (m.tool_call !== true) continue;
+
+				models.push({
+					id: modelId,
+					name: m.name || modelId,
+					api: "anthropic-messages",
+					provider: "anthropic",
+					baseUrl: "https://api.anthropic.com",
+					reasoning: m.reasoning === true,
+					input: m.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
+					cost: {
+						input: m.cost?.input || 0,
+						output: m.cost?.output || 0,
+						cacheRead: m.cost?.cache_read || 0,
+						cacheWrite: m.cost?.cache_write || 0,
+					},
+					contextWindow: m.limit?.context || 4096,
+					maxTokens: m.limit?.output || 4096,
+				});
+			}
+		}
+
+		// Process Google models
+		if (data.google?.models) {
+			for (const [modelId, model] of Object.entries(data.google.models)) {
+				const m = model as ModelsDevModel;
+				if (m.tool_call !== true) continue;
+
+				models.push({
+					id: modelId,
+					name: m.name || modelId,
+					api: "google-generative-ai",
+					provider: "google",
+					baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+					reasoning: m.reasoning === true,
+					input: m.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
+					cost: {
+						input: m.cost?.input || 0,
+						output: m.cost?.output || 0,
+						cacheRead: m.cost?.cache_read || 0,
+						cacheWrite: m.cost?.cache_write || 0,
+					},
+					contextWindow: m.limit?.context || 4096,
+					maxTokens: m.limit?.output || 4096,
+				});
+			}
+		}
+
+		// Process OpenAI models
+		if (data.openai?.models) {
+			for (const [modelId, model] of Object.entries(data.openai.models)) {
+				const m = model as ModelsDevModel;
+				if (m.tool_call !== true) continue;
+
+				models.push({
+					id: modelId,
+					name: m.name || modelId,
+					api: "openai-responses",
+					provider: "openai",
+					baseUrl: "https://api.openai.com/v1",
+					reasoning: m.reasoning === true,
+					input: m.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
+					cost: {
+						input: m.cost?.input || 0,
+						output: m.cost?.output || 0,
+						cacheRead: m.cost?.cache_read || 0,
+						cacheWrite: m.cost?.cache_write || 0,
+					},
+					contextWindow: m.limit?.context || 4096,
+					maxTokens: m.limit?.output || 4096,
+				});
+			}
+		}
+
+		// Process Groq models
+		if (data.groq?.models) {
+			for (const [modelId, model] of Object.entries(data.groq.models)) {
+				const m = model as ModelsDevModel;
+				if (m.tool_call !== true) continue;
+
+				models.push({
+					id: modelId,
+					name: m.name || modelId,
+					api: "openai-completions",
+					provider: "groq",
+					baseUrl: "https://api.groq.com/openai/v1",
+					reasoning: m.reasoning === true,
+					input: m.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
+					cost: {
+						input: m.cost?.input || 0,
+						output: m.cost?.output || 0,
+						cacheRead: m.cost?.cache_read || 0,
+						cacheWrite: m.cost?.cache_write || 0,
+					},
+					contextWindow: m.limit?.context || 4096,
+					maxTokens: m.limit?.output || 4096,
+				});
+			}
+		}
+
+		// Process Cerebras models
+		if (data.cerebras?.models) {
+			for (const [modelId, model] of Object.entries(data.cerebras.models)) {
+				const m = model as ModelsDevModel;
+				if (m.tool_call !== true) continue;
+
+				models.push({
+					id: modelId,
+					name: m.name || modelId,
+					api: "openai-completions",
+					provider: "cerebras",
+					baseUrl: "https://api.cerebras.ai/v1",
+					reasoning: m.reasoning === true,
+					input: m.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
+					cost: {
+						input: m.cost?.input || 0,
+						output: m.cost?.output || 0,
+						cacheRead: m.cost?.cache_read || 0,
+						cacheWrite: m.cost?.cache_write || 0,
+					},
+					contextWindow: m.limit?.context || 4096,
+					maxTokens: m.limit?.output || 4096,
+				});
+			}
+		}
+
+		// Process xAi models
+		if (data.xai?.models) {
+			for (const [modelId, model] of Object.entries(data.xai.models)) {
+				const m = model as ModelsDevModel;
+				if (m.tool_call !== true) continue;
+
+				models.push({
+					id: modelId,
+					name: m.name || modelId,
+					api: "openai-completions",
+					provider: "xai",
+					baseUrl: "https://api.x.ai/v1",
+					reasoning: m.reasoning === true,
+					input: m.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
+					cost: {
+						input: m.cost?.input || 0,
+						output: m.cost?.output || 0,
+						cacheRead: m.cost?.cache_read || 0,
+						cacheWrite: m.cost?.cache_write || 0,
+					},
+					contextWindow: m.limit?.context || 4096,
+					maxTokens: m.limit?.output || 4096,
+				});
+			}
+		}
+
+		// Process zAi models
+		if (data.zai?.models) {
+			for (const [modelId, model] of Object.entries(data.zai.models)) {
+				const m = model as ModelsDevModel;
+				if (m.tool_call !== true) continue;
+				const supportsImage = m.modalities?.input?.includes("image")
+
+				models.push({
+				id: modelId,
+				name: m.name || modelId,
+				api: "openai-completions",
+				provider: "zai",
+				baseUrl: "https://api.z.ai/api/coding/paas/v4",
+				reasoning: m.reasoning === true,
+				input: supportsImage ? ["text", "image"] : ["text"],
+				cost: {
+					input: m.cost?.input || 0,
+					output: m.cost?.output || 0,
+					cacheRead: m.cost?.cache_read || 0,
+					cacheWrite: m.cost?.cache_write || 0,
+				},
+				compat: {
+					supportsDeveloperRole: false,
+					thinkingFormat: "zai",
+				},
+				contextWindow: m.limit?.context || 4096,
+				maxTokens: m.limit?.output || 4096,
+				});
+			}
+		}
+
+		// Process Mistral models
+		if (data.mistral?.models) {
+			for (const [modelId, model] of Object.entries(data.mistral.models)) {
+				const m = model as ModelsDevModel;
+				if (m.tool_call !== true) continue;
+
+				models.push({
+					id: modelId,
+					name: m.name || modelId,
+					api: "mistral-conversations",
+					provider: "mistral",
+					baseUrl: "https://api.mistral.ai",
+					reasoning: m.reasoning === true,
+					input: m.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
+					cost: {
+						input: m.cost?.input || 0,
+						output: m.cost?.output || 0,
+						cacheRead: m.cost?.cache_read || 0,
+						cacheWrite: m.cost?.cache_write || 0,
+					},
+					contextWindow: m.limit?.context || 4096,
+					maxTokens: m.limit?.output || 4096,
+				});
+			}
+		}
+
+		// Process Hugging Face models
+		if (data.huggingface?.models) {
+			for (const [modelId, model] of Object.entries(data.huggingface.models)) {
+				const m = model as ModelsDevModel;
+				if (m.tool_call !== true) continue;
+
+				models.push({
+					id: modelId,
+					name: m.name || modelId,
+					api: "openai-completions",
+					provider: "huggingface",
+					baseUrl: "https://router.huggingface.co/v1",
+					reasoning: m.reasoning === true,
+					input: m.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
+					cost: {
+						input: m.cost?.input || 0,
+						output: m.cost?.output || 0,
+						cacheRead: m.cost?.cache_read || 0,
+						cacheWrite: m.cost?.cache_write || 0,
+					},
+					compat: {
+						supportsDeveloperRole: false,
+					},
+					contextWindow: m.limit?.context || 4096,
+					maxTokens: m.limit?.output || 4096,
+				});
+			}
+		}
+
+		// Process OpenCode models (Zen and Go)
+		// API mapping based on provider.npm field:
+		// - @ai-sdk/openai → openai-responses
+		// - @ai-sdk/anthropic → anthropic-messages
+		// - @ai-sdk/google → google-generative-ai
+		// - null/undefined/@ai-sdk/openai-compatible → openai-completions
+		const opencodeVariants = [
+			{ key: "opencode", provider: "opencode", basePath: "https://opencode.ai/zen" },
+			{ key: "opencode-go", provider: "opencode-go", basePath: "https://opencode.ai/zen/go" },
+		] as const;
+
+		for (const variant of opencodeVariants) {
+			if (!data[variant.key]?.models) continue;
+
+			for (const [modelId, model] of Object.entries(data[variant.key].models)) {
+				const m = model as ModelsDevModel & { status?: string };
+				if (m.tool_call !== true) continue;
+				if (m.status === "deprecated") continue;
+
+				const npm = m.provider?.npm;
+				let api: Api;
+				let baseUrl: string;
+
+				if (npm === "@ai-sdk/openai") {
+					api = "openai-responses";
+					baseUrl = `${variant.basePath}/v1`;
+				} else if (npm === "@ai-sdk/anthropic") {
+					api = "anthropic-messages";
+					// Anthropic SDK appends /v1/messages to baseURL
+					baseUrl = variant.basePath;
+				} else if (npm === "@ai-sdk/google") {
+					api = "google-generative-ai";
+					baseUrl = `${variant.basePath}/v1`;
+				} else {
+					// null, undefined, or @ai-sdk/openai-compatible
+					api = "openai-completions";
+					baseUrl = `${variant.basePath}/v1`;
+				}
+
+				models.push({
+					id: modelId,
+					name: m.name || modelId,
+					api,
+					provider: variant.provider,
+					baseUrl,
+					reasoning: m.reasoning === true,
+					input: m.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
+					cost: {
+						input: m.cost?.input || 0,
+						output: m.cost?.output || 0,
+						cacheRead: m.cost?.cache_read || 0,
+						cacheWrite: m.cost?.cache_write || 0,
+					},
+					contextWindow: m.limit?.context || 4096,
+					maxTokens: m.limit?.output || 4096,
+				});
+			}
+		}
+
+		// Process GitHub Copilot models
+		if (data["github-copilot"]?.models) {
+			for (const [modelId, model] of Object.entries(data["github-copilot"].models)) {
+				const m = model as ModelsDevModel & { status?: string };
+				if (m.tool_call !== true) continue;
+				if (m.status === "deprecated") continue;
+
+				// Claude 4.x models route to Anthropic Messages API
+				const isCopilotClaude4 = /^claude-(haiku|sonnet|opus)-4([.\-]|$)/.test(modelId);
+				// gpt-5 models require responses API, others use completions
+				const needsResponsesApi = modelId.startsWith("gpt-5") || modelId.startsWith("oswe");
+
+				const api: Api = isCopilotClaude4
+					? "anthropic-messages"
+					: needsResponsesApi
+						? "openai-responses"
+						: "openai-completions";
+
+				const copilotModel: Model<any> = {
+					id: modelId,
+					name: m.name || modelId,
+					api,
+					provider: "github-copilot",
+					baseUrl: "https://api.individual.githubcopilot.com",
+					reasoning: m.reasoning === true,
+					input: m.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
+					cost: {
+						input: m.cost?.input || 0,
+						output: m.cost?.output || 0,
+						cacheRead: m.cost?.cache_read || 0,
+						cacheWrite: m.cost?.cache_write || 0,
+					},
+					contextWindow: m.limit?.context || 128000,
+					maxTokens: m.limit?.output || 8192,
+					headers: { ...COPILOT_STATIC_HEADERS },
+					// compat only applies to openai-completions
+					...(api === "openai-completions" ? {
+						compat: {
+							supportsStore: false,
+							supportsDeveloperRole: false,
+							supportsReasoningEffort: false,
+						},
+					} : {}),
+				};
+
+				models.push(copilotModel);
+			}
+		}
+
+		// Process MiniMax models
+		const minimaxVariants = [
+			{ key: "minimax", provider: "minimax", baseUrl: "https://api.minimax.io/anthropic" },
+			{ key: "minimax-cn", provider: "minimax-cn", baseUrl: "https://api.minimaxi.com/anthropic" },
+		] as const;
+
+		for (const { key, provider, baseUrl } of minimaxVariants) {
+			if (data[key]?.models) {
+				for (const [modelId, model] of Object.entries(data[key].models)) {
+					const m = model as ModelsDevModel;
+					if (m.tool_call !== true) continue;
+
+					models.push({
+						id: modelId,
+						name: m.name || modelId,
+						api: "anthropic-messages",
+						provider,
+						// MiniMax's Anthropic-compatible API - SDK appends /v1/messages
+						baseUrl,
+						reasoning: m.reasoning === true,
+						input: m.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
+						cost: {
+							input: m.cost?.input || 0,
+							output: m.cost?.output || 0,
+							cacheRead: m.cost?.cache_read || 0,
+							cacheWrite: m.cost?.cache_write || 0,
+						},
+						contextWindow: m.limit?.context || 4096,
+						maxTokens: m.limit?.output || 4096,
+					});
+				}
+			}
+		}
+
+		// Process Kimi For Coding models
+		if (data["kimi-for-coding"]?.models) {
+			for (const [modelId, model] of Object.entries(data["kimi-for-coding"].models)) {
+				const m = model as ModelsDevModel;
+				if (m.tool_call !== true) continue;
+
+				models.push({
+					id: modelId,
+					name: m.name || modelId,
+					api: "anthropic-messages",
+					provider: "kimi-coding",
+					// Kimi For Coding's Anthropic-compatible API - SDK appends /v1/messages
+					baseUrl: "https://api.kimi.com/coding",
+					reasoning: m.reasoning === true,
+					input: m.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
+					cost: {
+						input: m.cost?.input || 0,
+						output: m.cost?.output || 0,
+						cacheRead: m.cost?.cache_read || 0,
+						cacheWrite: m.cost?.cache_write || 0,
+					},
+					contextWindow: m.limit?.context || 4096,
+					maxTokens: m.limit?.output || 4096,
+				});
+			}
+		}
+
+		console.log(`Loaded ${models.length} tool-capable models from models.dev`);
+		return models;
+	} catch (error) {
+		console.error("Failed to load models.dev data:", error);
+		return [];
+	}
+}
+
+async function generateModels() {
+	// Fetch models from both sources
+	// models.dev: Anthropic, Google, OpenAI, Groq, Cerebras
+	// OpenRouter: xAI and other providers (excluding Anthropic, Google, OpenAI)
+	// AI Gateway: OpenAI-compatible catalog with tool-capable models
+	const modelsDevModels = await loadModelsDevData();
+	const openRouterModels = await fetchOpenRouterModels();
+	const aiGatewayModels = await fetchAiGatewayModels();
+
+	// Combine models (models.dev has priority)
+	const allModels = [...modelsDevModels, ...openRouterModels, ...aiGatewayModels].filter(
+		(model) =>
+			!((model.provider === "opencode" || model.provider === "opencode-go") && model.id === "gpt-5.3-codex-spark"),
+	);
+
+	// Fix incorrect cache pricing for Claude Opus 4.5 from models.dev
+	// models.dev has 3x the correct pricing (1.5/18.75 instead of 0.5/6.25)
+	const opus45 = allModels.find(m => m.provider === "anthropic" && m.id === "claude-opus-4-5");
+	if (opus45) {
+		opus45.cost.cacheRead = 0.5;
+		opus45.cost.cacheWrite = 6.25;
+	}
+
+	// Temporary overrides until upstream model metadata is corrected.
+	for (const candidate of allModels) {
+		if (candidate.provider === "amazon-bedrock" && candidate.id.includes("anthropic.claude-opus-4-6-v1")) {
+			candidate.cost.cacheRead = 0.5;
+			candidate.cost.cacheWrite = 6.25;
+			candidate.contextWindow = 1000000;
+		}
+		if (candidate.provider === "amazon-bedrock" && candidate.id.includes("anthropic.claude-sonnet-4-6")) {
+			candidate.contextWindow = 1000000;
+		}
+		if (
+			(candidate.provider === "anthropic" ||
+				candidate.provider === "opencode" ||
+				candidate.provider === "opencode-go") &&
+			(candidate.id === "claude-opus-4-6" ||
+				candidate.id === "claude-sonnet-4-6" ||
+				candidate.id === "claude-opus-4.6" ||
+				candidate.id === "claude-sonnet-4.6")
+		) {
+			candidate.contextWindow = 1000000;
+		}
+		if (
+			candidate.provider === "google-antigravity" &&
+			(candidate.id === "claude-opus-4-6-thinking" || candidate.id === "claude-sonnet-4-6")
+		) {
+			candidate.contextWindow = 1000000;
+		}
+		// OpenCode variants list Claude Sonnet 4/4.5 with 1M context, actual limit is 200K
+		if (
+			(candidate.provider === "opencode" || candidate.provider === "opencode-go") &&
+			(candidate.id === "claude-sonnet-4-5" || candidate.id === "claude-sonnet-4")
+		) {
+			candidate.contextWindow = 200000;
+		}
+		if ((candidate.provider === "opencode" || candidate.provider === "opencode-go") && candidate.id === "gpt-5.4") {
+			candidate.contextWindow = 272000;
+			candidate.maxTokens = 128000;
+		}
+		if (candidate.provider === "openai" && candidate.id === "gpt-5.4") {
+			candidate.contextWindow = 272000;
+			candidate.maxTokens = 128000;
+		}
+		// Keep selected OpenRouter model metadata stable until upstream settles.
+		if (candidate.provider === "openrouter" && candidate.id === "moonshotai/kimi-k2.5") {
+			candidate.cost.input = 0.41;
+			candidate.cost.output = 2.06;
+			candidate.cost.cacheRead = 0.07;
+			candidate.maxTokens = 4096;
+		}
+		if (candidate.provider === "openrouter" && candidate.id === "z-ai/glm-5") {
+			candidate.cost.input = 0.6;
+			candidate.cost.output = 1.9;
+			candidate.cost.cacheRead = 0.119;
+		}
+	}
+
+
+	// Add missing EU Opus 4.6 profile
+	if (!allModels.some((m) => m.provider === "amazon-bedrock" && m.id === "eu.anthropic.claude-opus-4-6-v1")) {
+		allModels.push({
+			id: "eu.anthropic.claude-opus-4-6-v1",
+			name: "Claude Opus 4.6 (EU)",
+			api: "bedrock-converse-stream",
+			provider: "amazon-bedrock",
+			baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 5,
+				output: 25,
+				cacheRead: 0.5,
+				cacheWrite: 6.25,
+			},
+			contextWindow: 1000000,
+			maxTokens: 128000,
+		});
+	}
+
+	// Add missing Claude Opus 4.6
+	if (!allModels.some(m => m.provider === "anthropic" && m.id === "claude-opus-4-6")) {
+		allModels.push({
+			id: "claude-opus-4-6",
+			name: "Claude Opus 4.6",
+			api: "anthropic-messages",
+			baseUrl: "https://api.anthropic.com",
+			provider: "anthropic",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 5,
+				output: 25,
+				cacheRead: 0.5,
+				cacheWrite: 6.25,
+			},
+			contextWindow: 1000000,
+			maxTokens: 128000,
+		});
+	}
+
+	// Add missing Claude Sonnet 4.6
+	if (!allModels.some(m => m.provider === "anthropic" && m.id === "claude-sonnet-4-6")) {
+		allModels.push({
+			id: "claude-sonnet-4-6",
+			name: "Claude Sonnet 4.6",
+			api: "anthropic-messages",
+			baseUrl: "https://api.anthropic.com",
+			provider: "anthropic",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 3,
+				output: 15,
+				cacheRead: 0.3,
+				cacheWrite: 3.75,
+			},
+			contextWindow: 1000000,
+			maxTokens: 64000,
+		});
+	}
+
+	// Add missing Gemini 3.1 Flash Lite Preview until models.dev includes it.
+	if (!allModels.some((m) => m.provider === "google" && m.id === "gemini-3.1-flash-lite-preview")) {
+		allModels.push({
+			id: "gemini-3.1-flash-lite-preview",
+			name: "Gemini 3.1 Flash Lite Preview",
+			api: "google-generative-ai",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			provider: "google",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		});
+	}
+
+	// Add missing gpt models
+	if (!allModels.some(m => m.provider === "openai" && m.id === "gpt-5-chat-latest")) {
+		allModels.push({
+			id: "gpt-5-chat-latest",
+			name: "GPT-5 Chat Latest",
+			api: "openai-responses",
+			baseUrl: "https://api.openai.com/v1",
+			provider: "openai",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 1.25,
+				output: 10,
+				cacheRead: 0.125,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		});
+	}
+
+	if (!allModels.some(m => m.provider === "openai" && m.id === "gpt-5.1-codex")) {
+		allModels.push({
+			id: "gpt-5.1-codex",
+			name: "GPT-5.1 Codex",
+			api: "openai-responses",
+			baseUrl: "https://api.openai.com/v1",
+			provider: "openai",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.25,
+				output: 5,
+				cacheRead: 0.125,
+				cacheWrite: 1.25,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		});
+	}
+
+	if (!allModels.some(m => m.provider === "openai" && m.id === "gpt-5.1-codex-max")) {
+		allModels.push({
+			id: "gpt-5.1-codex-max",
+			name: "GPT-5.1 Codex Max",
+			api: "openai-responses",
+			baseUrl: "https://api.openai.com/v1",
+			provider: "openai",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.25,
+				output: 10,
+				cacheRead: 0.125,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		});
+	}
+
+	if (!allModels.some(m => m.provider === "openai" && m.id === "gpt-5.3-codex-spark")) {
+		allModels.push({
+			id: "gpt-5.3-codex-spark",
+			name: "GPT-5.3 Codex Spark",
