feat(coding-agent): replace model registry with model runtime

Move provider auth and OAuth flows onto pi-ai Models, compose models.json and extension overlays through ModelRuntime, and retain ModelRegistry as an extension compatibility facade.

packages/ai/src/providers/amazon-bedrock.models.ts

@@ -1290,6 +1290,60 @@ export const AMAZON_BEDROCK_MODELS = {
 		contextWindow: 272000,
 		maxTokens: 128000,
 	} satisfies Model<"bedrock-converse-stream">,
+	"openai.gpt-5.6-luna": {
+		id: "openai.gpt-5.6-luna",
+		name: "GPT-5.6 Luna",
+		api: "bedrock-converse-stream",
+		provider: "amazon-bedrock",
+		baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+		reasoning: true,
+		thinkingLevelMap: {"xhigh":"xhigh"},
+		input: ["text", "image"],
+		cost: {
+			input: 1,
+			output: 6,
+			cacheRead: 0.1,
+			cacheWrite: 1.25,
+		},
+		contextWindow: 272000,
+		maxTokens: 128000,
+	} satisfies Model<"bedrock-converse-stream">,
+	"openai.gpt-5.6-sol": {
+		id: "openai.gpt-5.6-sol",
+		name: "GPT-5.6 Sol",
+		api: "bedrock-converse-stream",
+		provider: "amazon-bedrock",
+		baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+		reasoning: true,
+		thinkingLevelMap: {"xhigh":"xhigh"},
+		input: ["text", "image"],
+		cost: {
+			input: 5,
+			output: 30,
+			cacheRead: 0.5,
+			cacheWrite: 6.25,
+		},
+		contextWindow: 272000,
+		maxTokens: 128000,
+	} satisfies Model<"bedrock-converse-stream">,
+	"openai.gpt-5.6-terra": {
+		id: "openai.gpt-5.6-terra",
+		name: "GPT-5.6 Terra",
+		api: "bedrock-converse-stream",
+		provider: "amazon-bedrock",
+		baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+		reasoning: true,
+		thinkingLevelMap: {"xhigh":"xhigh"},
+		input: ["text", "image"],
+		cost: {
+			input: 2.5,
+			output: 15,
+			cacheRead: 0.25,
+			cacheWrite: 3.125,
+		},
+		contextWindow: 272000,
+		maxTokens: 128000,
+	} satisfies Model<"bedrock-converse-stream">,
 	"openai.gpt-oss-120b": {
 		id: "openai.gpt-oss-120b",
 		name: "gpt-oss-120b",

packages/ai/src/providers/amazon-bedrock.ts

@@ -4,16 +4,61 @@ import { createProvider, type Provider } from "../models.ts";
 import { AMAZON_BEDROCK_MODELS } from "./amazon-bedrock.models.ts";
 
 /**
- * Bedrock auth is ambient: the AWS SDK's default credential chain handles the
- * actual signing, so `resolve` only reports whether the provider is
- * configured. A stored credential key is surfaced as the bearer token.
+ * Bedrock accepts a bearer token or the AWS SDK's default credential chain.
+ * The login flow can store a token/profile choice; resolve also detects ambient
+ * AWS credentials without copying them into pi's credential store.
  */
 const bedrockAuth: ApiKeyAuth = {
-	name: "AWS credentials",
+	name: "AWS credentials or bearer token",
+	login: async (interaction) => {
+		const method = await interaction.prompt({
+			type: "select",
+			message: "Select Amazon Bedrock authentication method:",
+			options: [
+				{ id: "bearer-token", label: "Bearer token" },
+				{ id: "aws-profile", label: "AWS profile" },
+				{ id: "credential-chain", label: "Existing AWS credential chain" },
+			],
+		});
+		if (method === "bearer-token") {
+			return {
+				type: "api_key",
+				key: await interaction.prompt({ type: "secret", message: "Enter Amazon Bedrock bearer token" }),
+			};
+		}
+		interaction.notify({
+			type: "info",
+			message: "Amazon Bedrock supports AWS profiles, IAM credentials, and role-based credentials.",
+			links: [
+				{
+					label: "AWS credential provider chain",
+					url: "https://docs.aws.amazon.com/sdkref/latest/guide/standardized-credentials.html",
+				},
+			],
+		});
+		if (method === "aws-profile") {
+			return {
+				type: "api_key",
+				env: { AWS_PROFILE: await interaction.prompt({ type: "text", message: "Enter AWS profile name" }) },
+			};
+		}
+		if (method !== "credential-chain") throw new Error(`Unknown Amazon Bedrock auth method: ${method}`);
+		await interaction.prompt({
+			type: "text",
+			message: "Configure AWS credentials, then press Enter to continue",
+		});
+		return { type: "api_key" };
+	},
 	resolve: async ({ ctx, credential }) => {
 		if (credential?.key) return { auth: { apiKey: credential.key }, source: "stored credential" };
 		if (await ctx.env("AWS_BEARER_TOKEN_BEDROCK")) return { auth: {}, source: "AWS_BEARER_TOKEN_BEDROCK" };
-		if (await ctx.env("AWS_PROFILE")) return { auth: {}, source: "AWS_PROFILE" };
+		if (credential?.env?.AWS_PROFILE ?? (await ctx.env("AWS_PROFILE"))) {
+			return {
+				auth: {},
+				env: credential?.env,
+				source: credential?.env?.AWS_PROFILE ? "stored credential" : "AWS_PROFILE",
+			};
+		}
 		if ((await ctx.env("AWS_ACCESS_KEY_ID")) && (await ctx.env("AWS_SECRET_ACCESS_KEY"))) {
 			return { auth: {}, source: "AWS access keys" };
 		}