+			api: "openai-responses",
+			baseUrl: "https://api.openai.com/v1",
+			provider: "openai",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		});
+	}
+
+	// Add missing GitHub Copilot GPT-5.3 models until models.dev includes them.
+	const copilotBaseModel = allModels.find(
+		(m) => m.provider === "github-copilot" && m.id === "gpt-5.2-codex",
+	);
+	if (copilotBaseModel) {
+		if (!allModels.some((m) => m.provider === "github-copilot" && m.id === "gpt-5.3-codex")) {
+			allModels.push({
+				...copilotBaseModel,
+				id: "gpt-5.3-codex",
+				name: "GPT-5.3 Codex",
+			});
+		}
+	}
+
+	if (!allModels.some((m) => m.provider === "openai" && m.id === "gpt-5.4")) {
+		allModels.push({
+			id: "gpt-5.4",
+			name: "GPT-5.4",
+			api: "openai-responses",
+			baseUrl: "https://api.openai.com/v1",
+			provider: "openai",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 2.5,
+				output: 15,
+				cacheRead: 0.25,
+				cacheWrite: 0,
+			},
+			contextWindow: 272000,
+			maxTokens: 128000,
+		});
+	}
+
+	// OpenAI Codex (ChatGPT OAuth) models
+	// NOTE: These are not fetched from models.dev; we keep a small, explicit list to avoid aliases.
+	// Context window is based on observed server limits (400s above ~272k), not marketing numbers.
+	const CODEX_BASE_URL = "https://chatgpt.com/backend-api";
+	const CODEX_CONTEXT = 272000;
+	const CODEX_MAX_TOKENS = 128000;
+	const codexModels: Model<"openai-codex-responses">[] = [
+		{
+			id: "gpt-5.1",
+			name: "GPT-5.1",
+			api: "openai-codex-responses",
+			provider: "openai-codex",
+			baseUrl: CODEX_BASE_URL,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 1.25, output: 10, cacheRead: 0.125, cacheWrite: 0 },
+			contextWindow: CODEX_CONTEXT,
+			maxTokens: CODEX_MAX_TOKENS,
+		},
+		{
+			id: "gpt-5.1-codex-max",
+			name: "GPT-5.1 Codex Max",
+			api: "openai-codex-responses",
+			provider: "openai-codex",
+			baseUrl: CODEX_BASE_URL,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 1.25, output: 10, cacheRead: 0.125, cacheWrite: 0 },
+			contextWindow: CODEX_CONTEXT,
+			maxTokens: CODEX_MAX_TOKENS,
+		},
+		{
+			id: "gpt-5.1-codex-mini",
+			name: "GPT-5.1 Codex Mini",
+			api: "openai-codex-responses",
+			provider: "openai-codex",
+			baseUrl: CODEX_BASE_URL,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 0.25, output: 2, cacheRead: 0.025, cacheWrite: 0 },
+			contextWindow: CODEX_CONTEXT,
+			maxTokens: CODEX_MAX_TOKENS,
+		},
+		{
+			id: "gpt-5.2",
+			name: "GPT-5.2",
+			api: "openai-codex-responses",
+			provider: "openai-codex",
+			baseUrl: CODEX_BASE_URL,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 1.75, output: 14, cacheRead: 0.175, cacheWrite: 0 },
+			contextWindow: CODEX_CONTEXT,
+			maxTokens: CODEX_MAX_TOKENS,
+		},
+		{
+			id: "gpt-5.2-codex",
+			name: "GPT-5.2 Codex",
+			api: "openai-codex-responses",
+			provider: "openai-codex",
+			baseUrl: CODEX_BASE_URL,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 1.75, output: 14, cacheRead: 0.175, cacheWrite: 0 },
+			contextWindow: CODEX_CONTEXT,
+			maxTokens: CODEX_MAX_TOKENS,
+		},
+		{
+			id: "gpt-5.3-codex",
+			name: "GPT-5.3 Codex",
+			api: "openai-codex-responses",
+			provider: "openai-codex",
+			baseUrl: CODEX_BASE_URL,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 1.75, output: 14, cacheRead: 0.175, cacheWrite: 0 },
+			contextWindow: CODEX_CONTEXT,
+			maxTokens: CODEX_MAX_TOKENS,
+		},
+		{
+			id: "gpt-5.4",
+			name: "GPT-5.4",
+			api: "openai-codex-responses",
+			provider: "openai-codex",
+			baseUrl: CODEX_BASE_URL,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 2.5, output: 15, cacheRead: 0.25, cacheWrite: 0 },
+			contextWindow: CODEX_CONTEXT,
+			maxTokens: CODEX_MAX_TOKENS,
+		},
+		{
+			id: "gpt-5.3-codex-spark",
+			name: "GPT-5.3 Codex Spark",
+			api: "openai-codex-responses",
+			provider: "openai-codex",
+			baseUrl: CODEX_BASE_URL,
+			reasoning: true,
+			input: ["text"],
+			cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+			contextWindow: 128000,
+			maxTokens: CODEX_MAX_TOKENS,
+		},
+	];
+	allModels.push(...codexModels);
+
+	// Add missing Grok models
+	if (!allModels.some(m => m.provider === "xai" && m.id === "grok-code-fast-1")) {
+		allModels.push({
+			id: "grok-code-fast-1",
+			name: "Grok Code Fast 1",
+			api: "openai-completions",
+			baseUrl: "https://api.x.ai/v1",
+			provider: "xai",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.2,
+				output: 1.5,
+				cacheRead: 0.02,
+				cacheWrite: 0,
+			},
+			contextWindow: 32768,
+			maxTokens: 8192,
+		});
+	}
+
+	// Add "auto" alias for openrouter/auto
+	if (!allModels.some(m => m.provider === "openrouter" && m.id === "auto")) {
+		allModels.push({
+			id: "auto",
+			name: "Auto",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				// we dont know about the costs because OpenRouter auto routes to different models
+				// and then charges you for the underlying used model
+				input:0,
+				output:0,
+				cacheRead:0,
+				cacheWrite:0,
+			},
+			contextWindow: 2000000,
+			maxTokens: 30000,
+		});
+	}
+
+	// Google Cloud Code Assist models (Gemini CLI)
+	// Uses production endpoint, standard Gemini models only
+	const CLOUD_CODE_ASSIST_ENDPOINT = "https://cloudcode-pa.googleapis.com";
+	const cloudCodeAssistModels: Model<"google-gemini-cli">[] = [
+		{
+			id: "gemini-2.5-pro",
+			name: "Gemini 2.5 Pro (Cloud Code Assist)",
+			api: "google-gemini-cli",
+			provider: "google-gemini-cli",
+			baseUrl: CLOUD_CODE_ASSIST_ENDPOINT,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+			contextWindow: 1048576,
+			maxTokens: 65535,
+		},
+		{
+			id: "gemini-2.5-flash",
+			name: "Gemini 2.5 Flash (Cloud Code Assist)",
+			api: "google-gemini-cli",
+			provider: "google-gemini-cli",
+			baseUrl: CLOUD_CODE_ASSIST_ENDPOINT,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+			contextWindow: 1048576,
+			maxTokens: 65535,
+		},
+		{
+			id: "gemini-2.0-flash",
+			name: "Gemini 2.0 Flash (Cloud Code Assist)",
+			api: "google-gemini-cli",
+			provider: "google-gemini-cli",
+			baseUrl: CLOUD_CODE_ASSIST_ENDPOINT,
+			reasoning: false,
+			input: ["text", "image"],
+			cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+			contextWindow: 1048576,
+			maxTokens: 8192,
+		},
+		{
+			id: "gemini-3-pro-preview",
+			name: "Gemini 3 Pro Preview (Cloud Code Assist)",
+			api: "google-gemini-cli",
+			provider: "google-gemini-cli",
+			baseUrl: CLOUD_CODE_ASSIST_ENDPOINT,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+			contextWindow: 1048576,
+			maxTokens: 65535,
+		},
+		{
+			id: "gemini-3-flash-preview",
+			name: "Gemini 3 Flash Preview (Cloud Code Assist)",
+			api: "google-gemini-cli",
+			provider: "google-gemini-cli",
+			baseUrl: CLOUD_CODE_ASSIST_ENDPOINT,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+			contextWindow: 1048576,
+			maxTokens: 65535,
+		},
+		{
+			id: "gemini-3.1-pro-preview",
+			name: "Gemini 3.1 Pro Preview (Cloud Code Assist)",
+			api: "google-gemini-cli",
+			provider: "google-gemini-cli",
+			baseUrl: CLOUD_CODE_ASSIST_ENDPOINT,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+			contextWindow: 1048576,
+			maxTokens: 65535,
+		},
+	];
+	allModels.push(...cloudCodeAssistModels);
+
+	// Antigravity models (Gemini 3, Claude, GPT-OSS via Google Cloud)
+	// Uses sandbox endpoint and different OAuth credentials for access to additional models
+	const ANTIGRAVITY_ENDPOINT = "https://daily-cloudcode-pa.sandbox.googleapis.com";
+	const antigravityModels: Model<"google-gemini-cli">[] = [
+		{
+			id: "gemini-3.1-pro-high",
+			name: "Gemini 3.1 Pro High (Antigravity)",
+			api: "google-gemini-cli",
+			provider: "google-antigravity",
+			baseUrl: ANTIGRAVITY_ENDPOINT,
+			reasoning: true,
+			input: ["text", "image"],
+			// the Model type doesn't seem to support having extended-context costs, so I'm just using the pricing for <200k input
+			cost: { input: 2, output: 12, cacheRead: 0.2, cacheWrite: 2.375 },
+			contextWindow: 1048576,
+			maxTokens: 65535,
+		},
+		{
+			id: "gemini-3.1-pro-low",
+			name: "Gemini 3.1 Pro Low (Antigravity)",
+			api: "google-gemini-cli",
+			provider: "google-antigravity",
+			baseUrl: ANTIGRAVITY_ENDPOINT,
+			reasoning: true,
+			input: ["text", "image"],
+			// the Model type doesn't seem to support having extended-context costs, so I'm just using the pricing for <200k input
+			cost: { input: 2, output: 12, cacheRead: 0.2, cacheWrite: 2.375 },
+			contextWindow: 1048576,
+			maxTokens: 65535,
+		},
+		{
+			id: "gemini-3-flash",
+			name: "Gemini 3 Flash (Antigravity)",
+			api: "google-gemini-cli",
+			provider: "google-antigravity",
+			baseUrl: ANTIGRAVITY_ENDPOINT,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 0.5, output: 3, cacheRead: 0.5, cacheWrite: 0 },
+			contextWindow: 1048576,
+			maxTokens: 65535,
+		},
+		{
+			id: "claude-sonnet-4-5",
+			name: "Claude Sonnet 4.5 (Antigravity)",
+			api: "google-gemini-cli",
+			provider: "google-antigravity",
+			baseUrl: ANTIGRAVITY_ENDPOINT,
+			reasoning: false,
+			input: ["text", "image"],
+			cost: { input: 3, output: 15, cacheRead: 0.3, cacheWrite: 3.75 },
+			contextWindow: 200000,
+			maxTokens: 64000,
+		},
+		{
+			id: "claude-sonnet-4-5-thinking",
+			name: "Claude Sonnet 4.5 Thinking (Antigravity)",
+			api: "google-gemini-cli",
+			provider: "google-antigravity",
+			baseUrl: ANTIGRAVITY_ENDPOINT,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 3, output: 15, cacheRead: 0.3, cacheWrite: 3.75 },
+			contextWindow: 200000,
+			maxTokens: 64000,
+		},
+		{
+			id: "claude-opus-4-5-thinking",
+			name: "Claude Opus 4.5 Thinking (Antigravity)",
+			api: "google-gemini-cli",
+			provider: "google-antigravity",
+			baseUrl: ANTIGRAVITY_ENDPOINT,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 5, output: 25, cacheRead: 0.5, cacheWrite: 6.25 },
+			contextWindow: 200000,
+			maxTokens: 64000,
+		},
+		{
+			id: "claude-opus-4-6-thinking",
+			name: "Claude Opus 4.6 Thinking (Antigravity)",
+			api: "google-gemini-cli",
+			provider: "google-antigravity",
+			baseUrl: ANTIGRAVITY_ENDPOINT,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 5, output: 25, cacheRead: 0.5, cacheWrite: 6.25 },
+			contextWindow: 200000,
+			maxTokens: 128000,
+		},
+		{
+			id: "claude-sonnet-4-6",
+			name: "Claude Sonnet 4.6 (Antigravity)",
+			api: "google-gemini-cli",
+			provider: "google-antigravity",
+			baseUrl: ANTIGRAVITY_ENDPOINT,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 3, output: 15, cacheRead: 0.3, cacheWrite: 3.75 },
+			contextWindow: 200000,
+			maxTokens: 64000,
+		},
+		{
+			id: "gpt-oss-120b-medium",
+			name: "GPT-OSS 120B Medium (Antigravity)",
+			api: "google-gemini-cli",
+			provider: "google-antigravity",
+			baseUrl: ANTIGRAVITY_ENDPOINT,
+			reasoning: false,
+			input: ["text"],
+			cost: { input: 0.09, output: 0.36, cacheRead: 0, cacheWrite: 0 },
+			contextWindow: 131072,
+			maxTokens: 32768,
+		},
+	];
+	allModels.push(...antigravityModels);
+
+	const VERTEX_BASE_URL = "https://{location}-aiplatform.googleapis.com";
+	const vertexModels: Model<"google-vertex">[] = [
+		{
+			id: "gemini-3-pro-preview",
+			name: "Gemini 3 Pro Preview (Vertex)",
+			api: "google-vertex",
+			provider: "google-vertex",
+			baseUrl: VERTEX_BASE_URL,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 2, output: 12, cacheRead: 0.2, cacheWrite: 0 },
+			contextWindow: 1000000,
+			maxTokens: 64000,
+		},
+		{
+			id: "gemini-3.1-pro-preview",
+			name: "Gemini 3.1 Pro Preview (Vertex)",
+			api: "google-vertex",
+			provider: "google-vertex",
+			baseUrl: VERTEX_BASE_URL,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 2, output: 12, cacheRead: 0.2, cacheWrite: 0 },
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		},
+		{
+			id: "gemini-3-flash-preview",
+			name: "Gemini 3 Flash Preview (Vertex)",
+			api: "google-vertex",
+			provider: "google-vertex",
+			baseUrl: VERTEX_BASE_URL,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 0.5, output: 3, cacheRead: 0.05, cacheWrite: 0 },
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		},
+		{
+			id: "gemini-2.0-flash",
+			name: "Gemini 2.0 Flash (Vertex)",
+			api: "google-vertex",
+			provider: "google-vertex",
+			baseUrl: VERTEX_BASE_URL,
+			reasoning: false,
+			input: ["text", "image"],
+			cost: { input: 0.15, output: 0.6, cacheRead: 0.0375, cacheWrite: 0 },
+			contextWindow: 1048576,
+			maxTokens: 8192,
+		},
+		{
+			id: "gemini-2.0-flash-lite",
+			name: "Gemini 2.0 Flash Lite (Vertex)",
+			api: "google-vertex",
+			provider: "google-vertex",
+			baseUrl: VERTEX_BASE_URL,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 0.075, output: 0.3, cacheRead: 0.01875, cacheWrite: 0 },
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		},
+		{
+			id: "gemini-2.5-pro",
+			name: "Gemini 2.5 Pro (Vertex)",
+			api: "google-vertex",
+			provider: "google-vertex",
+			baseUrl: VERTEX_BASE_URL,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 1.25, output: 10, cacheRead: 0.125, cacheWrite: 0 },
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		},
+		{
+			id: "gemini-2.5-flash",
+			name: "Gemini 2.5 Flash (Vertex)",
+			api: "google-vertex",
+			provider: "google-vertex",
+			baseUrl: VERTEX_BASE_URL,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 0.3, output: 2.5, cacheRead: 0.03, cacheWrite: 0 },
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		},
+		{
+			id: "gemini-2.5-flash-lite-preview-09-2025",
+			name: "Gemini 2.5 Flash Lite Preview 09-25 (Vertex)",
+			api: "google-vertex",
+			provider: "google-vertex",
+			baseUrl: VERTEX_BASE_URL,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 0.1, output: 0.4, cacheRead: 0.01, cacheWrite: 0 },
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		},
+		{
+			id: "gemini-2.5-flash-lite",
+			name: "Gemini 2.5 Flash Lite (Vertex)",
+			api: "google-vertex",
+			provider: "google-vertex",
+			baseUrl: VERTEX_BASE_URL,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 0.1, output: 0.4, cacheRead: 0.01, cacheWrite: 0 },
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		},
+		{
+			id: "gemini-1.5-pro",
+			name: "Gemini 1.5 Pro (Vertex)",
+			api: "google-vertex",
+			provider: "google-vertex",
+			baseUrl: VERTEX_BASE_URL,
+			reasoning: false,
+			input: ["text", "image"],
+			cost: { input: 1.25, output: 5, cacheRead: 0.3125, cacheWrite: 0 },
+			contextWindow: 1000000,
+			maxTokens: 8192,
+		},
+		{
+			id: "gemini-1.5-flash",
+			name: "Gemini 1.5 Flash (Vertex)",
+			api: "google-vertex",
+			provider: "google-vertex",
+			baseUrl: VERTEX_BASE_URL,
+			reasoning: false,
+			input: ["text", "image"],
+			cost: { input: 0.075, output: 0.3, cacheRead: 0.01875, cacheWrite: 0 },
+			contextWindow: 1000000,
+			maxTokens: 8192,
+		},
+		{
+			id: "gemini-1.5-flash-8b",
+			name: "Gemini 1.5 Flash-8B (Vertex)",
+			api: "google-vertex",
+			provider: "google-vertex",
+			baseUrl: VERTEX_BASE_URL,
+			reasoning: false,
+			input: ["text", "image"],
+			cost: { input: 0.0375, output: 0.15, cacheRead: 0.01, cacheWrite: 0 },
+			contextWindow: 1000000,
+			maxTokens: 8192,
+		},
+	];
+	allModels.push(...vertexModels);
+
+	// Kimi For Coding models (Moonshot AI's Anthropic-compatible coding API)
+	// Static fallback in case models.dev doesn't have them yet
+	const KIMI_CODING_BASE_URL = "https://api.kimi.com/coding";
+	const kimiCodingModels: Model<"anthropic-messages">[] = [
+		{
+			id: "kimi-k2-thinking",
+			name: "Kimi K2 Thinking",
+			api: "anthropic-messages",
+			provider: "kimi-coding",
+			baseUrl: KIMI_CODING_BASE_URL,
+			reasoning: true,
+			input: ["text"],
+			cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+			contextWindow: 262144,
+			maxTokens: 32768,
+		},
+		{
+			id: "k2p5",
+			name: "Kimi K2.5",
+			api: "anthropic-messages",
+			provider: "kimi-coding",
+			baseUrl: KIMI_CODING_BASE_URL,
+			reasoning: true,
+			input: ["text"],
+			cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+			contextWindow: 262144,
+			maxTokens: 32768,
+		},
+	];
+	// Only add if not already present from models.dev
+	for (const model of kimiCodingModels) {
+		if (!allModels.some(m => m.provider === "kimi-coding" && m.id === model.id)) {
+			allModels.push(model);
+		}
+	}
+
+	const azureOpenAiModels: Model<Api>[] = allModels
+		.filter((model) => model.provider === "openai" && model.api === "openai-responses")
+		.map((model) => ({
+			...model,
+			api: "azure-openai-responses",
+			provider: "azure-openai-responses",
+			baseUrl: "",
+		}));
+	allModels.push(...azureOpenAiModels);
+
+	// Group by provider and deduplicate by model ID
+	const providers: Record<string, Record<string, Model<any>>> = {};
+	for (const model of allModels) {
+		if (!providers[model.provider]) {
+			providers[model.provider] = {};
+		}
+		// Use model ID as key to automatically deduplicate
+		// Only add if not already present (models.dev takes priority over OpenRouter)
+		if (!providers[model.provider][model.id]) {
+			providers[model.provider][model.id] = model;
+		}
+	}
+
+	// Generate TypeScript file
+	let output = `// This file is auto-generated by scripts/generate-models.ts
+// Do not edit manually - run 'npm run generate-models' to update
+
+import type { Model } from "./types.js";
+
+export const MODELS = {
+`;
+
+	// Generate provider sections (sorted for deterministic output)
+	const sortedProviderIds = Object.keys(providers).sort();
+	for (const providerId of sortedProviderIds) {
+		const models = providers[providerId];
+		output += `\t${JSON.stringify(providerId)}: {\n`;
+
+		const sortedModelIds = Object.keys(models).sort();
+		for (const modelId of sortedModelIds) {
+			const model = models[modelId];
+			output += `\t\t"${model.id}": {\n`;
+			output += `\t\t\tid: "${model.id}",\n`;
+			output += `\t\t\tname: "${model.name}",\n`;
+			output += `\t\t\tapi: "${model.api}",\n`;
+			output += `\t\t\tprovider: "${model.provider}",\n`;
+			if (model.baseUrl !== undefined) {
+				output += `\t\t\tbaseUrl: "${model.baseUrl}",\n`;
+			}
+			if (model.headers) {
+				output += `\t\t\theaders: ${JSON.stringify(model.headers)},\n`;
+			}
+			if (model.compat) {
+				output += `			compat: ${JSON.stringify(model.compat)},
+`;
+			}
+			output += `\t\t\treasoning: ${model.reasoning},\n`;
+			output += `\t\t\tinput: [${model.input.map(i => `"${i}"`).join(", ")}],\n`;
+			output += `\t\t\tcost: {\n`;
+			output += `\t\t\t\tinput: ${model.cost.input},\n`;
+			output += `\t\t\t\toutput: ${model.cost.output},\n`;
+			output += `\t\t\t\tcacheRead: ${model.cost.cacheRead},\n`;
+			output += `\t\t\t\tcacheWrite: ${model.cost.cacheWrite},\n`;
+			output += `\t\t\t},\n`;
+			output += `\t\t\tcontextWindow: ${model.contextWindow},\n`;
+			output += `\t\t\tmaxTokens: ${model.maxTokens},\n`;
+			output += `\t\t} satisfies Model<"${model.api}">,\n`;
+		}
+
+		output += `\t},\n`;
+	}
+
+	output += `} as const;
+`;
+
+	// Write file
+	writeFileSync(join(packageRoot, "src/models.generated.ts"), output);
+	console.log("Generated src/models.generated.ts");
+
+	// Print statistics
+	const totalModels = allModels.length;
+	const reasoningModels = allModels.filter(m => m.reasoning).length;
+
+	console.log(`\nModel Statistics:`);
+	console.log(`  Total tool-capable models: ${totalModels}`);
+	console.log(`  Reasoning-capable models: ${reasoningModels}`);
+
+	for (const [provider, models] of Object.entries(providers)) {
+		console.log(`  ${provider}: ${Object.keys(models).length} models`);
+	}
+}
+
+// Run the generator
+generateModels().catch(console.error);
diff --git a/packages/pi-ai/src/models.generated.ts b/packages/pi-ai/src/models.generated.ts
index ac56d2069..e62965533 100644
--- a/packages/pi-ai/src/models.generated.ts
+++ b/packages/pi-ai/src/models.generated.ts
@@ -90,40 +90,6 @@ export const MODELS = {
 			contextWindow: 300000,
 			maxTokens: 8192,
 		} satisfies Model<"bedrock-converse-stream">,
-		"amazon.titan-text-express-v1": {
-			id: "amazon.titan-text-express-v1",
-			name: "Titan Text G1 - Express",
-			api: "bedrock-converse-stream",
-			provider: "amazon-bedrock",
-			baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.2,
-				output: 0.6,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 4096,
-		} satisfies Model<"bedrock-converse-stream">,
-		"amazon.titan-text-express-v1:0:8k": {
-			id: "amazon.titan-text-express-v1:0:8k",
-			name: "Titan Text G1 - Express",
-			api: "bedrock-converse-stream",
-			provider: "amazon-bedrock",
-			baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.2,
-				output: 0.6,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 4096,
-		} satisfies Model<"bedrock-converse-stream">,
 		"anthropic.claude-3-5-haiku-20241022-v1:0": {
 			id: "anthropic.claude-3-5-haiku-20241022-v1:0",
 			name: "Claude Haiku 3.5",
@@ -209,40 +175,6 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 4096,
 		} satisfies Model<"bedrock-converse-stream">,
-		"anthropic.claude-3-opus-20240229-v1:0": {
-			id: "anthropic.claude-3-opus-20240229-v1:0",
-			name: "Claude Opus 3",
-			api: "bedrock-converse-stream",
-			provider: "amazon-bedrock",
-			baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 15,
-				output: 75,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 4096,
-		} satisfies Model<"bedrock-converse-stream">,
-		"anthropic.claude-3-sonnet-20240229-v1:0": {
-			id: "anthropic.claude-3-sonnet-20240229-v1:0",
-			name: "Claude Sonnet 3",
-			api: "bedrock-converse-stream",
-			provider: "amazon-bedrock",
-			baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 4096,
-		} satisfies Model<"bedrock-converse-stream">,
 		"anthropic.claude-haiku-4-5-20251001-v1:0": {
 			id: "anthropic.claude-haiku-4-5-20251001-v1:0",
 			name: "Claude Haiku 4.5",
@@ -325,7 +257,7 @@ export const MODELS = {
 				cacheRead: 0.5,
 				cacheWrite: 6.25,
 			},
-			contextWindow: 200000,
+			contextWindow: 1000000,
 			maxTokens: 128000,
 		} satisfies Model<"bedrock-converse-stream">,
 		"anthropic.claude-sonnet-4-20250514-v1:0": {
@@ -376,43 +308,9 @@ export const MODELS = {
 				cacheRead: 0.3,
 				cacheWrite: 3.75,
 			},
-			contextWindow: 200000,
+			contextWindow: 1000000,
 			maxTokens: 64000,
 		} satisfies Model<"bedrock-converse-stream">,
-		"cohere.command-r-plus-v1:0": {
-			id: "cohere.command-r-plus-v1:0",
-			name: "Command R+",
-			api: "bedrock-converse-stream",
-			provider: "amazon-bedrock",
-			baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 4096,
-		} satisfies Model<"bedrock-converse-stream">,
-		"cohere.command-r-v1:0": {
-			id: "cohere.command-r-v1:0",
-			name: "Command R",
-			api: "bedrock-converse-stream",
-			provider: "amazon-bedrock",
-			baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.5,
-				output: 1.5,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 4096,
-		} satisfies Model<"bedrock-converse-stream">,
 		"deepseek.r1-v1:0": {
 			id: "deepseek.r1-v1:0",
 			name: "DeepSeek-R1",
@@ -447,8 +345,8 @@ export const MODELS = {
 			contextWindow: 163840,
 			maxTokens: 81920,
 		} satisfies Model<"bedrock-converse-stream">,
-		"deepseek.v3.2-v1:0": {
-			id: "deepseek.v3.2-v1:0",
+		"deepseek.v3.2": {
+			id: "deepseek.v3.2",
 			name: "DeepSeek-V3.2",
 			api: "bedrock-converse-stream",
 			provider: "amazon-bedrock",
@@ -512,7 +410,7 @@ export const MODELS = {
 				cacheRead: 0.5,
 				cacheWrite: 6.25,
 			},
-			contextWindow: 200000,
+			contextWindow: 1000000,
 			maxTokens: 128000,
 		} satisfies Model<"bedrock-converse-stream">,
 		"eu.anthropic.claude-sonnet-4-20250514-v1:0": {
@@ -563,7 +461,7 @@ export const MODELS = {
 				cacheRead: 0.3,
 				cacheWrite: 3.75,
 			},
-			contextWindow: 200000,
+			contextWindow: 1000000,
 			maxTokens: 64000,
 		} satisfies Model<"bedrock-converse-stream">,
 		"global.anthropic.claude-haiku-4-5-20251001-v1:0": {
@@ -614,7 +512,7 @@ export const MODELS = {
 				cacheRead: 0.5,
 				cacheWrite: 6.25,
 			},
-			contextWindow: 200000,
+			contextWindow: 1000000,
 			maxTokens: 128000,
 		} satisfies Model<"bedrock-converse-stream">,
 		"global.anthropic.claude-sonnet-4-20250514-v1:0": {
@@ -665,7 +563,7 @@ export const MODELS = {
 				cacheRead: 0.3,
 				cacheWrite: 3.75,
 			},
-			contextWindow: 200000,
+			contextWindow: 1000000,
 			maxTokens: 64000,
 		} satisfies Model<"bedrock-converse-stream">,
 		"google.gemma-3-27b-it": {
@@ -702,6 +600,23 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 4096,
 		} satisfies Model<"bedrock-converse-stream">,
+		"meta.llama3-1-405b-instruct-v1:0": {
+			id: "meta.llama3-1-405b-instruct-v1:0",
+			name: "Llama 3.1 405B Instruct",
+			api: "bedrock-converse-stream",
+			provider: "amazon-bedrock",
+			baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 2.4,
+				output: 2.4,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"bedrock-converse-stream">,
 		"meta.llama3-1-70b-instruct-v1:0": {
 			id: "meta.llama3-1-70b-instruct-v1:0",
 			name: "Llama 3.1 70B Instruct",
@@ -889,6 +804,40 @@ export const MODELS = {
 			contextWindow: 204800,
 			maxTokens: 131072,
 		} satisfies Model<"bedrock-converse-stream">,
+		"mistral.devstral-2-123b": {
+			id: "mistral.devstral-2-123b",
+			name: "Devstral 2 123B",
+			api: "bedrock-converse-stream",
+			provider: "amazon-bedrock",
+			baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.4,
+				output: 2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 8192,
+		} satisfies Model<"bedrock-converse-stream">,
+		"mistral.magistral-small-2509": {
+			id: "mistral.magistral-small-2509",
+			name: "Magistral Small 1.2",
+			api: "bedrock-converse-stream",
+			provider: "amazon-bedrock",
+			baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.5,
+				output: 1.5,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 40000,
+		} satisfies Model<"bedrock-converse-stream">,
 		"mistral.ministral-3-14b-instruct": {
 			id: "mistral.ministral-3-14b-instruct",
 			name: "Ministral 14B 3.0",
@@ -906,6 +855,23 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 4096,
 		} satisfies Model<"bedrock-converse-stream">,
+		"mistral.ministral-3-3b-instruct": {
+			id: "mistral.ministral-3-3b-instruct",
+			name: "Ministral 3 3B",
+			api: "bedrock-converse-stream",
+			provider: "amazon-bedrock",
+			baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.1,
+				output: 0.1,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 8192,
+		} satisfies Model<"bedrock-converse-stream">,
 		"mistral.ministral-3-8b-instruct": {
 			id: "mistral.ministral-3-8b-instruct",
 			name: "Ministral 3 8B",
@@ -923,22 +889,39 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 4096,
 		} satisfies Model<"bedrock-converse-stream">,
-		"mistral.mistral-large-2402-v1:0": {
-			id: "mistral.mistral-large-2402-v1:0",
-			name: "Mistral Large (24.02)",
+		"mistral.mistral-large-3-675b-instruct": {
+			id: "mistral.mistral-large-3-675b-instruct",
+			name: "Mistral Large 3",
 			api: "bedrock-converse-stream",
 			provider: "amazon-bedrock",
 			baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
 			reasoning: false,
-			input: ["text"],
+			input: ["text", "image"],
 			cost: {
 				input: 0.5,
 				output: 1.5,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
+			contextWindow: 256000,
+			maxTokens: 8192,
+		} satisfies Model<"bedrock-converse-stream">,
+		"mistral.pixtral-large-2502-v1:0": {
+			id: "mistral.pixtral-large-2502-v1:0",
+			name: "Pixtral Large (25.02)",
+			api: "bedrock-converse-stream",
+			provider: "amazon-bedrock",
+			baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 2,
+				output: 6,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
 			contextWindow: 128000,
-			maxTokens: 4096,
+			maxTokens: 8192,
 		} satisfies Model<"bedrock-converse-stream">,
 		"mistral.voxtral-mini-3b-2507": {
 			id: "mistral.voxtral-mini-3b-2507",
@@ -1025,6 +1008,23 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 4096,
 		} satisfies Model<"bedrock-converse-stream">,
+		"nvidia.nemotron-nano-3-30b": {
+			id: "nvidia.nemotron-nano-3-30b",
+			name: "NVIDIA Nemotron Nano 3 30B",
+			api: "bedrock-converse-stream",
+			provider: "amazon-bedrock",
+			baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.06,
+				output: 0.24,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"bedrock-converse-stream">,
 		"nvidia.nemotron-nano-9b-v2": {
 			id: "nvidia.nemotron-nano-9b-v2",
 			name: "NVIDIA Nemotron Nano 9B v2",
@@ -1294,7 +1294,7 @@ export const MODELS = {
 				cacheRead: 0.5,
 				cacheWrite: 6.25,
 			},
-			contextWindow: 200000,
+			contextWindow: 1000000,
 			maxTokens: 128000,
 		} satisfies Model<"bedrock-converse-stream">,
 		"us.anthropic.claude-sonnet-4-20250514-v1:0": {
@@ -1345,7 +1345,7 @@ export const MODELS = {
 				cacheRead: 0.3,
 				cacheWrite: 3.75,
 			},
-			contextWindow: 200000,
+			contextWindow: 1000000,
 			maxTokens: 64000,
 		} satisfies Model<"bedrock-converse-stream">,
 		"writer.palmyra-x4-v1:0": {
@@ -1721,23 +1721,6 @@ export const MODELS = {
 				cacheRead: 0.5,
 				cacheWrite: 6.25,
 			},
-			contextWindow: 200000,
-			maxTokens: 128000,
-		} satisfies Model<"anthropic-messages">,
-		"claude-opus-4-6[1m]": {
-			id: "claude-opus-4-6[1m]",
-			name: "Claude Opus 4.6 (1M)",
-			api: "anthropic-messages",
-			provider: "anthropic",
-			baseUrl: "https://api.anthropic.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 5,
-				output: 25,
-				cacheRead: 0.5,
-				cacheWrite: 6.25,
-			},
 			contextWindow: 1000000,
 			maxTokens: 128000,
 		} satisfies Model<"anthropic-messages">,
@@ -1823,182 +1806,10 @@ export const MODELS = {
 				cacheRead: 0.3,
 				cacheWrite: 3.75,
 			},
-			contextWindow: 200000,
+			contextWindow: 1000000,
 			maxTokens: 64000,
 		} satisfies Model<"anthropic-messages">,
 	},
-	"anthropic-vertex": {
-		"claude-opus-4-6": {
-			id: "claude-opus-4-6",
-			name: "Claude Opus 4.6 (Vertex)",
-			api: "anthropic-vertex",
-			provider: "anthropic-vertex",
-			baseUrl: "https://us-central1-aiplatform.googleapis.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 15,
-				output: 75,
-				cacheRead: 1.5,
-				cacheWrite: 18.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 128000,
-		} satisfies Model<"anthropic-vertex">,
-		"claude-opus-4-6[1m]": {
-			id: "claude-opus-4-6[1m]",
-			name: "Claude Opus 4.6 1M (Vertex)",
-			api: "anthropic-vertex",
-			provider: "anthropic-vertex",
-			baseUrl: "https://us-central1-aiplatform.googleapis.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 15,
-				output: 75,
-				cacheRead: 1.5,
-				cacheWrite: 18.75,
-			},
-			contextWindow: 1000000,
-			maxTokens: 128000,
-		} satisfies Model<"anthropic-vertex">,
-		"claude-sonnet-4-6": {
-			id: "claude-sonnet-4-6",
-			name: "Claude Sonnet 4.6 (Vertex)",
-			api: "anthropic-vertex",
-			provider: "anthropic-vertex",
-			baseUrl: "https://us-central1-aiplatform.googleapis.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.3,
-				cacheWrite: 3.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 64000,
-		} satisfies Model<"anthropic-vertex">,
-		"claude-sonnet-4-6[1m]": {
-			id: "claude-sonnet-4-6[1m]",
-			name: "Claude Sonnet 4.6 1M (Vertex)",
-			api: "anthropic-vertex",
-			provider: "anthropic-vertex",
-			baseUrl: "https://us-central1-aiplatform.googleapis.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.3,
-				cacheWrite: 3.75,
-			},
-			contextWindow: 1000000,
-			maxTokens: 64000,
-		} satisfies Model<"anthropic-vertex">,
-		"claude-sonnet-4-5@20250929": {
-			id: "claude-sonnet-4-5@20250929",
-			name: "Claude Sonnet 4.5 (Vertex)",
-			api: "anthropic-vertex",
-			provider: "anthropic-vertex",
-			baseUrl: "https://us-central1-aiplatform.googleapis.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.3,
-				cacheWrite: 3.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 64000,
-		} satisfies Model<"anthropic-vertex">,
-		"claude-sonnet-4@20250514": {
-			id: "claude-sonnet-4@20250514",
-			name: "Claude Sonnet 4 (Vertex)",
-			api: "anthropic-vertex",
-			provider: "anthropic-vertex",
-			baseUrl: "https://us-central1-aiplatform.googleapis.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.3,
-				cacheWrite: 3.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 64000,
-		} satisfies Model<"anthropic-vertex">,
-		"claude-opus-4-5@20251101": {
-			id: "claude-opus-4-5@20251101",
-			name: "Claude Opus 4.5 (Vertex)",
-			api: "anthropic-vertex",
-			provider: "anthropic-vertex",
-			baseUrl: "https://us-central1-aiplatform.googleapis.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 15,
-				output: 75,
-				cacheRead: 1.5,
-				cacheWrite: 18.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 32000,
-		} satisfies Model<"anthropic-vertex">,
-		"claude-opus-4-1@20250805": {
-			id: "claude-opus-4-1@20250805",
-			name: "Claude Opus 4.1 (Vertex)",
-			api: "anthropic-vertex",
-			provider: "anthropic-vertex",
-			baseUrl: "https://us-central1-aiplatform.googleapis.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 15,
-				output: 75,
-				cacheRead: 1.5,
-				cacheWrite: 18.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 32000,
-		} satisfies Model<"anthropic-vertex">,
-		"claude-opus-4@20250514": {
-			id: "claude-opus-4@20250514",
-			name: "Claude Opus 4 (Vertex)",
-			api: "anthropic-vertex",
-			provider: "anthropic-vertex",
-			baseUrl: "https://us-central1-aiplatform.googleapis.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 15,
-				output: 75,
-				cacheRead: 1.5,
-				cacheWrite: 18.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 32000,
-		} satisfies Model<"anthropic-vertex">,
-		"claude-haiku-4-5@20251001": {
-			id: "claude-haiku-4-5@20251001",
-			name: "Claude Haiku 4.5 (Vertex)",
-			api: "anthropic-vertex",
-			provider: "anthropic-vertex",
-			baseUrl: "https://us-central1-aiplatform.googleapis.com",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.8,
-				output: 4,
-				cacheRead: 0.08,
-				cacheWrite: 1,
-			},
-			contextWindow: 200000,
-			maxTokens: 8192,
-		} satisfies Model<"anthropic-vertex">,
-	},
 	"azure-openai-responses": {
 		"codex-mini-latest": {
 			id: "codex-mini-latest",
@@ -2493,6 +2304,40 @@ export const MODELS = {
 			contextWindow: 272000,
 			maxTokens: 128000,
 		} satisfies Model<"azure-openai-responses">,
+		"gpt-5.4-mini": {
+			id: "gpt-5.4-mini",
+			name: "GPT-5.4 mini",
+			api: "azure-openai-responses",
+			provider: "azure-openai-responses",
+			baseUrl: "",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.75,
+				output: 4.5,
+				cacheRead: 0.075,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"azure-openai-responses">,
+		"gpt-5.4-nano": {
+			id: "gpt-5.4-nano",
+			name: "GPT-5.4 nano",
+			api: "azure-openai-responses",
+			provider: "azure-openai-responses",
+			baseUrl: "",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.2,
+				output: 1.25,
+				cacheRead: 0.02,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"azure-openai-responses">,
 		"gpt-5.4-pro": {
 			id: "gpt-5.4-pro",
 			name: "GPT-5.4 Pro",
@@ -2733,7 +2578,7 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
+			contextWindow: 144000,
 			maxTokens: 32000,
 		} satisfies Model<"anthropic-messages">,
 		"claude-opus-4.5": {
@@ -2751,7 +2596,7 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
+			contextWindow: 160000,
 			maxTokens: 32000,
 		} satisfies Model<"anthropic-messages">,
 		"claude-opus-4.6": {
@@ -2769,7 +2614,7 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
+			contextWindow: 144000,
 			maxTokens: 64000,
 		} satisfies Model<"anthropic-messages">,
 		"claude-sonnet-4": {
@@ -2787,7 +2632,7 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
+			contextWindow: 216000,
 			maxTokens: 16000,
 		} satisfies Model<"anthropic-messages">,
 		"claude-sonnet-4.5": {
@@ -2805,7 +2650,7 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
+			contextWindow: 144000,
 			maxTokens: 32000,
 		} satisfies Model<"anthropic-messages">,
 		"claude-sonnet-4.6": {
@@ -2823,7 +2668,7 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
+			contextWindow: 200000,
 			maxTokens: 32000,
 		} satisfies Model<"anthropic-messages">,
 		"gemini-2.5-pro": {
@@ -2918,7 +2763,7 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 64000,
+			contextWindow: 128000,
 			maxTokens: 16384,
 		} satisfies Model<"openai-completions">,
 		"gpt-4o": {
@@ -2937,8 +2782,8 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 64000,
-			maxTokens: 16384,
+			contextWindow: 128000,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"gpt-5": {
 			id: "gpt-5",
@@ -2973,7 +2818,7 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
+			contextWindow: 264000,
 			maxTokens: 64000,
 		} satisfies Model<"openai-responses">,
 		"gpt-5.1": {
@@ -2991,7 +2836,7 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
+			contextWindow: 264000,
 			maxTokens: 64000,
 		} satisfies Model<"openai-responses">,
 		"gpt-5.1-codex": {
@@ -3009,7 +2854,7 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
+			contextWindow: 400000,
 			maxTokens: 128000,
 		} satisfies Model<"openai-responses">,
 		"gpt-5.1-codex-max": {
@@ -3027,7 +2872,7 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
+			contextWindow: 400000,
 			maxTokens: 128000,
 		} satisfies Model<"openai-responses">,
 		"gpt-5.1-codex-mini": {
@@ -3045,7 +2890,7 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
+			contextWindow: 400000,
 			maxTokens: 128000,
 		} satisfies Model<"openai-responses">,
 		"gpt-5.2": {
@@ -3063,7 +2908,7 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
+			contextWindow: 264000,
 			maxTokens: 64000,
 		} satisfies Model<"openai-responses">,
 		"gpt-5.2-codex": {
@@ -3081,7 +2926,7 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 272000,
+			contextWindow: 400000,
 			maxTokens: 128000,
 		} satisfies Model<"openai-responses">,
 		"gpt-5.3-codex": {
@@ -3120,6 +2965,24 @@ export const MODELS = {
 			contextWindow: 400000,
 			maxTokens: 128000,
 		} satisfies Model<"openai-responses">,
+		"gpt-5.4-mini": {
+			id: "gpt-5.4-mini",
+			name: "GPT-5.4 mini",
+			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: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-responses">,
 		"grok-code-fast-1": {
 			id: "grok-code-fast-1",
 			name: "Grok Code Fast 1",
@@ -3439,10 +3302,10 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
+				input: 0.25,
+				output: 1.5,
+				cacheRead: 0.025,
+				cacheWrite: 1,
 			},
 			contextWindow: 1048576,
 			maxTokens: 65536,
@@ -4703,6 +4566,40 @@ export const MODELS = {
 			contextWindow: 204800,
 			maxTokens: 131072,
 		} satisfies Model<"anthropic-messages">,
+		"MiniMax-M2.7": {
+			id: "MiniMax-M2.7",
+			name: "MiniMax-M2.7",
+			api: "anthropic-messages",
+			provider: "minimax",
+			baseUrl: "https://api.minimax.io/anthropic",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.3,
+				output: 1.2,
+				cacheRead: 0.06,
+				cacheWrite: 0.375,
+			},
+			contextWindow: 204800,
+			maxTokens: 131072,
+		} satisfies Model<"anthropic-messages">,
+		"MiniMax-M2.7-highspeed": {
+			id: "MiniMax-M2.7-highspeed",
+			name: "MiniMax-M2.7-highspeed",
+			api: "anthropic-messages",
+			provider: "minimax",
+			baseUrl: "https://api.minimax.io/anthropic",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.6,
+				output: 2.4,
+				cacheRead: 0.06,
+				cacheWrite: 0.375,
+			},
+			contextWindow: 204800,
+			maxTokens: 131072,
+		} satisfies Model<"anthropic-messages">,
 	},