packages/ai/src/providers/anthropic.ts

@@ -1,7 +1,7 @@
 import { anthropicMessagesApi } from "../api/anthropic-messages.lazy.ts";
 import { envApiKeyAuth, lazyOAuth } from "../auth/helpers.ts";
+import { loadAnthropicOAuth } from "../auth/oauth/load.ts";
 import { createProvider, type Provider } from "../models.ts";
-import { loadAnthropicOAuth } from "../utils/oauth/load.ts";
 import { ANTHROPIC_MODELS } from "./anthropic.models.ts";
 
 export function anthropicProvider(): Provider<"anthropic-messages"> {

packages/ai/src/providers/azure-openai-responses.models.ts

@@ -660,6 +660,23 @@ export const AZURE_OPENAI_RESPONSES_MODELS = {
 		contextWindow: 1050000,
 		maxTokens: 128000,
 	} satisfies Model<"azure-openai-responses">,
+	"gpt-realtime-2.1": {
+		id: "gpt-realtime-2.1",
+		name: "GPT-Realtime-2.1",
+		api: "azure-openai-responses",
+		provider: "azure-openai-responses",
+		baseUrl: "",
+		reasoning: true,
+		input: ["text", "image"],
+		cost: {
+			input: 4,
+			output: 24,
+			cacheRead: 0.4,
+			cacheWrite: 0,
+		},
+		contextWindow: 128000,
+		maxTokens: 32000,
+	} satisfies Model<"azure-openai-responses">,
 	"o1": {
 		id: "o1",
 		name: "o1",

packages/ai/src/providers/cerebras.models.ts

@@ -52,7 +52,7 @@ export const CEREBRAS_MODELS = {
 		cost: {
 			input: 2.25,
 			output: 2.75,
-			cacheRead: 0,
+			cacheRead: 2.25,
 			cacheWrite: 0,
 		},
 		contextWindow: 131072,