 	"minimax-cn": {
 		"MiniMax-M2": {
@@ -4773,11 +4670,45 @@ export const MODELS = {
 			contextWindow: 204800,
 			maxTokens: 131072,
 		} satisfies Model<"anthropic-messages">,
+		"MiniMax-M2.7": {
+			id: "MiniMax-M2.7",
+			name: "MiniMax-M2.7",
+			api: "anthropic-messages",
+			provider: "minimax-cn",
+			baseUrl: "https://api.minimaxi.com/anthropic",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.3,
+				output: 1.2,
+				cacheRead: 0.06,
+				cacheWrite: 0.375,
+			},
+			contextWindow: 204800,
+			maxTokens: 131072,
+		} satisfies Model<"anthropic-messages">,
+		"MiniMax-M2.7-highspeed": {
+			id: "MiniMax-M2.7-highspeed",
+			name: "MiniMax-M2.7-highspeed",
+			api: "anthropic-messages",
+			provider: "minimax-cn",
+			baseUrl: "https://api.minimaxi.com/anthropic",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.6,
+				output: 2.4,
+				cacheRead: 0.06,
+				cacheWrite: 0.375,
+			},
+			contextWindow: 204800,
+			maxTokens: 131072,
+		} satisfies Model<"anthropic-messages">,
 	},
 	"mistral": {
 		"codestral-latest": {
 			id: "codestral-latest",
-			name: "Codestral",
+			name: "Codestral (latest)",
 			api: "mistral-conversations",
 			provider: "mistral",
 			baseUrl: "https://api.mistral.ai",
@@ -4828,7 +4759,7 @@ export const MODELS = {
 		} satisfies Model<"mistral-conversations">,
 		"devstral-medium-latest": {
 			id: "devstral-medium-latest",
-			name: "Devstral 2",
+			name: "Devstral 2 (latest)",
 			api: "mistral-conversations",
 			provider: "mistral",
 			baseUrl: "https://api.mistral.ai",
@@ -4896,7 +4827,7 @@ export const MODELS = {
 		} satisfies Model<"mistral-conversations">,
 		"magistral-medium-latest": {
 			id: "magistral-medium-latest",
-			name: "Magistral Medium",
+			name: "Magistral Medium (latest)",
 			api: "mistral-conversations",
 			provider: "mistral",
 			baseUrl: "https://api.mistral.ai",
@@ -4930,7 +4861,7 @@ export const MODELS = {
 		} satisfies Model<"mistral-conversations">,
 		"ministral-3b-latest": {
 			id: "ministral-3b-latest",
-			name: "Ministral 3B",
+			name: "Ministral 3B (latest)",
 			api: "mistral-conversations",
 			provider: "mistral",
 			baseUrl: "https://api.mistral.ai",
@@ -4947,7 +4878,7 @@ export const MODELS = {
 		} satisfies Model<"mistral-conversations">,
 		"ministral-8b-latest": {
 			id: "ministral-8b-latest",
-			name: "Ministral 8B",
+			name: "Ministral 8B (latest)",
 			api: "mistral-conversations",
 			provider: "mistral",
 			baseUrl: "https://api.mistral.ai",
@@ -4998,7 +4929,7 @@ export const MODELS = {
 		} satisfies Model<"mistral-conversations">,
 		"mistral-large-latest": {
 			id: "mistral-large-latest",
-			name: "Mistral Large",
+			name: "Mistral Large (latest)",
 			api: "mistral-conversations",
 			provider: "mistral",
 			baseUrl: "https://api.mistral.ai",
@@ -5049,7 +4980,7 @@ export const MODELS = {
 		} satisfies Model<"mistral-conversations">,
 		"mistral-medium-latest": {
 			id: "mistral-medium-latest",
-			name: "Mistral Medium",
+			name: "Mistral Medium (latest)",
 			api: "mistral-conversations",
 			provider: "mistral",
 			baseUrl: "https://api.mistral.ai",
@@ -5100,7 +5031,7 @@ export const MODELS = {
 		} satisfies Model<"mistral-conversations">,
 		"mistral-small-latest": {
 			id: "mistral-small-latest",
-			name: "Mistral Small",
+			name: "Mistral Small (latest)",
 			api: "mistral-conversations",
 			provider: "mistral",
 			baseUrl: "https://api.mistral.ai",
@@ -5185,7 +5116,7 @@ export const MODELS = {
 		} satisfies Model<"mistral-conversations">,
 		"pixtral-large-latest": {
 			id: "pixtral-large-latest",
-			name: "Pixtral Large",
+			name: "Pixtral Large (latest)",
 			api: "mistral-conversations",
 			provider: "mistral",
 			baseUrl: "https://api.mistral.ai",
@@ -5695,6 +5626,40 @@ export const MODELS = {
 			contextWindow: 272000,
 			maxTokens: 128000,
 		} satisfies Model<"openai-responses">,
+		"gpt-5.4-mini": {
+			id: "gpt-5.4-mini",
+			name: "GPT-5.4 mini",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.75,
+				output: 4.5,
+				cacheRead: 0.075,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-responses">,
+		"gpt-5.4-nano": {
+			id: "gpt-5.4-nano",
+			name: "GPT-5.4 nano",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.2,
+				output: 1.25,
+				cacheRead: 0.02,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-responses">,
 		"gpt-5.4-pro": {
 			id: "gpt-5.4-pro",
 			name: "GPT-5.4 Pro",
@@ -6087,7 +6052,7 @@ export const MODELS = {
 				cacheRead: 0.5,
 				cacheWrite: 6.25,
 			},
-			contextWindow: 200000,
+			contextWindow: 1000000,
 			maxTokens: 128000,
 		} satisfies Model<"anthropic-messages">,
 		"claude-sonnet-4": {
@@ -6158,23 +6123,6 @@ export const MODELS = {
 			contextWindow: 1048576,
 			maxTokens: 65536,
 		} satisfies Model<"google-generative-ai">,
-		"gemini-3-pro": {
-			id: "gemini-3-pro",
-			name: "Gemini 3 Pro",
-			api: "google-generative-ai",
-			provider: "opencode",
-			baseUrl: "https://opencode.ai/zen/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 2,
-				output: 12,
-				cacheRead: 0.2,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		} satisfies Model<"google-generative-ai">,
 		"gemini-3.1-pro": {
 			id: "gemini-3.1-pro",
 			name: "Gemini 3.1 Pro Preview",
@@ -6192,40 +6140,6 @@ export const MODELS = {
 			contextWindow: 1048576,
 			maxTokens: 65536,
 		} satisfies Model<"google-generative-ai">,
-		"glm-4.6": {
-			id: "glm-4.6",
-			name: "GLM-4.6",
-			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": {
-			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-5": {
 			id: "glm-5",
 			name: "GLM-5",
@@ -6430,6 +6344,40 @@ export const MODELS = {
 			contextWindow: 272000,
 			maxTokens: 128000,
 		} satisfies Model<"openai-responses">,
+		"gpt-5.4-mini": {
+			id: "gpt-5.4-mini",
+			name: "GPT-5.4 Mini",
+			api: "openai-responses",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.75,
+				output: 4.5,
+				cacheRead: 0.075,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-responses">,
+		"gpt-5.4-nano": {
+			id: "gpt-5.4-nano",
+			name: "GPT-5.4 Nano",
+			api: "openai-responses",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.2,
+				output: 1.25,
+				cacheRead: 0.02,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-responses">,
 		"gpt-5.4-pro": {
 			id: "gpt-5.4-pro",
 			name: "GPT-5.4 Pro",
@@ -6464,22 +6412,39 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
-		"minimax-m2.1": {
-			id: "minimax-m2.1",
-			name: "MiniMax M2.1",
+		"mimo-v2-omni-free": {
+			id: "mimo-v2-omni-free",
+			name: "MiMo V2 Omni Free",
+			api: "openai-completions",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 64000,
+		} satisfies Model<"openai-completions">,
+		"mimo-v2-pro-free": {
+			id: "mimo-v2-pro-free",
+			name: "MiMo V2 Pro Free",
 			api: "openai-completions",
 			provider: "opencode",
 			baseUrl: "https://opencode.ai/zen/v1",
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.3,
-				output: 1.2,
-				cacheRead: 0.1,
+				input: 0,
+				output: 0,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 204800,
-			maxTokens: 131072,
+			contextWindow: 1048576,
+			maxTokens: 64000,
 		} satisfies Model<"openai-completions">,
 		"minimax-m2.5": {
 			id: "minimax-m2.5",
@@ -6515,6 +6480,23 @@ export const MODELS = {
 			contextWindow: 204800,
 			maxTokens: 131072,
 		} satisfies Model<"anthropic-messages">,
+		"nemotron-3-super-free": {
+			id: "nemotron-3-super-free",
+			name: "Nemotron 3 Super Free",
+			api: "openai-completions",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1000000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
 	},
 	"opencode-go": {
 		"glm-5": {
@@ -6568,6 +6550,23 @@ export const MODELS = {
 			contextWindow: 204800,
 			maxTokens: 131072,
 		} satisfies Model<"anthropic-messages">,
+		"minimax-m2.7": {
+			id: "minimax-m2.7",
+			name: "MiniMax M2.7",
+			api: "anthropic-messages",
+			provider: "opencode-go",
+			baseUrl: "https://opencode.ai/zen/go",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.3,
+				output: 1.2,
+				cacheRead: 0.06,
+				cacheWrite: 0,
+			},
+			contextWindow: 204800,
+			maxTokens: 131072,
+		} satisfies Model<"anthropic-messages">,
 	},
 	"openrouter": {
 		"ai21/jamba-large-1.7": {
@@ -7080,6 +7079,23 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 32768,
 		} satisfies Model<"openai-completions">,
+		"bytedance-seed/seed-2.0-lite": {
+			id: "bytedance-seed/seed-2.0-lite",
+			name: "ByteDance Seed: Seed-2.0-Lite",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.25,
+				output: 2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
 		"bytedance-seed/seed-2.0-mini": {
 			id: "bytedance-seed/seed-2.0-mini",
 			name: "ByteDance Seed: Seed-2.0-Mini",
@@ -7159,11 +7175,11 @@ export const MODELS = {
 			cost: {
 				input: 0.19999999999999998,
 				output: 0.77,
-				cacheRead: 0.13,
+				cacheRead: 0.135,
 				cacheWrite: 0,
 			},
 			contextWindow: 163840,
-			maxTokens: 163840,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"deepseek/deepseek-chat-v3.1": {
 			id: "deepseek/deepseek-chat-v3.1",
@@ -7233,23 +7249,6 @@ export const MODELS = {
 			contextWindow: 163840,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
-		"deepseek/deepseek-v3.1-terminus:exacto": {
-			id: "deepseek/deepseek-v3.1-terminus:exacto",
-			name: "DeepSeek: DeepSeek V3.1 Terminus (exacto)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.21,
-				output: 0.7899999999999999,
-				cacheRead: 0.16799999999999998,
-				cacheWrite: 0,
-			},
-			contextWindow: 163840,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
 		"deepseek/deepseek-v3.2": {
 			id: "deepseek/deepseek-v3.2",
 			name: "DeepSeek: DeepSeek V3.2",
@@ -7259,13 +7258,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.25,
-				output: 0.39999999999999997,
-				cacheRead: 0,
+				input: 0.26,
+				output: 0.38,
+				cacheRead: 0.13,
 				cacheWrite: 0,
 			},
 			contextWindow: 163840,
-			maxTokens: 65536,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"deepseek/deepseek-v3.2-exp": {
 			id: "deepseek/deepseek-v3.2-exp",
@@ -7522,40 +7521,6 @@ export const MODELS = {
 			contextWindow: 1048576,
 			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
-		"google/gemma-3-27b-it": {
-			id: "google/gemma-3-27b-it",
-			name: "Google: Gemma 3 27B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.04,
-				output: 0.15,
-				cacheRead: 0.02,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
-		"google/gemma-3-27b-it:free": {
-			id: "google/gemma-3-27b-it:free",
-			name: "Google: Gemma 3 27B (free)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
 		"inception/mercury": {
 			id: "inception/mercury",
 			name: "Inception: Mercury",
@@ -7658,23 +7623,6 @@ export const MODELS = {
 			contextWindow: 8192,
 			maxTokens: 16384,
 		} satisfies Model<"openai-completions">,
-		"meta-llama/llama-3.1-405b-instruct": {
-			id: "meta-llama/llama-3.1-405b-instruct",
-			name: "Meta: Llama 3.1 405B Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 4,
-				output: 4,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
 		"meta-llama/llama-3.1-70b-instruct": {
 			id: "meta-llama/llama-3.1-70b-instruct",
 			name: "Meta: Llama 3.1 70B Instruct",
@@ -7740,8 +7688,8 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
-			maxTokens: 128000,
+			contextWindow: 65536,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"meta-llama/llama-4-maverick": {
 			id: "meta-llama/llama-4-maverick",
@@ -7837,14 +7785,48 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.295,
-				output: 1.2,
-				cacheRead: 0.03,
+				input: 0.19999999999999998,
+				output: 1.17,
+				cacheRead: 0.09999999999999999,
+				cacheWrite: 0,
+			},
+			contextWindow: 196608,
+			maxTokens: 65536,
+		} satisfies Model<"openai-completions">,
+		"minimax/minimax-m2.5:free": {
+			id: "minimax/minimax-m2.5:free",
+			name: "MiniMax: MiniMax M2.5 (free)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 196608,
 			maxTokens: 196608,
 		} satisfies Model<"openai-completions">,
+		"minimax/minimax-m2.7": {
+			id: "minimax/minimax-m2.7",
+			name: "MiniMax: MiniMax M2.7",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.3,
+				output: 1.2,
+				cacheRead: 0.06,
+				cacheWrite: 0,
+			},
+			contextWindow: 204800,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
 		"mistralai/codestral-2508": {
 			id: "mistralai/codestral-2508",
 			name: "Mistral: Codestral 2508",
@@ -7856,7 +7838,7 @@ export const MODELS = {
 			cost: {
 				input: 0.3,
 				output: 0.8999999999999999,
-				cacheRead: 0,
+				cacheRead: 0.03,
 				cacheWrite: 0,
 			},
 			contextWindow: 256000,
@@ -7873,7 +7855,7 @@ export const MODELS = {
 			cost: {
 				input: 0.39999999999999997,
 				output: 2,
-				cacheRead: 0,
+				cacheRead: 0.04,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
@@ -7890,7 +7872,7 @@ export const MODELS = {
 			cost: {
 				input: 0.39999999999999997,
 				output: 2,
-				cacheRead: 0,
+				cacheRead: 0.04,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
@@ -7907,7 +7889,7 @@ export const MODELS = {
 			cost: {
 				input: 0.09999999999999999,
 				output: 0.3,
-				cacheRead: 0,
+				cacheRead: 0.01,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
@@ -7924,7 +7906,7 @@ export const MODELS = {
 			cost: {
 				input: 0.19999999999999998,
 				output: 0.19999999999999998,
-				cacheRead: 0,
+				cacheRead: 0.02,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
@@ -7941,7 +7923,7 @@ export const MODELS = {
 			cost: {
 				input: 0.09999999999999999,
 				output: 0.09999999999999999,
-				cacheRead: 0,
+				cacheRead: 0.01,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
@@ -7958,7 +7940,7 @@ export const MODELS = {
 			cost: {
 				input: 0.15,
 				output: 0.15,
-				cacheRead: 0,
+				cacheRead: 0.015,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
@@ -7975,7 +7957,7 @@ export const MODELS = {
 			cost: {
 				input: 2,
 				output: 6,
-				cacheRead: 0,
+				cacheRead: 0.19999999999999998,
 				cacheWrite: 0,
 			},
 			contextWindow: 128000,
@@ -7992,7 +7974,7 @@ export const MODELS = {
 			cost: {
 				input: 2,
 				output: 6,
-				cacheRead: 0,
+				cacheRead: 0.19999999999999998,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
@@ -8009,7 +7991,7 @@ export const MODELS = {
 			cost: {
 				input: 2,
 				output: 6,
-				cacheRead: 0,
+				cacheRead: 0.19999999999999998,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
@@ -8026,7 +8008,7 @@ export const MODELS = {
 			cost: {
 				input: 0.5,
 				output: 1.5,
-				cacheRead: 0,
+				cacheRead: 0.049999999999999996,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
@@ -8043,7 +8025,7 @@ export const MODELS = {
 			cost: {
 				input: 0.39999999999999997,
 				output: 2,
-				cacheRead: 0,
+				cacheRead: 0.04,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
@@ -8060,7 +8042,7 @@ export const MODELS = {
 			cost: {
 				input: 0.39999999999999997,
 				output: 2,
-				cacheRead: 0,
+				cacheRead: 0.04,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
@@ -8094,7 +8076,7 @@ export const MODELS = {
 			cost: {
 				input: 0.19999999999999998,
 				output: 0.6,
-				cacheRead: 0,
+				cacheRead: 0.02,
 				cacheWrite: 0,
 			},
 			contextWindow: 32768,
@@ -8117,6 +8099,23 @@ export const MODELS = {
 			contextWindow: 32768,
 			maxTokens: 16384,
 		} satisfies Model<"openai-completions">,
+		"mistralai/mistral-small-2603": {
+			id: "mistralai/mistral-small-2603",
+			name: "Mistral: Mistral Small 4",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.15,
+				output: 0.6,
+				cacheRead: 0.015,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
 		"mistralai/mistral-small-3.1-24b-instruct:free": {
 			id: "mistralai/mistral-small-3.1-24b-instruct:free",
 			name: "Mistral: Mistral Small 3.1 24B (free)",
@@ -8143,13 +8142,13 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text", "image"],
 			cost: {
-				input: 0.06,
-				output: 0.18,
-				cacheRead: 0.03,
+				input: 0.075,
+				output: 0.19999999999999998,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
-			maxTokens: 131072,
+			contextWindow: 128000,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"mistralai/mistral-small-creative": {
 			id: "mistralai/mistral-small-creative",
@@ -8162,7 +8161,7 @@ export const MODELS = {
 			cost: {
 				input: 0.09999999999999999,
 				output: 0.3,
-				cacheRead: 0,
+				cacheRead: 0.01,
 				cacheWrite: 0,
 			},
 			contextWindow: 32768,
@@ -8179,7 +8178,7 @@ export const MODELS = {
 			cost: {
 				input: 2,
 				output: 6,
-				cacheRead: 0,
+				cacheRead: 0.19999999999999998,
 				cacheWrite: 0,
 			},
 			contextWindow: 65536,
@@ -8213,7 +8212,7 @@ export const MODELS = {
 			cost: {
 				input: 2,
 				output: 6,
-				cacheRead: 0,
+				cacheRead: 0.19999999999999998,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
@@ -8230,7 +8229,7 @@ export const MODELS = {
 			cost: {
 				input: 0.09999999999999999,
 				output: 0.3,
-				cacheRead: 0,
+				cacheRead: 0.01,
 				cacheWrite: 0,
 			},
 			contextWindow: 32000,
@@ -8270,23 +8269,6 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
-		"moonshotai/kimi-k2-0905:exacto": {
-			id: "moonshotai/kimi-k2-0905:exacto",
-			name: "MoonshotAI: Kimi K2 0905 (exacto)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.6,
-				output: 2.5,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
 		"moonshotai/kimi-k2-thinking": {
 			id: "moonshotai/kimi-k2-thinking",
 			name: "MoonshotAI: Kimi K2 Thinking",
@@ -8406,6 +8388,40 @@ export const MODELS = {
 			contextWindow: 256000,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
+		"nvidia/nemotron-3-super-120b-a12b": {
+			id: "nvidia/nemotron-3-super-120b-a12b",
+			name: "NVIDIA: Nemotron 3 Super",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.09999999999999999,
+				output: 0.5,
+				cacheRead: 0.04,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"nvidia/nemotron-3-super-120b-a12b:free": {
+			id: "nvidia/nemotron-3-super-120b-a12b:free",
+			name: "NVIDIA: Nemotron 3 Super (free)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
 		"nvidia/nemotron-nano-12b-v2-vl:free": {
 			id: "nvidia/nemotron-nano-12b-v2-vl:free",
 			name: "NVIDIA: Nemotron Nano 12B 2 VL (free)",
@@ -9103,6 +9119,40 @@ export const MODELS = {
 			contextWindow: 1050000,
 			maxTokens: 128000,
 		} satisfies Model<"openai-completions">,
+		"openai/gpt-5.4-mini": {
+			id: "openai/gpt-5.4-mini",
+			name: "OpenAI: GPT-5.4 Mini",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.75,
+				output: 4.5,
+				cacheRead: 0.075,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-5.4-nano": {
+			id: "openai/gpt-5.4-nano",
+			name: "OpenAI: GPT-5.4 Nano",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.19999999999999998,
+				output: 1.25,
+				cacheRead: 0.02,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
 		"openai/gpt-5.4-pro": {
 			id: "openai/gpt-5.4-pro",
 			name: "OpenAI: GPT-5.4 Pro",
@@ -9137,23 +9187,6 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
-		"openai/gpt-oss-120b:exacto": {
-			id: "openai/gpt-oss-120b:exacto",
-			name: "OpenAI: gpt-oss-120b (exacto)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.039,
-				output: 0.19,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
 		"openai/gpt-oss-120b:free": {
 			id: "openai/gpt-oss-120b:free",
 			name: "OpenAI: gpt-oss-120b (free)",
@@ -9181,12 +9214,12 @@ export const MODELS = {
 			input: ["text"],
 			cost: {
 				input: 0.03,
-				output: 0.14,
-				cacheRead: 0,
+				output: 0.11,
+				cacheRead: 0.015,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
-			maxTokens: 4096,