packages/ai/src/providers/cloudflare-ai-gateway.models.ts

@@ -528,6 +528,60 @@ export const CLOUDFLARE_AI_GATEWAY_MODELS = {
 		contextWindow: 1050000,
 		maxTokens: 128000,
 	} satisfies Model<"openai-responses">,
+	"gpt-5.6-luna": {
+		id: "gpt-5.6-luna",
+		name: "GPT-5.6 Luna",
+		api: "openai-responses",
+		provider: "cloudflare-ai-gateway",
+		baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
+		reasoning: true,
+		thinkingLevelMap: {"off":null,"xhigh":"xhigh","max":"max"},
+		input: ["text", "image"],
+		cost: {
+			input: 1,
+			output: 6,
+			cacheRead: 0.1,
+			cacheWrite: 0,
+		},
+		contextWindow: 1050000,
+		maxTokens: 128000,
+	} satisfies Model<"openai-responses">,
+	"gpt-5.6-sol": {
+		id: "gpt-5.6-sol",
+		name: "GPT-5.6 Sol",
+		api: "openai-responses",
+		provider: "cloudflare-ai-gateway",
+		baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
+		reasoning: true,
+		thinkingLevelMap: {"off":null,"xhigh":"xhigh","max":"max"},
+		input: ["text", "image"],
+		cost: {
+			input: 5,
+			output: 30,
+			cacheRead: 0.5,
+			cacheWrite: 0,
+		},
+		contextWindow: 1050000,
+		maxTokens: 128000,
+	} satisfies Model<"openai-responses">,
+	"gpt-5.6-terra": {
+		id: "gpt-5.6-terra",
+		name: "GPT-5.6 Terra",
+		api: "openai-responses",
+		provider: "cloudflare-ai-gateway",
+		baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
+		reasoning: true,
+		thinkingLevelMap: {"off":null,"xhigh":"xhigh","max":"max"},
+		input: ["text", "image"],
+		cost: {
+			input: 2.5,
+			output: 15,
+			cacheRead: 0.25,
+			cacheWrite: 0,
+		},
+		contextWindow: 1050000,
+		maxTokens: 128000,
+	} satisfies Model<"openai-responses">,
 	"o1": {
 		id: "o1",
 		name: "o1",
@@ -685,4 +739,22 @@ export const CLOUDFLARE_AI_GATEWAY_MODELS = {
 		contextWindow: 131072,
 		maxTokens: 131072,
 	} satisfies Model<"openai-completions">,
+	"workers-ai/@cf/zai-org/glm-5.2": {
+		id: "workers-ai/@cf/zai-org/glm-5.2",
+		name: "Glm 5.2",
+		api: "openai-completions",
+		provider: "cloudflare-ai-gateway",
+		baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
+		compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"sendSessionAffinityHeaders":true},
+		reasoning: true,
+		input: ["text"],
+		cost: {
+			input: 1.4,
+			output: 4.4,
+			cacheRead: 0.26,
+			cacheWrite: 0,
+		},
+		contextWindow: 262144,
+		maxTokens: 262144,
+	} satisfies Model<"openai-completions">,
 } as const;

packages/ai/src/providers/cloudflare-ai-gateway.ts

@@ -4,6 +4,7 @@ import { openAIResponsesApi } from "../api/openai-responses.lazy.ts";
 import { createProvider, type Provider } from "../models.ts";
 import { CLOUDFLARE_AI_GATEWAY_MODELS } from "./cloudflare-ai-gateway.models.ts";
 import { cloudflareAIGatewayAuth } from "./cloudflare-auth.ts";
+import { cloudflareStreams } from "./cloudflare-stream.ts";
 
 export function cloudflareAIGatewayProvider(): Provider<
 	"anthropic-messages" | "openai-completions" | "openai-responses"
@@ -14,9 +15,9 @@ export function cloudflareAIGatewayProvider(): Provider<
 		auth: { apiKey: cloudflareAIGatewayAuth() },
 		models: Object.values(CLOUDFLARE_AI_GATEWAY_MODELS),
 		api: {
-			"anthropic-messages": anthropicMessagesApi(),
-			"openai-completions": openAICompletionsApi(),
-			"openai-responses": openAIResponsesApi(),
+			"anthropic-messages": cloudflareStreams(anthropicMessagesApi()),
+			"openai-completions": cloudflareStreams(openAICompletionsApi()),
+			"openai-responses": cloudflareStreams(openAIResponsesApi()),
 		},
 	});
 }

packages/ai/src/providers/cloudflare-auth.ts

@@ -1,5 +1,5 @@
 import type { ApiKeyAuth, ApiKeyCredential, AuthContext } from "../auth/types.ts";
-import type { Api, ImagesApi, ImagesModel, Model, ProviderEnv } from "../types.ts";
+import type { ProviderEnv } from "../types.ts";
 
 const CLOUDFLARE_API_KEY = "CLOUDFLARE_API_KEY";
 const CLOUDFLARE_ACCOUNT_ID = "CLOUDFLARE_ACCOUNT_ID";
@@ -19,22 +19,11 @@ async function resolveValue(
 	return ctx.env(name);
 }
 