+			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
 		"openai/gpt-oss-20b:free": {
 			id: "openai/gpt-oss-20b:free",
@@ -9228,7 +9261,7 @@ export const MODELS = {
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
+			reasoning: true,
 			input: ["text", "image"],
 			cost: {
 				input: 15,
@@ -9279,7 +9312,7 @@ export const MODELS = {
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
+			reasoning: true,
 			input: ["text"],
 			cost: {
 				input: 1.1,
@@ -9296,7 +9329,7 @@ export const MODELS = {
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
+			reasoning: true,
 			input: ["text"],
 			cost: {
 				input: 1.1,
@@ -9486,9 +9519,9 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.39999999999999997,
-				output: 1.2,
-				cacheRead: 0.08,
+				input: 0.26,
+				output: 0.78,
+				cacheRead: 0.052000000000000005,
 				cacheWrite: 0,
 			},
 			contextWindow: 1000000,
@@ -9554,8 +9587,8 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text", "image"],
 			cost: {
-				input: 0.7999999999999999,
-				output: 3.1999999999999997,
+				input: 0.52,
+				output: 2.08,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -9622,13 +9655,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.11,
-				output: 0.6,
-				cacheRead: 0.055,
+				input: 0.14950000000000002,
+				output: 1.495,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 262144,
-			maxTokens: 262144,
+			contextWindow: 131072,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"qwen/qwen3-30b-a3b": {
 			id: "qwen/qwen3-30b-a3b",
@@ -9673,13 +9706,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.051,
-				output: 0.33999999999999997,
-				cacheRead: 0,
+				input: 0.08,
+				output: 0.39999999999999997,
+				cacheRead: 0.08,
 				cacheWrite: 0,
 			},
-			contextWindow: 32768,
-			maxTokens: 4096,
+			contextWindow: 131072,
+			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
 		"qwen/qwen3-32b": {
 			id: "qwen/qwen3-32b",
@@ -9817,23 +9850,6 @@ export const MODELS = {
 			contextWindow: 1000000,
 			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-coder:exacto": {
-			id: "qwen/qwen3-coder:exacto",
-			name: "Qwen: Qwen3 Coder 480B A35B (exacto)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.22,
-				output: 1.7999999999999998,
-				cacheRead: 0.022,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
 		"qwen/qwen3-coder:free": {
 			id: "qwen/qwen3-coder:free",
 			name: "Qwen: Qwen3 Coder 480B A35B (free)",
@@ -9860,9 +9876,9 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 1.2,
-				output: 6,
-				cacheRead: 0.24,
+				input: 0.78,
+				output: 3.9,
+				cacheRead: 0.156,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
@@ -9928,13 +9944,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.15,
-				output: 1.2,
+				input: 0.0975,
+				output: 0.78,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
-			maxTokens: 4096,
+			contextWindow: 131072,
+			maxTokens: 32768,
 		} satisfies Model<"openai-completions">,
 		"qwen/qwen3-vl-235b-a22b-instruct": {
 			id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -9962,8 +9978,8 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0,
-				output: 0,
+				input: 0.26,
+				output: 2.6,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -9996,8 +10012,8 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0,
-				output: 0,
+				input: 0.13,
+				output: 1.56,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -10123,6 +10139,23 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
+		"qwen/qwen3.5-9b": {
+			id: "qwen/qwen3.5-9b",
+			name: "Qwen: Qwen3.5-9B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.049999999999999996,
+				output: 0.15,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
 		"qwen/qwen3.5-flash-02-23": {
 			id: "qwen/qwen3.5-flash-02-23",
 			name: "Qwen: Qwen3.5-Flash",
@@ -10132,8 +10165,8 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0.09999999999999999,
-				output: 0.39999999999999997,
+				input: 0.065,
+				output: 0.26,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -10167,12 +10200,12 @@ export const MODELS = {
 			input: ["text"],
 			cost: {
 				input: 0.15,
-				output: 0.39999999999999997,
+				output: 0.58,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 32768,
-			maxTokens: 32768,
+			contextWindow: 131072,
+			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
 		"relace/relace-search": {
 			id: "relace/relace-search",
@@ -10217,13 +10250,13 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.65,
-				output: 0.75,
+				input: 0.85,
+				output: 0.85,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 32768,
-			maxTokens: 32768,
+			contextWindow: 131072,
+			maxTokens: 16384,
 		} satisfies Model<"openai-completions">,
 		"stepfun/step-3.5-flash": {
 			id: "stepfun/step-3.5-flash",
@@ -10302,9 +10335,9 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.25,
-				output: 0.85,
-				cacheRead: 0.125,
+				input: 0.3,
+				output: 1.1,
+				cacheRead: 0.15,
 				cacheWrite: 0,
 			},
 			contextWindow: 163840,
@@ -10446,6 +10479,23 @@ export const MODELS = {
 			contextWindow: 2000000,
 			maxTokens: 30000,
 		} satisfies Model<"openai-completions">,
+		"x-ai/grok-4.20-beta": {
+			id: "x-ai/grok-4.20-beta",
+			name: "xAI: Grok 4.20 Beta",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 2,
+				output: 6,
+				cacheRead: 0.19999999999999998,
+				cacheWrite: 0,
+			},
+			contextWindow: 2000000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
 		"x-ai/grok-code-fast-1": {
 			id: "x-ai/grok-code-fast-1",
 			name: "xAI: Grok Code Fast 1",
@@ -10480,6 +10530,40 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
+		"xiaomi/mimo-v2-omni": {
+			id: "xiaomi/mimo-v2-omni",
+			name: "Xiaomi: MiMo-V2-Omni",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.39999999999999997,
+				output: 2,
+				cacheRead: 0.08,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 65536,
+		} satisfies Model<"openai-completions">,
+		"xiaomi/mimo-v2-pro": {
+			id: "xiaomi/mimo-v2-pro",
+			name: "Xiaomi: MiMo-V2-Pro",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 1,
+				output: 3,
+				cacheRead: 0.19999999999999998,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
 		"z-ai/glm-4-32b": {
 			id: "z-ai/glm-4-32b",
 			name: "Z.ai: GLM 4 32B ",
@@ -10582,23 +10666,6 @@ export const MODELS = {
 			contextWindow: 204800,
 			maxTokens: 204800,
 		} satisfies Model<"openai-completions">,
-		"z-ai/glm-4.6:exacto": {
-			id: "z-ai/glm-4.6:exacto",
-			name: "Z.ai: GLM 4.6 (exacto)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.44,
-				output: 1.76,
-				cacheRead: 0.11,
-				cacheWrite: 0,
-			},
-			contextWindow: 204800,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
 		"z-ai/glm-4.6v": {
 			id: "z-ai/glm-4.6v",
 			name: "Z.ai: GLM 4.6V",
@@ -10625,13 +10692,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.38,
-				output: 1.9800000000000002,
-				cacheRead: 0.19,
+				input: 0.39,
+				output: 1.75,
+				cacheRead: 0.195,
 				cacheWrite: 0,
 			},
 			contextWindow: 202752,
-			maxTokens: 4096,
+			maxTokens: 65535,
 		} satisfies Model<"openai-completions">,
 		"z-ai/glm-4.7-flash": {
 			id: "z-ai/glm-4.7-flash",
@@ -10664,8 +10731,25 @@ export const MODELS = {
 				cacheRead: 0.119,
 				cacheWrite: 0,
 			},
+			contextWindow: 80000,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+		"z-ai/glm-5-turbo": {
+			id: "z-ai/glm-5-turbo",
+			name: "Z.ai: GLM 5 Turbo",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.96,
+				output: 3.1999999999999997,
+				cacheRead: 0.192,
+				cacheWrite: 0,
+			},
 			contextWindow: 202752,
-			maxTokens: 4096,
+			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
 	},
 	"vercel-ai-gateway": {
@@ -10678,7 +10762,7 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.06,
+				input: 0.12,
 				output: 0.24,
 				cacheRead: 0,
 				cacheWrite: 0,
@@ -10729,13 +10813,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.09999999999999999,
-				output: 0.3,
-				cacheRead: 0,
+				input: 0.29,
+				output: 0.59,
+				cacheRead: 0.145,
 				cacheWrite: 0,
 			},
-			contextWindow: 40960,
-			maxTokens: 16384,
+			contextWindow: 131072,
+			maxTokens: 40960,
 		} satisfies Model<"anthropic-messages">,
 		"alibaba/qwen3-235b-a22b-thinking": {
 			id: "alibaba/qwen3-235b-a22b-thinking",
@@ -10746,9 +10830,9 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0.3,
-				output: 2.9000000000000004,
-				cacheRead: 0,
+				input: 0.22999999999999998,
+				output: 2.3,
+				cacheRead: 0.19999999999999998,
 				cacheWrite: 0,
 			},
 			contextWindow: 262114,
@@ -10765,7 +10849,7 @@ export const MODELS = {
 			cost: {
 				input: 0.39999999999999997,
 				output: 1.5999999999999999,
-				cacheRead: 0,
+				cacheRead: 0.022,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
@@ -10780,13 +10864,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.07,
-				output: 0.27,
+				input: 0.15,
+				output: 0.6,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 160000,
-			maxTokens: 32768,
+			contextWindow: 262144,
+			maxTokens: 8192,
 		} satisfies Model<"anthropic-messages">,
 		"alibaba/qwen3-coder-next": {
 			id: "alibaba/qwen3-coder-next",
@@ -10794,7 +10878,7 @@ export const MODELS = {
 			api: "anthropic-messages",
 			provider: "vercel-ai-gateway",
 			baseUrl: "https://ai-gateway.vercel.sh",
-			reasoning: true,
+			reasoning: false,
 			input: ["text"],
 			cost: {
 				input: 0.5,
@@ -10822,6 +10906,23 @@ export const MODELS = {
 			contextWindow: 1000000,
 			maxTokens: 65536,
 		} satisfies Model<"anthropic-messages">,
+		"alibaba/qwen3-max": {
+			id: "alibaba/qwen3-max",
+			name: "Qwen3 Max",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 1.2,
+				output: 6,
+				cacheRead: 0.24,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 32768,
+		} satisfies Model<"anthropic-messages">,
 		"alibaba/qwen3-max-preview": {
 			id: "alibaba/qwen3-max-preview",
 			name: "Qwen3 Max Preview",
@@ -10969,8 +11070,8 @@ export const MODELS = {
 			cost: {
 				input: 3,
 				output: 15,
-				cacheRead: 0,
-				cacheWrite: 0,
+				cacheRead: 0.3,
+				cacheWrite: 3.75,
 			},
 			contextWindow: 200000,
 			maxTokens: 8192,
@@ -11179,6 +11280,23 @@ export const MODELS = {
 			contextWindow: 256000,
 			maxTokens: 8000,
 		} satisfies Model<"anthropic-messages">,
+		"deepseek/deepseek-r1": {
+			id: "deepseek/deepseek-r1",
+			name: "DeepSeek-R1",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 1.35,
+				output: 5.4,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 8192,
+		} satisfies Model<"anthropic-messages">,
 		"deepseek/deepseek-v3": {
 			id: "deepseek/deepseek-v3",
 			name: "DeepSeek V3 0324",
@@ -11205,13 +11323,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.21,
-				output: 0.7899999999999999,
+				input: 0.5,
+				output: 1.5,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 163840,
-			maxTokens: 128000,
+			maxTokens: 16384,
 		} satisfies Model<"anthropic-messages">,
 		"deepseek/deepseek-v3.1-terminus": {
 			id: "deepseek/deepseek-v3.1-terminus",
@@ -11224,7 +11342,7 @@ export const MODELS = {
 			cost: {
 				input: 0.27,
 				output: 1,
-				cacheRead: 0,
+				cacheRead: 0.135,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
@@ -11239,9 +11357,9 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.26,
-				output: 0.38,
-				cacheRead: 0.13,
+				input: 0.28,
+				output: 0.42,
+				cacheRead: 0.028,
 				cacheWrite: 0,
 			},
 			contextWindow: 128000,
@@ -11264,6 +11382,40 @@ 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: 0.15,
+				output: 0.6,
+				cacheRead: 0.024999999999999998,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			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: 0.02,
+				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",
@@ -11271,11 +11423,11 @@ export const MODELS = {
 			provider: "vercel-ai-gateway",
 			baseUrl: "https://ai-gateway.vercel.sh",
 			reasoning: true,
-			input: ["text"],
+			input: ["text", "image"],
 			cost: {
 				input: 0.3,
 				output: 2.5,
-				cacheRead: 0,
+				cacheRead: 0.03,
 				cacheWrite: 0,
 			},
 			contextWindow: 1000000,
@@ -11298,40 +11450,6 @@ export const MODELS = {
 			contextWindow: 1048576,
 			maxTokens: 65536,
 		} satisfies Model<"anthropic-messages">,
-		"google/gemini-2.5-flash-lite-preview-09-2025": {
-			id: "google/gemini-2.5-flash-lite-preview-09-2025",
-			name: "Gemini 2.5 Flash Lite Preview 09-2025",
-			api: "anthropic-messages",
-			provider: "vercel-ai-gateway",
-			baseUrl: "https://ai-gateway.vercel.sh",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.09999999999999999,
-				output: 0.39999999999999997,
-				cacheRead: 0.01,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		} satisfies Model<"anthropic-messages">,
-		"google/gemini-2.5-flash-preview-09-2025": {
-			id: "google/gemini-2.5-flash-preview-09-2025",
-			name: "Gemini 2.5 Flash Preview 09-2025",
-			api: "anthropic-messages",
-			provider: "vercel-ai-gateway",
-			baseUrl: "https://ai-gateway.vercel.sh",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.3,
-				output: 2.5,
-				cacheRead: 0.03,
-				cacheWrite: 0,
-			},
-			contextWindow: 1000000,
-			maxTokens: 65536,
-		} satisfies Model<"anthropic-messages">,
 		"google/gemini-2.5-pro": {
 			id: "google/gemini-2.5-pro",
 			name: "Gemini 2.5 Pro",
@@ -11339,11 +11457,11 @@ export const MODELS = {
 			provider: "vercel-ai-gateway",
 			baseUrl: "https://ai-gateway.vercel.sh",
 			reasoning: true,
-			input: ["text"],
+			input: ["text", "image"],
 			cost: {
 				input: 1.25,
 				output: 10,
-				cacheRead: 0,
+				cacheRead: 0.125,
 				cacheWrite: 0,
 			},
 			contextWindow: 1048576,
@@ -11364,7 +11482,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 1000000,
-			maxTokens: 64000,
+			maxTokens: 65000,
 		} satisfies Model<"anthropic-messages">,
 		"google/gemini-3-pro-preview": {
 			id: "google/gemini-3-pro-preview",
@@ -11466,7 +11584,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 128000,
-			maxTokens: 8192,
+			maxTokens: 100000,
 		} satisfies Model<"anthropic-messages">,
 		"meituan/longcat-flash-thinking": {
 			id: "meituan/longcat-flash-thinking",
@@ -11494,13 +11612,13 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.39999999999999997,
-				output: 0.39999999999999997,
+				input: 0.72,
+				output: 0.72,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
-			maxTokens: 16384,
+			contextWindow: 128000,
+			maxTokens: 8192,
 		} satisfies Model<"anthropic-messages">,
 		"meta/llama-3.1-8b": {
 			id: "meta/llama-3.1-8b",
@@ -11511,12 +11629,12 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.03,
-				output: 0.049999999999999996,
-				cacheRead: 0,
+				input: 0.09999999999999999,
+				output: 0.09999999999999999,
+				cacheRead: 0.09999999999999999,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
+			contextWindow: 128000,
 			maxTokens: 16384,
 		} satisfies Model<"anthropic-messages">,
 		"meta/llama-3.2-11b": {
@@ -11579,12 +11697,12 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text", "image"],
 			cost: {
-				input: 0.15,
-				output: 0.6,
+				input: 0.24,
+				output: 0.9700000000000001,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
+			contextWindow: 128000,
 			maxTokens: 8192,
 		} satisfies Model<"anthropic-messages">,
 		"meta/llama-4-scout": {
@@ -11596,12 +11714,12 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text", "image"],
 			cost: {
-				input: 0.08,
-				output: 0.3,
+				input: 0.16999999999999998,
+				output: 0.66,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
+			contextWindow: 128000,
 			maxTokens: 8192,
 		} satisfies Model<"anthropic-messages">,
 		"minimax/minimax-m2": {
@@ -11632,8 +11750,8 @@ export const MODELS = {
 			cost: {
 				input: 0.3,
 				output: 1.2,
-				cacheRead: 0.15,
-				cacheWrite: 0,
+				cacheRead: 0.03,
+				cacheWrite: 0.375,
 			},
 			contextWindow: 204800,
 			maxTokens: 131072,
@@ -11686,8 +11804,42 @@ export const MODELS = {
 				cacheRead: 0.03,
 				cacheWrite: 0.375,
 			},
-			contextWindow: 4096,
-			maxTokens: 4096,
+			contextWindow: 204800,
+			maxTokens: 131000,
+		} satisfies Model<"anthropic-messages">,
+		"minimax/minimax-m2.7": {
+			id: "minimax/minimax-m2.7",
+			name: "Minimax M2.7",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.3,
+				output: 1.2,
+				cacheRead: 0.06,
+				cacheWrite: 0.375,
+			},
+			contextWindow: 204800,
+			maxTokens: 131000,
+		} satisfies Model<"anthropic-messages">,
+		"minimax/minimax-m2.7-highspeed": {
+			id: "minimax/minimax-m2.7-highspeed",
+			name: "MiniMax M2.7 High Speed",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.6,
+				output: 2.4,
+				cacheRead: 0.06,
+				cacheWrite: 0.375,
+			},
+			contextWindow: 204800,
+			maxTokens: 131100,
 		} satisfies Model<"anthropic-messages">,
 		"mistral/codestral": {
 			id: "mistral/codestral",
@@ -11715,8 +11867,8 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0,
-				output: 0,
+				input: 0.39999999999999997,
+				output: 2,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -11749,8 +11901,8 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0,
-				output: 0,
+				input: 0.09999999999999999,
+				output: 0.3,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -11766,8 +11918,8 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.04,
-				output: 0.04,
+				input: 0.09999999999999999,
+				output: 0.09999999999999999,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -11783,8 +11935,8 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.09999999999999999,
-				output: 0.09999999999999999,
+				input: 0.15,
+				output: 0.15,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -11868,14 +12020,31 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.5,
-				output: 2,
-				cacheRead: 0,
+				input: 0.6,
+				output: 2.5,
+				cacheRead: 0.15,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
 			maxTokens: 16384,
 		} satisfies Model<"anthropic-messages">,
+		"moonshotai/kimi-k2-0905": {
+			id: "moonshotai/kimi-k2-0905",
+			name: "Kimi K2 0905",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.6,
+				output: 2.5,
+				cacheRead: 0.15,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 16384,
+		} satisfies Model<"anthropic-messages">,
 		"moonshotai/kimi-k2-thinking": {
 			id: "moonshotai/kimi-k2-thinking",
 			name: "Kimi K2 Thinking",
@@ -11885,13 +12054,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.47,
-				output: 2,
-				cacheRead: 0.14100000000000001,
+				input: 0.6,
+				output: 2.5,
+				cacheRead: 0.15,
 				cacheWrite: 0,
 			},
-			contextWindow: 216144,
-			maxTokens: 216144,
+			contextWindow: 262114,
+			maxTokens: 262114,
 		} satisfies Model<"anthropic-messages">,
 		"moonshotai/kimi-k2-thinking-turbo": {
 			id: "moonshotai/kimi-k2-thinking-turbo",
@@ -11919,9 +12088,9 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 2.4,
-				output: 10,
-				cacheRead: 0,
+				input: 1.15,
+				output: 8,
+				cacheRead: 0.15,
 				cacheWrite: 0,
 			},
 			contextWindow: 256000,
@@ -11936,13 +12105,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0.5,
-				output: 2.8,
-				cacheRead: 0,
+				input: 0.6,
+				output: 3,
+				cacheRead: 0.09999999999999999,
 				cacheWrite: 0,
 			},
-			contextWindow: 256000,
-			maxTokens: 256000,
+			contextWindow: 262114,
+			maxTokens: 262114,
 		} satisfies Model<"anthropic-messages">,
 		"nvidia/nemotron-nano-12b-v2-vl": {
 			id: "nvidia/nemotron-nano-12b-v2-vl",
@@ -11970,31 +12139,14 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.04,
-				output: 0.16,
+				input: 0.06,
+				output: 0.22999999999999998,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
 			maxTokens: 131072,
 		} satisfies Model<"anthropic-messages">,
-		"openai/codex-mini": {
-			id: "openai/codex-mini",
-			name: "Codex Mini",
-			api: "anthropic-messages",
-			provider: "vercel-ai-gateway",
-			baseUrl: "https://ai-gateway.vercel.sh",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 1.5,
-				output: 6,
-				cacheRead: 0.375,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 100000,
-		} satisfies Model<"anthropic-messages">,
 		"openai/gpt-4-turbo": {
 			id: "openai/gpt-4-turbo",
 			name: "GPT-4 Turbo",
@@ -12057,7 +12209,7 @@ export const MODELS = {
 			cost: {
 				input: 0.09999999999999999,
 				output: 0.39999999999999997,
-				cacheRead: 0.03,
+				cacheRead: 0.024999999999999998,
 				cacheWrite: 0,
 			},
 			contextWindow: 1047576,
@@ -12108,7 +12260,7 @@ export const MODELS = {
 			cost: {
 				input: 1.25,
 				output: 10,
-				cacheRead: 0.13,
+				cacheRead: 0.125,
 				cacheWrite: 0,
 			},
 			contextWindow: 400000,
@@ -12138,11 +12290,11 @@ 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: 0.13,
+				cacheRead: 0.125,
 				cacheWrite: 0,
 			},
 			contextWindow: 400000,
@@ -12159,7 +12311,7 @@ export const MODELS = {
 			cost: {
 				input: 0.25,
 				output: 2,
-				cacheRead: 0.03,
+				cacheRead: 0.024999999999999998,
 				cacheWrite: 0,
 			},
 			contextWindow: 400000,
@@ -12176,7 +12328,7 @@ export const MODELS = {
 			cost: {
 				input: 0.049999999999999996,
 				output: 0.39999999999999997,
-				cacheRead: 0.01,
+				cacheRead: 0.005,
 				cacheWrite: 0,
 			},
 			contextWindow: 400000,
@@ -12210,7 +12362,7 @@ export const MODELS = {
 			cost: {
 				input: 1.25,
 				output: 10,
-				cacheRead: 0.13,
+				cacheRead: 0.125,
 				cacheWrite: 0,
 			},
 			contextWindow: 400000,
@@ -12261,7 +12413,7 @@ export const MODELS = {
 			cost: {
 				input: 1.25,
 				output: 10,
-				cacheRead: 0.13,
+				cacheRead: 0.125,
 				cacheWrite: 0,
 			},
 			contextWindow: 128000,
@@ -12278,7 +12430,7 @@ export const MODELS = {
 			cost: {
 				input: 1.25,
 				output: 10,
-				cacheRead: 0.13,
+				cacheRead: 0.125,
 				cacheWrite: 0,
 			},
 			contextWindow: 400000,
@@ -12295,7 +12447,7 @@ export const MODELS = {
 			cost: {
 				input: 1.75,
 				output: 14,
-				cacheRead: 0.18,
+				cacheRead: 0.175,
 				cacheWrite: 0,
 			},
 			contextWindow: 400000,
@@ -12400,7 +12552,41 @@ export const MODELS = {
 				cacheRead: 0.25,
 				cacheWrite: 0,
 			},
-			contextWindow: 200000,
+			contextWindow: 1050000,
+			maxTokens: 128000,
+		} satisfies Model<"anthropic-messages">,
+		"openai/gpt-5.4-mini": {
+			id: "openai/gpt-5.4-mini",
+			name: "GPT 5.4 Mini",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.75,
+				output: 4.5,
+				cacheRead: 0.075,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"anthropic-messages">,
+		"openai/gpt-5.4-nano": {
+			id: "openai/gpt-5.4-nano",
+			name: "GPT 5.4 Nano",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.19999999999999998,
+				output: 1.25,
+				cacheRead: 0.02,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
 			maxTokens: 128000,
 		} satisfies Model<"anthropic-messages">,
 		"openai/gpt-5.4-pro": {
@@ -12420,23 +12606,6 @@ export const MODELS = {
 			contextWindow: 1050000,
 			maxTokens: 128000,
 		} satisfies Model<"anthropic-messages">,
-		"openai/gpt-oss-120b": {
-			id: "openai/gpt-oss-120b",
-			name: "gpt-oss-120b",
-			api: "anthropic-messages",
-			provider: "vercel-ai-gateway",
-			baseUrl: "https://ai-gateway.vercel.sh",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.09999999999999999,
-				output: 0.5,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 131072,
-		} satisfies Model<"anthropic-messages">,
 		"openai/gpt-oss-20b": {
 			id: "openai/gpt-oss-20b",
 			name: "gpt-oss-20b",
@@ -12624,40 +12793,6 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 131072,
 		} satisfies Model<"anthropic-messages">,
-		"vercel/v0-1.0-md": {
-			id: "vercel/v0-1.0-md",
-			name: "v0-1.0-md",
-			api: "anthropic-messages",
-			provider: "vercel-ai-gateway",
-			baseUrl: "https://ai-gateway.vercel.sh",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 32000,
-		} satisfies Model<"anthropic-messages">,
-		"vercel/v0-1.5-md": {
-			id: "vercel/v0-1.5-md",
-			name: "v0-1.5-md",
-			api: "anthropic-messages",
-			provider: "vercel-ai-gateway",
-			baseUrl: "https://ai-gateway.vercel.sh",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 32768,
-		} satisfies Model<"anthropic-messages">,
 		"xai/grok-2-vision": {
 			id: "xai/grok-2-vision",
 			name: "Grok 2 Vision",
@@ -12686,7 +12821,7 @@ export const MODELS = {
 			cost: {
 				input: 3,
 				output: 15,
-				cacheRead: 0,
+				cacheRead: 0.75,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
@@ -12703,7 +12838,7 @@ export const MODELS = {
 			cost: {
 				input: 5,
 				output: 25,
-				cacheRead: 0,
+				cacheRead: 1.25,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
@@ -12720,7 +12855,7 @@ export const MODELS = {
 			cost: {
 				input: 0.3,
 				output: 0.5,
-				cacheRead: 0,
+				cacheRead: 0.075,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
@@ -12754,7 +12889,7 @@ export const MODELS = {
 			cost: {
 				input: 3,
 				output: 15,
-				cacheRead: 0,
+				cacheRead: 0.75,
 				cacheWrite: 0,
 			},
 			contextWindow: 256000,
@@ -12828,6 +12963,57 @@ export const MODELS = {
 			contextWindow: 2000000,
 			maxTokens: 30000,
 		} satisfies Model<"anthropic-messages">,
+		"xai/grok-4.20-multi-agent-beta": {
+			id: "xai/grok-4.20-multi-agent-beta",
+			name: "Grok 4.20 Multi Agent Beta",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 2,
+				output: 6,
+				cacheRead: 0.19999999999999998,
+				cacheWrite: 0,
+			},
+			contextWindow: 2000000,
+			maxTokens: 2000000,
+		} satisfies Model<"anthropic-messages">,
+		"xai/grok-4.20-non-reasoning-beta": {
+			id: "xai/grok-4.20-non-reasoning-beta",
+			name: "Grok 4.20 Beta Non-Reasoning",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 2,
+				output: 6,
+				cacheRead: 0.19999999999999998,
+				cacheWrite: 0,
+			},
+			contextWindow: 2000000,
+			maxTokens: 2000000,
+		} satisfies Model<"anthropic-messages">,
+		"xai/grok-4.20-reasoning-beta": {
+			id: "xai/grok-4.20-reasoning-beta",
+			name: "Grok 4.20 Beta Reasoning",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 2,
+				output: 6,
+				cacheRead: 0.19999999999999998,
+				cacheWrite: 0,
+			},
+			contextWindow: 2000000,
+			maxTokens: 2000000,
+		} satisfies Model<"anthropic-messages">,
 		"xai/grok-code-fast-1": {
 			id: "xai/grok-code-fast-1",
 			name: "Grok Code Fast 1",
@@ -12854,14 +13040,31 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.09,
-				output: 0.29,
-				cacheRead: 0,
+				input: 0.09999999999999999,
+				output: 0.3,
+				cacheRead: 0.02,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
 			maxTokens: 32000,
 		} satisfies Model<"anthropic-messages">,
+		"xiaomi/mimo-v2-pro": {
+			id: "xiaomi/mimo-v2-pro",
+			name: "MiMo V2 Pro",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 1,
+				output: 3,
+				cacheRead: 0.19999999999999998,
+				cacheWrite: 0,
+			},
+			contextWindow: 1000000,
+			maxTokens: 128000,
+		} satisfies Model<"anthropic-messages">,
 		"zai/glm-4.5": {
 			id: "zai/glm-4.5",
 			name: "GLM-4.5",
@@ -12873,11 +13076,11 @@ export const MODELS = {
 			cost: {
 				input: 0.6,
 				output: 2.2,
-				cacheRead: 0,
+				cacheRead: 0.11,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
-			maxTokens: 131072,
+			contextWindow: 128000,
+			maxTokens: 96000,
 		} satisfies Model<"anthropic-messages">,
 		"zai/glm-4.5-air": {
 			id: "zai/glm-4.5-air",
@@ -12902,16 +13105,16 @@ export const MODELS = {
 			api: "anthropic-messages",
 			provider: "vercel-ai-gateway",
 			baseUrl: "https://ai-gateway.vercel.sh",
-			reasoning: true,
+			reasoning: false,
 			input: ["text", "image"],
 			cost: {
 				input: 0.6,
 				output: 1.7999999999999998,
-				cacheRead: 0,
+				cacheRead: 0.11,
 				cacheWrite: 0,
 			},
-			contextWindow: 65536,
-			maxTokens: 16384,
+			contextWindow: 66000,
+			maxTokens: 16000,
 		} satisfies Model<"anthropic-messages">,
 		"zai/glm-4.6": {
 			id: "zai/glm-4.6",
@@ -12922,8 +13125,8 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.44999999999999996,
-				output: 1.7999999999999998,
+				input: 0.6,
+				output: 2.2,
 				cacheRead: 0.11,
 				cacheWrite: 0,
 			},
@@ -12973,14 +13176,31 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.43,
-				output: 1.75,
-				cacheRead: 0.08,
+				input: 0.6,
+				output: 2.2,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 202752,
+			contextWindow: 200000,
 			maxTokens: 120000,
 		} satisfies Model<"anthropic-messages">,
+		"zai/glm-4.7-flash": {
+			id: "zai/glm-4.7-flash",
+			name: "GLM 4.7 Flash",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.07,
+				output: 0.39999999999999997,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 131000,
+		} satisfies Model<"anthropic-messages">,
 		"zai/glm-4.7-flashx": {
 			id: "zai/glm-4.7-flashx",
 			name: "GLM 4.7 FlashX",
@@ -13000,7 +13220,7 @@ export const MODELS = {
 		} satisfies Model<"anthropic-messages">,
 		"zai/glm-5": {
 			id: "zai/glm-5",
-			name: "GLM-5",
+			name: "GLM 5",
 			api: "anthropic-messages",
 			provider: "vercel-ai-gateway",
 			baseUrl: "https://ai-gateway.vercel.sh",
@@ -13013,7 +13233,24 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 202800,
-			maxTokens: 131072,
+			maxTokens: 131100,
+		} satisfies Model<"anthropic-messages">,
+		"zai/glm-5-turbo": {
+			id: "zai/glm-5-turbo",
+			name: "GLM 5 Turbo",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 1.2,
+				output: 4,
+				cacheRead: 0.24,
+				cacheWrite: 0,
+			},
+			contextWindow: 202800,
+			maxTokens: 131100,
 		} satisfies Model<"anthropic-messages">,
 	},
 	"xai": {
@@ -13340,6 +13577,40 @@ export const MODELS = {
 			contextWindow: 2000000,
 			maxTokens: 30000,
 		} satisfies Model<"openai-completions">,
+		"grok-4.20-0309-non-reasoning": {
+			id: "grok-4.20-0309-non-reasoning",
+			name: "Grok 4.20 (Non-Reasoning)",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 2,
+				output: 6,
+				cacheRead: 0.2,
+				cacheWrite: 0,
+			},
+			contextWindow: 2000000,
+			maxTokens: 30000,
+		} satisfies Model<"openai-completions">,
+		"grok-4.20-0309-reasoning": {
+			id: "grok-4.20-0309-reasoning",
+			name: "Grok 4.20 (Reasoning)",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 2,
+				output: 6,
+				cacheRead: 0.2,
+				cacheWrite: 0,
+			},
+			contextWindow: 2000000,
+			maxTokens: 30000,
+		} satisfies Model<"openai-completions">,
 		"grok-beta": {
 			id: "grok-beta",
 			name: "Grok Beta",
@@ -13555,747 +13826,23 @@ export const MODELS = {
 			contextWindow: 204800,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
-	},
-	"alibaba-coding-plan": {
-		"qwen3.5-plus": {
-			id: "qwen3.5-plus",
-			name: "Qwen3.5 Plus",
+		"glm-5-turbo": {
+			id: "glm-5-turbo",
+			name: "GLM-5-Turbo",
 			api: "openai-completions",
-			provider: "alibaba-coding-plan",
-			baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
+			provider: "zai",
+			baseUrl: "https://api.z.ai/api/coding/paas/v4",
+			compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai"},
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
+				input: 1.2,
+				output: 4,
+				cacheRead: 0.24,
 				cacheWrite: 0,
 			},
-			contextWindow: 983616,
-			maxTokens: 65536,
-			compat: { thinkingFormat: "qwen", supportsDeveloperRole: false },
-		} satisfies Model<"openai-completions">,
-		"qwen3-max-2026-01-23": {
-			id: "qwen3-max-2026-01-23",
-			name: "Qwen3 Max 2026-01-23",
-			api: "openai-completions",
-			provider: "alibaba-coding-plan",
-			baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 258048,
-			maxTokens: 32768,
-			compat: { thinkingFormat: "qwen", supportsDeveloperRole: false },
-		} satisfies Model<"openai-completions">,
-		"qwen3-coder-next": {
-			id: "qwen3-coder-next",
-			name: "Qwen3 Coder Next",
-			api: "openai-completions",
-			provider: "alibaba-coding-plan",
-			baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 204800,
-			maxTokens: 65536,
-			compat: { supportsDeveloperRole: false },
-		} satisfies Model<"openai-completions">,
-		"qwen3-coder-plus": {
-			id: "qwen3-coder-plus",
-			name: "Qwen3 Coder Plus",
-			api: "openai-completions",
-			provider: "alibaba-coding-plan",
-			baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 997952,
-			maxTokens: 65536,
-			compat: { supportsDeveloperRole: false },
-		} satisfies Model<"openai-completions">,
-		"MiniMax-M2.5": {
-			id: "MiniMax-M2.5",
-			name: "MiniMax M2.5",
-			api: "openai-completions",
-			provider: "alibaba-coding-plan",
-			baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 196608,
-			maxTokens: 65536,
-			compat: { supportsStore: false, supportsDeveloperRole: false, supportsReasoningEffort: true, maxTokensField: "max_tokens" },
-		} satisfies Model<"openai-completions">,
-		"glm-5": {
-			id: "glm-5",
-			name: "GLM-5",
-			api: "openai-completions",
-			provider: "alibaba-coding-plan",
-			baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 202752,
-			maxTokens: 16384,
-			compat: { thinkingFormat: "qwen", supportsDeveloperRole: false },
-		} satisfies Model<"openai-completions">,
-		"glm-4.7": {
-			id: "glm-4.7",
-			name: "GLM-4.7",
-			api: "openai-completions",
-			provider: "alibaba-coding-plan",
-			baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 169984,
-			maxTokens: 16384,
-			compat: { thinkingFormat: "qwen", supportsDeveloperRole: false },
-		} satisfies Model<"openai-completions">,
-		"kimi-k2.5": {
-			id: "kimi-k2.5",
-			name: "Kimi K2.5",
-			api: "openai-completions",
-			provider: "alibaba-coding-plan",
-			baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 258048,
-			maxTokens: 32768,
-			compat: { thinkingFormat: "zai", supportsDeveloperRole: false },
-		} satisfies Model<"openai-completions">,
-	},
-	"ollama-cloud": {
-		"cogito-2.1:671b": {
-			id: "cogito-2.1:671b",
-			name: "Cogito 2.1 671B",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 163840,
-			maxTokens: 32000,
-		} satisfies Model<"openai-completions">,
-		"deepseek-v3.1:671b": {
-			id: "deepseek-v3.1:671b",
-			name: "DeepSeek V3.1 671B",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 163840,
-			maxTokens: 163840,
-		} satisfies Model<"openai-completions">,
-		"deepseek-v3.2": {
-			id: "deepseek-v3.2",
-			name: "DeepSeek V3.2",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 163840,
-			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
-		"devstral-2:123b": {
-			id: "devstral-2:123b",
-			name: "Devstral 2 123B",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 262144,
-		} satisfies Model<"openai-completions">,
-		"devstral-small-2:24b": {
-			id: "devstral-small-2:24b",
-			name: "Devstral Small 2 24B",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 262144,
-		} satisfies Model<"openai-completions">,
-		"gemini-3-flash-preview": {
-			id: "gemini-3-flash-preview",
-			name: "Gemini 3 Flash Preview",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
-		"gemma3:12b": {
-			id: "gemma3:12b",
-			name: "Gemma 3 12B",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
+			contextWindow: 200000,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
-		"gemma3:27b": {
-			id: "gemma3:27b",
-			name: "Gemma 3 27B",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
-		"gemma3:4b": {
-			id: "gemma3:4b",
-			name: "Gemma 3 4B",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
-		"glm-4.6": {
-			id: "glm-4.6",
-			name: "GLM 4.6",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 202752,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
-		"glm-4.7": {
-			id: "glm-4.7",
-			name: "GLM 4.7",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 202752,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
-		"glm-5": {
-			id: "glm-5",
-			name: "GLM 5",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 202752,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
-		"gpt-oss:120b": {
-			id: "gpt-oss:120b",
-			name: "GPT-OSS 120B",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
-		"gpt-oss:20b": {
-			id: "gpt-oss:20b",
-			name: "GPT-OSS 20B",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
-		"kimi-k2:1t": {
-			id: "kimi-k2:1t",
-			name: "Kimi K2 1T",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 262144,
-		} satisfies Model<"openai-completions">,
-		"kimi-k2.5": {
-			id: "kimi-k2.5",
-			name: "Kimi K2.5",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 262144,
-		} satisfies Model<"openai-completions">,
-		"kimi-k2-thinking": {
-			id: "kimi-k2-thinking",
-			name: "Kimi K2 Thinking",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 262144,
-		} satisfies Model<"openai-completions">,
-		"minimax-m2.1": {
-			id: "minimax-m2.1",
-			name: "Minimax M2.1",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 204800,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
-		"minimax-m2.5": {
-			id: "minimax-m2.5",
-			name: "Minimax M2.5",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 204800,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
-		"minimax-m2": {
-			id: "minimax-m2",
-			name: "Minimax M2",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 204800,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
-		"ministral-3:14b": {
-			id: "ministral-3:14b",
-			name: "Ministral 3 14B",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
-		"ministral-3:3b": {
-			id: "ministral-3:3b",
-			name: "Ministral 3 3B",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
-		"ministral-3:8b": {
-			id: "ministral-3:8b",
-			name: "Ministral 3 8B",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
-		"mistral-large-3:675b": {
-			id: "mistral-large-3:675b",
-			name: "Mistral Large 3 675B",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 262144,
-		} satisfies Model<"openai-completions">,
-		"nemotron-3-nano:30b": {
-			id: "nemotron-3-nano:30b",
-			name: "Nemotron 3 Nano 30B",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
-		"nemotron-3-super": {
-			id: "nemotron-3-super",
-			name: "Nemotron 3 Super",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
-		"qwen3.5:397b": {
-			id: "qwen3.5:397b",
-			name: "Qwen 3.5 397B",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 81920,
-		} satisfies Model<"openai-completions">,
-		"qwen3-coder:480b": {
-			id: "qwen3-coder:480b",
-			name: "Qwen 3 Coder 480B",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
-		"qwen3-coder-next": {
-			id: "qwen3-coder-next",
-			name: "Qwen 3 Coder Next",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
-		"qwen3-next:80b": {
-			id: "qwen3-next:80b",
-			name: "Qwen 3 Next 80B",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
-		"qwen3-vl:235b-instruct": {
-			id: "qwen3-vl:235b-instruct",
-			name: "Qwen 3 VL 235B Instruct",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
-		"qwen3-vl:235b": {
-			id: "qwen3-vl:235b",
-			name: "Qwen 3 VL 235B",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
-		"rnj-1:8b": {
-			id: "rnj-1:8b",
-			name: "RNJ 1 8B",
-			api: "openai-completions",
-			provider: "ollama-cloud",
-			baseUrl: "https://ollama.com/v1",
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
 	},
 } as const;
diff --git a/packages/pi-ai/src/models.ts b/packages/pi-ai/src/models.ts
index 3c06c0cc6..8a4805ac1 100644
--- a/packages/pi-ai/src/models.ts
+++ b/packages/pi-ai/src/models.ts
@@ -12,12 +12,15 @@ for (const [provider, models] of Object.entries(MODELS)) {
 	modelRegistry.set(provider, providerModels);
 }
 