-function resolveCloudflareBaseUrl(
-	model: Model<Api> | ImagesModel<ImagesApi>,
-	accountId: string,
-	gatewayId: string | undefined,
-): string {
-	return model.baseUrl
-		.replaceAll(`{${CLOUDFLARE_ACCOUNT_ID}}`, accountId)
-		.replaceAll(`{${CLOUDFLARE_GATEWAY_ID}}`, gatewayId ?? "");
-}
-
 async function resolveCloudflareEnv(
 	kind: CloudflareAuthKind,
-	model: Model<Api> | ImagesModel<ImagesApi>,
 	ctx: AuthContext,
 	credential: ApiKeyCredential | undefined,
-): Promise<{ apiKey: string; env: ProviderEnv; baseUrl: string; source: string } | undefined> {
+): Promise<{ apiKey: string; env: ProviderEnv; source: string } | undefined> {
 	const apiKey = await resolveValue(CLOUDFLARE_API_KEY, ctx, credential);
 	const accountId = await resolveValue(CLOUDFLARE_ACCOUNT_ID, ctx, credential);
 	const gatewayId = kind === "ai-gateway" ? await resolveValue(CLOUDFLARE_GATEWAY_ID, ctx, credential) : undefined;
@@ -47,7 +36,6 @@ async function resolveCloudflareEnv(
 			CLOUDFLARE_ACCOUNT_ID: accountId,
 			...(gatewayId ? { CLOUDFLARE_GATEWAY_ID: gatewayId } : {}),
 		},
-		baseUrl: resolveCloudflareBaseUrl(model, accountId, gatewayId),
 		source: credential ? "stored credential" : CLOUDFLARE_API_KEY,
 	};
 }
@@ -55,16 +43,16 @@ async function resolveCloudflareEnv(
 export function cloudflareWorkersAIAuth(): ApiKeyAuth {
 	return {
 		name: "Cloudflare API key",
-		login: async (callbacks) => {
-			const key = await callbacks.prompt({ type: "secret", message: "Enter Cloudflare API key" });
-			const accountId = await callbacks.prompt({ type: "text", message: "Enter Cloudflare account ID" });
+		login: async (interaction) => {
+			const key = await interaction.prompt({ type: "secret", message: "Enter Cloudflare API key" });
+			const accountId = await interaction.prompt({ type: "text", message: "Enter Cloudflare account ID" });
 			return { type: "api_key", key, env: { CLOUDFLARE_ACCOUNT_ID: accountId } };
 		},
-		resolve: async ({ model, ctx, credential }) => {
-			const resolved = await resolveCloudflareEnv("workers-ai", model, ctx, credential);
+		resolve: async ({ ctx, credential }) => {
+			const resolved = await resolveCloudflareEnv("workers-ai", ctx, credential);
 			if (!resolved) return undefined;
 			return {
-				auth: { apiKey: resolved.apiKey, baseUrl: resolved.baseUrl },
+				auth: { apiKey: resolved.apiKey },
 				env: resolved.env,
 				source: resolved.source,
 			};
@@ -75,18 +63,18 @@ export function cloudflareWorkersAIAuth(): ApiKeyAuth {
 export function cloudflareAIGatewayAuth(): ApiKeyAuth {
 	return {
 		name: "Cloudflare API key",
-		login: async (callbacks) => {
-			const key = await callbacks.prompt({ type: "secret", message: "Enter Cloudflare API key" });
-			const accountId = await callbacks.prompt({ type: "text", message: "Enter Cloudflare account ID" });
-			const gatewayId = await callbacks.prompt({ type: "text", message: "Enter Cloudflare AI Gateway ID" });
+		login: async (interaction) => {
+			const key = await interaction.prompt({ type: "secret", message: "Enter Cloudflare API key" });
+			const accountId = await interaction.prompt({ type: "text", message: "Enter Cloudflare account ID" });
+			const gatewayId = await interaction.prompt({ type: "text", message: "Enter Cloudflare AI Gateway ID" });
 			return {
 				type: "api_key",
 				key,
 				env: { CLOUDFLARE_ACCOUNT_ID: accountId, CLOUDFLARE_GATEWAY_ID: gatewayId },
 			};
 		},
-		resolve: async ({ model, ctx, credential }) => {
-			const resolved = await resolveCloudflareEnv("ai-gateway", model, ctx, credential);
+		resolve: async ({ ctx, credential }) => {
+			const resolved = await resolveCloudflareEnv("ai-gateway", ctx, credential);
 			if (!resolved) return undefined;
 			return {
 				auth: {
@@ -95,7 +83,6 @@ export function cloudflareAIGatewayAuth(): ApiKeyAuth {
 						Authorization: null,
 						"x-api-key": null,
 					},
-					baseUrl: resolved.baseUrl,
 				},
 				env: resolved.env,
 				source: resolved.source,

packages/ai/src/providers/cloudflare-stream.ts

@@ -0,0 +1,28 @@
+import type { Api, Model, ProviderEnv, ProviderStreams } from "../types.ts";
+
+const CLOUDFLARE_ACCOUNT_ID = "CLOUDFLARE_ACCOUNT_ID";
+const CLOUDFLARE_GATEWAY_ID = "CLOUDFLARE_GATEWAY_ID";
+
+export function resolveCloudflareModel<TApi extends Api>(
+	model: Model<TApi>,
+	env: ProviderEnv | undefined,
+): Model<TApi> {
+	if (!env) return model;
+	const baseUrl = model.baseUrl
+		.replaceAll(`{${CLOUDFLARE_ACCOUNT_ID}}`, env[CLOUDFLARE_ACCOUNT_ID] ?? `{${CLOUDFLARE_ACCOUNT_ID}}`)
+		.replaceAll(`{${CLOUDFLARE_GATEWAY_ID}}`, env[CLOUDFLARE_GATEWAY_ID] ?? `{${CLOUDFLARE_GATEWAY_ID}}`);
+	return baseUrl === model.baseUrl ? model : { ...model, baseUrl };
+}
+
+/**
+ * Wrap an API implementation so Cloudflare account/gateway endpoint
+ * placeholders materialize from the resolved provider env before dispatch.
+ */
+export function cloudflareStreams(streams: ProviderStreams): ProviderStreams {
+	return {
+		stream: (model, context, options) =>
+			streams.stream(resolveCloudflareModel(model, options?.env), context, options),
+		streamSimple: (model, context, options) =>
+			streams.streamSimple(resolveCloudflareModel(model, options?.env), context, options),
+	};
+}

packages/ai/src/providers/cloudflare-workers-ai.ts

@@ -1,6 +1,7 @@
 import { openAICompletionsApi } from "../api/openai-completions.lazy.ts";
 import { createProvider, type Provider } from "../models.ts";
 import { cloudflareWorkersAIAuth } from "./cloudflare-auth.ts";
+import { cloudflareStreams } from "./cloudflare-stream.ts";
 import { CLOUDFLARE_WORKERS_AI_MODELS } from "./cloudflare-workers-ai.models.ts";
 
 export function cloudflareWorkersAIProvider(): Provider<"openai-completions"> {
@@ -9,6 +10,6 @@ export function cloudflareWorkersAIProvider(): Provider<"openai-completions"> {
 		name: "Cloudflare Workers AI",
 		auth: { apiKey: cloudflareWorkersAIAuth() },
 		models: Object.values(CLOUDFLARE_WORKERS_AI_MODELS),
-		api: openAICompletionsApi(),
+		api: cloudflareStreams(openAICompletionsApi()),
 	});
 }