+/** Providers that have entries in the generated MODELS constant */
+type GeneratedProvider = keyof typeof MODELS & KnownProvider;
+
 type ModelApi<
-	TProvider extends KnownProvider,
+	TProvider extends GeneratedProvider,
 	TModelId extends keyof (typeof MODELS)[TProvider],
 > = (typeof MODELS)[TProvider][TModelId] extends { api: infer TApi } ? (TApi extends Api ? TApi : never) : never;
 
-export function getModel<TProvider extends KnownProvider, TModelId extends keyof (typeof MODELS)[TProvider]>(
+export function getModel<TProvider extends GeneratedProvider, TModelId extends keyof (typeof MODELS)[TProvider]>(
 	provider: TProvider,
 	modelId: TModelId,
 ): Model<ModelApi<TProvider, TModelId>> {
@@ -31,9 +34,9 @@ export function getProviders(): KnownProvider[] {
 
 export function getModels<TProvider extends KnownProvider>(
 	provider: TProvider,
-): Model<ModelApi<TProvider, keyof (typeof MODELS)[TProvider]>>[] {
+): Model<Api>[] {
 	const models = modelRegistry.get(provider);
-	return models ? (Array.from(models.values()) as Model<ModelApi<TProvider, keyof (typeof MODELS)[TProvider]>>[]) : [];
+	return models ? (Array.from(models.values()) as Model<Api>[]) : [];
 }
 