packages/ai/src/providers/github-copilot.models.ts

@@ -252,7 +252,7 @@ export const GITHUB_COPILOT_MODELS = {
 			cacheRead: 0.2,
 			cacheWrite: 0,
 		},
-		contextWindow: 200000,
+		contextWindow: 1000000,
 		maxTokens: 64000,
 	} satisfies Model<"openai-completions">,
 	"gemini-3.5-flash": {
@@ -445,6 +445,63 @@ export const GITHUB_COPILOT_MODELS = {
 		contextWindow: 1000000,
 		maxTokens: 128000,
 	} satisfies Model<"openai-responses">,
+	"gpt-5.6-luna": {
+		id: "gpt-5.6-luna",
+		name: "GPT-5.6 Luna",
+		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,
+		thinkingLevelMap: {"off":null,"minimal":"low","xhigh":"xhigh","max":"max"},
+		input: ["text", "image"],
+		cost: {
+			input: 1,
+			output: 6,
+			cacheRead: 0.1,
+			cacheWrite: 0,
+		},
+		contextWindow: 1050000,
+		maxTokens: 128000,
+	} satisfies Model<"openai-responses">,
+	"gpt-5.6-sol": {
+		id: "gpt-5.6-sol",
+		name: "GPT-5.6 Sol",
+		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,
+		thinkingLevelMap: {"off":null,"minimal":"low","xhigh":"xhigh","max":"max"},
+		input: ["text", "image"],
+		cost: {
+			input: 5,
+			output: 30,
+			cacheRead: 0.5,
+			cacheWrite: 0,
+		},
+		contextWindow: 1050000,
+		maxTokens: 128000,
+	} satisfies Model<"openai-responses">,
+	"gpt-5.6-terra": {
+		id: "gpt-5.6-terra",
+		name: "GPT-5.6 Terra",
+		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,
+		thinkingLevelMap: {"off":null,"minimal":"low","xhigh":"xhigh","max":"max"},
+		input: ["text", "image"],
+		cost: {
+			input: 2.5,
+			output: 15,
+			cacheRead: 0.25,
+			cacheWrite: 0,
+		},
+		contextWindow: 1050000,
+		maxTokens: 128000,
+	} satisfies Model<"openai-responses">,
 	"kimi-k2.7-code": {
 		id: "kimi-k2.7-code",
 		name: "Kimi K2.7 Code",

packages/ai/src/providers/github-copilot.ts

@@ -2,8 +2,8 @@ import { anthropicMessagesApi } from "../api/anthropic-messages.lazy.ts";
 import { openAICompletionsApi } from "../api/openai-completions.lazy.ts";
 import { openAIResponsesApi } from "../api/openai-responses.lazy.ts";
 import { envApiKeyAuth, lazyOAuth } from "../auth/helpers.ts";
+import { loadGitHubCopilotOAuth } from "../auth/oauth/load.ts";
 import { createProvider, type Provider } from "../models.ts";
-import { loadGitHubCopilotOAuth } from "../utils/oauth/load.ts";
 import { GITHUB_COPILOT_MODELS } from "./github-copilot.models.ts";
 
 export function githubCopilotProvider(): Provider<"anthropic-messages" | "openai-completions" | "openai-responses"> {
@@ -16,6 +16,15 @@ export function githubCopilotProvider(): Provider<"anthropic-messages" | "openai
 			oauth: lazyOAuth({ name: "GitHub Copilot", load: loadGitHubCopilotOAuth }),
 		},
 		models: Object.values(GITHUB_COPILOT_MODELS),
+		filterModels: (models, credential) => {
+			if (credential?.type !== "oauth") return models;
+			const availableModelIds = credential.availableModelIds;
+			if (!Array.isArray(availableModelIds) || !availableModelIds.every((id) => typeof id === "string")) {
+				return models;
+			}
+			const available = new Set(availableModelIds);
+			return models.filter((model) => available.has(model.id));
+		},
 		api: {
 			"anthropic-messages": anthropicMessagesApi(),
 			"openai-completions": openAICompletionsApi(),

packages/ai/src/providers/google-vertex.ts

@@ -12,16 +12,71 @@ const VERTEX_ADC_PATH = "~/.config/gcloud/application_default_credentials.json";
  */
 const vertexAuth: ApiKeyAuth = {
 	name: "Google Cloud credentials",
+	login: async (interaction) => {
+		const method = await interaction.prompt({
+			type: "select",
+			message: "Select Google Vertex AI authentication method:",
+			options: [
+				{ id: "api-key", label: "Google Cloud API key" },
+				{ id: "adc", label: "Application Default Credentials" },
+				{ id: "service-account", label: "Service account credentials file" },
+			],
+		});
+		if (method === "api-key") {
+			return {
+				type: "api_key",
+				key: await interaction.prompt({ type: "secret", message: "Enter Google Cloud API key" }),
+			};
+		}
+		if (method !== "adc" && method !== "service-account") {
+			throw new Error(`Unknown Google Vertex AI auth method: ${method}`);
+		}
+		interaction.notify({
+			type: "info",
+			message:
+				method === "adc"
+					? "Run `gcloud auth application-default login`, then provide the project and location."
+					: "Provide a service account credentials file, project, and location.",
+			links: [
+				{
+					label: "Application Default Credentials",
+					url: "https://cloud.google.com/docs/authentication/provide-credentials-adc",
+				},
+			],
+		});
+		const project = await interaction.prompt({ type: "text", message: "Enter Google Cloud project ID" });
+		const location = await interaction.prompt({ type: "text", message: "Enter Google Cloud location" });
+		const credentialsPath =
+			method === "service-account"
+				? await interaction.prompt({ type: "text", message: "Enter service account credentials file path" })
+				: undefined;
+		return {
+			type: "api_key",
+			env: {
+				GOOGLE_CLOUD_PROJECT: project,
+				GOOGLE_CLOUD_LOCATION: location,
+				...(credentialsPath ? { GOOGLE_APPLICATION_CREDENTIALS: credentialsPath } : {}),
+			},
+		};
+	},
 	resolve: async ({ ctx, credential }) => {
 		const key = credential?.key ?? (await ctx.env("GOOGLE_CLOUD_API_KEY"));
 		if (key) return { auth: { apiKey: key }, source: credential?.key ? "stored credential" : "GOOGLE_CLOUD_API_KEY" };
 
-		const adcPath = await ctx.env("GOOGLE_APPLICATION_CREDENTIALS");
+		const adcPath =
+			credential?.env?.GOOGLE_APPLICATION_CREDENTIALS ?? (await ctx.env("GOOGLE_APPLICATION_CREDENTIALS"));
 		const hasCredentials = await ctx.fileExists(adcPath ?? VERTEX_ADC_PATH);
-		const hasProject = Boolean((await ctx.env("GOOGLE_CLOUD_PROJECT")) ?? (await ctx.env("GCLOUD_PROJECT")));
-		const hasLocation = Boolean(await ctx.env("GOOGLE_CLOUD_LOCATION"));
-		if (hasCredentials && hasProject && hasLocation) {
-			return { auth: {}, source: "gcloud application default credentials" };
+		const project =
+			credential?.env?.GOOGLE_CLOUD_PROJECT ??
+			(await ctx.env("GOOGLE_CLOUD_PROJECT")) ??
+			(await ctx.env("GCLOUD_PROJECT"));
+		const location = credential?.env?.GOOGLE_CLOUD_LOCATION ?? (await ctx.env("GOOGLE_CLOUD_LOCATION"));
+		if (hasCredentials && project && location) {
+			return {
+				auth: {},
+				env: credential?.env,
+				source: credential ? "stored credential" : "gcloud application default credentials",
+			};
 		}
 		return undefined;
 	},

packages/ai/src/providers/openai-codex.ts

@@ -1,7 +1,7 @@
 import { openAICodexResponsesApi } from "../api/openai-codex-responses.lazy.ts";
 import { lazyOAuth } from "../auth/helpers.ts";
+import { loadOpenAICodexOAuth } from "../auth/oauth/load.ts";
 import { createProvider, type Provider } from "../models.ts";
-import { loadOpenAICodexOAuth } from "../utils/oauth/load.ts";
 import { OPENAI_CODEX_MODELS } from "./openai-codex.models.ts";
 
 export function openaiCodexProvider(): Provider<"openai-codex-responses"> {

packages/ai/src/providers/openai.models.ts

@@ -667,6 +667,23 @@ export const OPENAI_MODELS = {
 		contextWindow: 272000,
 		maxTokens: 128000,
 	} satisfies Model<"openai-responses">,
+	"gpt-realtime-2.1": {
+		id: "gpt-realtime-2.1",
+		name: "GPT-Realtime-2.1",
+		api: "openai-responses",
+		provider: "openai",
+		baseUrl: "https://api.openai.com/v1",
+		reasoning: true,
+		input: ["text", "image"],
+		cost: {
+			input: 4,
+			output: 24,
+			cacheRead: 0.4,
+			cacheWrite: 0,
+		},
+		contextWindow: 128000,
+		maxTokens: 32000,
+	} satisfies Model<"openai-responses">,
 	"o1": {
 		id: "o1",
 		name: "o1",