 export function calculateCost<TApi extends Api>(model: Model<TApi>, usage: Usage): Usage["cost"] {
diff --git a/packages/pi-ai/src/utils/oauth/github-copilot.ts b/packages/pi-ai/src/utils/oauth/github-copilot.ts
index 08ffb24d3..eae8e9a5f 100644
--- a/packages/pi-ai/src/utils/oauth/github-copilot.ts
+++ b/packages/pi-ai/src/utils/oauth/github-copilot.ts
@@ -8,6 +8,8 @@ import type { OAuthCredentials, OAuthLoginCallbacks, OAuthProviderInterface } fr
 
 type CopilotCredentials = OAuthCredentials & {
 	enterpriseUrl?: string;
+	/** Model limits from the /models API, keyed by model ID */
+	modelLimits?: Record<string, { contextWindow: number; maxTokens: number }>;
 };
 
 const decode = (s: string) => atob(s);
@@ -305,6 +307,47 @@ async function enableAllGitHubCopilotModels(
 	);
 }
 
+async function fetchCopilotModelLimits(
+	token: string,
+	enterpriseDomain?: string,
+): Promise<Record<string, { contextWindow: number; maxTokens: number }>> {
+	const baseUrl = getGitHubCopilotBaseUrl(token, enterpriseDomain);
+	try {
+		const response = await fetch(`${baseUrl}/models`, {
+			headers: {
+				Accept: "application/json",
+				Authorization: `Bearer ${token}`,
+				"X-GitHub-Api-Version": "2025-05-01",
+				...COPILOT_HEADERS,
+			},
+			signal: AbortSignal.timeout(30_000),
+		});
+		if (!response.ok) return {};
+		const data = (await response.json()) as {
+			data?: Array<{
+				id: string;
+				capabilities?: {
+					limits?: {
+						max_context_window_tokens?: number;
+						max_output_tokens?: number;
+					};
+				};
+			}>;
+		};
+		const limits: Record<string, { contextWindow: number; maxTokens: number }> = {};
+		for (const m of data.data || []) {
+			const ctx = m.capabilities?.limits?.max_context_window_tokens;
+			const out = m.capabilities?.limits?.max_output_tokens;
+			if (typeof ctx === "number" && typeof out === "number" && ctx > 0 && out > 0 && Number.isFinite(ctx) && Number.isFinite(out)) {
+				limits[m.id] = { contextWindow: ctx, maxTokens: out };
+			}
+		}
+		return limits;
+	} catch {
+		return {};
+	}
+}
+
 /**
  * Login with GitHub Copilot OAuth (device code flow)
  *
@@ -351,6 +394,14 @@ export async function loginGitHubCopilot(options: {
 	// Enable all models after successful login
 	options.onProgress?.("Enabling models...");
 	await enableAllGitHubCopilotModels(credentials.access, enterpriseDomain ?? undefined);
+
+	// Fetch real model limits from the Copilot API
+	options.onProgress?.("Fetching model limits...");
+	const modelLimits = await fetchCopilotModelLimits(credentials.access, enterpriseDomain ?? undefined);
+	if (Object.keys(modelLimits).length > 0) {
+		(credentials as CopilotCredentials).modelLimits = modelLimits;
+	}
+
 	return credentials;
 }
 
@@ -369,7 +420,16 @@ export const githubCopilotOAuthProvider: OAuthProviderInterface = {
 
 	async refreshToken(credentials: OAuthCredentials): Promise<OAuthCredentials> {
 		const creds = credentials as CopilotCredentials;
-		return refreshGitHubCopilotToken(creds.refresh, creds.enterpriseUrl);
+		const refreshed = await refreshGitHubCopilotToken(creds.refresh, creds.enterpriseUrl);
+		try {
+			const modelLimits = await fetchCopilotModelLimits(refreshed.access, creds.enterpriseUrl);
+			if (Object.keys(modelLimits).length > 0) {
+				(refreshed as CopilotCredentials).modelLimits = modelLimits;
+			}
+		} catch {
+			// Model limits fetch is best-effort; don't block token refresh
+		}
+		return refreshed;
 	},
 
 	getApiKey(credentials: OAuthCredentials): string {
@@ -380,6 +440,18 @@ export const githubCopilotOAuthProvider: OAuthProviderInterface = {
 		const creds = credentials as CopilotCredentials;
 		const domain = creds.enterpriseUrl ? (normalizeDomain(creds.enterpriseUrl) ?? undefined) : undefined;
 		const baseUrl = getGitHubCopilotBaseUrl(creds.access, domain);
-		return models.map((m) => (m.provider === "github-copilot" ? { ...m, baseUrl } : m));
+		const limits = creds.modelLimits;
+		return models.map((m) => {
+			if (m.provider !== "github-copilot") return m;
+			const modelLimits = limits?.[m.id];
+			return {
+				...m,
+				baseUrl,
+				...(modelLimits && {
+					contextWindow: modelLimits.contextWindow,
+					maxTokens: modelLimits.maxTokens,
+				}),
+			};
+		});
 	},
 };
diff --git a/packages/pi-coding-agent/src/core/auth-storage.ts b/packages/pi-coding-agent/src/core/auth-storage.ts
index e921328f2..c632090a7 100644
--- a/packages/pi-coding-agent/src/core/auth-storage.ts
+++ b/packages/pi-coding-agent/src/core/auth-storage.ts
@@ -202,6 +202,7 @@ export class AuthStorage {
 	private fallbackResolver?: (provider: string) => string | undefined;
 	private loadError: Error | null = null;
 	private errors: Error[] = [];
+	private credentialChangeListeners: Set<() => void> = new Set();
 
 	/**
 	 * Round-robin index per provider. Incremented on each call to getApiKey
@@ -263,6 +264,25 @@ export class AuthStorage {
 		this.fallbackResolver = resolver;
 	}
 
+	/**
+	 * Register a callback to be notified when credentials change (e.g., after OAuth token refresh).
+	 * Returns a function to unregister the listener.
+	 */
+	onCredentialChange(listener: () => void): () => void {
+		this.credentialChangeListeners.add(listener);
+		return () => this.credentialChangeListeners.delete(listener);
+	}
+
+	private notifyCredentialChange(): void {
+		for (const listener of this.credentialChangeListeners) {
+			try {
+				listener();
+			} catch {
+				// Don't let listener errors break the refresh flow
+			}
+		}
+	}
+
 	private recordError(error: unknown): void {
 		const normalizedError = error instanceof Error ? error : new Error(String(error));
 		this.errors.push(normalizedError);
@@ -667,6 +687,11 @@ export class AuthStorage {
 			return { result: refreshed, next: JSON.stringify(merged, null, 2) };
 		});
 
+		// Notify listeners after credential change (e.g., model registry refresh)
+		if (result) {
+			queueMicrotask(() => this.notifyCredentialChange());
+		}
+
 		return result;
 	}
 
diff --git a/packages/pi-coding-agent/src/core/model-registry.ts b/packages/pi-coding-agent/src/core/model-registry.ts
index 08766af24..b6d161c89 100644
--- a/packages/pi-coding-agent/src/core/model-registry.ts
+++ b/packages/pi-coding-agent/src/core/model-registry.ts
@@ -243,6 +243,9 @@ export class ModelRegistry {
 			return undefined;
 		});
 
+		// Refresh models when credentials change (e.g., OAuth token refresh with new model limits)
+		this.authStorage.onCredentialChange(() => this.refresh());
+
 		// Load models
 		this.loadModels();
 	}