packages/ai/src/providers/opencode.models.ts

@@ -674,6 +674,60 @@ export const OPENCODE_MODELS = {
 		contextWindow: 1050000,
 		maxTokens: 128000,
 	} satisfies Model<"openai-responses">,
+	"gpt-5.6-luna": {
+		id: "gpt-5.6-luna",
+		name: "GPT-5.6 Luna",
+		api: "openai-responses",
+		provider: "opencode",
+		baseUrl: "https://opencode.ai/zen/v1",
+		reasoning: true,
+		thinkingLevelMap: {"off":null,"xhigh":"xhigh","max":"max"},
+		input: ["text", "image"],
+		cost: {
+			input: 1,
+			output: 6,
+			cacheRead: 0.1,
+			cacheWrite: 1.25,
+		},
+		contextWindow: 1050000,
+		maxTokens: 128000,
+	} satisfies Model<"openai-responses">,
+	"gpt-5.6-sol": {
+		id: "gpt-5.6-sol",
+		name: "GPT-5.6 Sol",
+		api: "openai-responses",
+		provider: "opencode",
+		baseUrl: "https://opencode.ai/zen/v1",
+		reasoning: true,
+		thinkingLevelMap: {"off":null,"xhigh":"xhigh","max":"max"},
+		input: ["text", "image"],
+		cost: {
+			input: 5,
+			output: 30,
+			cacheRead: 0.5,
+			cacheWrite: 6.25,
+		},
+		contextWindow: 1050000,
+		maxTokens: 128000,
+	} satisfies Model<"openai-responses">,
+	"gpt-5.6-terra": {
+		id: "gpt-5.6-terra",
+		name: "GPT-5.6 Terra",
+		api: "openai-responses",
+		provider: "opencode",
+		baseUrl: "https://opencode.ai/zen/v1",
+		reasoning: true,
+		thinkingLevelMap: {"off":null,"xhigh":"xhigh","max":"max"},
+		input: ["text", "image"],
+		cost: {
+			input: 2.5,
+			output: 15,
+			cacheRead: 0.25,
+			cacheWrite: 3.125,
+		},
+		contextWindow: 1050000,
+		maxTokens: 128000,
+	} satisfies Model<"openai-responses">,
 	"grok-4.5": {
 		id: "grok-4.5",
 		name: "Grok 4.5",
@@ -726,7 +780,7 @@ export const OPENCODE_MODELS = {
 			cacheRead: 0,
 			cacheWrite: 0,
 		},
-		contextWindow: 256000,
+		contextWindow: 190000,
 		maxTokens: 64000,
 	} satisfies Model<"openai-completions">,
 	"kimi-k2.5": {

packages/ai/src/providers/openrouter.models.ts

@@ -461,24 +461,6 @@ export const OPENROUTER_MODELS = {
 		contextWindow: 262144,
 		maxTokens: 80000,
 	} satisfies Model<"openai-completions">,
-	"arcee-ai/trinity-mini": {
-		id: "arcee-ai/trinity-mini",
-		name: "Arcee AI: Trinity Mini",
-		api: "openai-completions",
-		provider: "openrouter",
-		baseUrl: "https://openrouter.ai/api/v1",
-		compat: {"supportsDeveloperRole":false,"thinkingFormat":"openrouter"},
-		reasoning: true,
-		input: ["text"],
-		cost: {
-			input: 0.045,
-			output: 0.15,
-			cacheRead: 0,
-			cacheWrite: 0,
-		},
-		contextWindow: 131072,
-		maxTokens: 131072,
-	} satisfies Model<"openai-completions">,
 	"arcee-ai/virtuoso-large": {
 		id: "arcee-ai/virtuoso-large",
 		name: "Arcee AI: Virtuoso Large",
@@ -687,8 +669,8 @@ export const OPENROUTER_MODELS = {
 		reasoning: true,
 		input: ["text"],
 		cost: {
-			input: 0.21,
-			output: 0.79,
+			input: 0.25,
+			output: 0.95,
 			cacheRead: 0.13,
 			cacheWrite: 0,
 		},
@@ -759,9 +741,9 @@ export const OPENROUTER_MODELS = {
 		reasoning: true,
 		input: ["text"],
 		cost: {
-			input: 0.2288,
-			output: 0.3432,
-			cacheRead: 0.02288,
+			input: 0.2145,
+			output: 0.32175,
+			cacheRead: 0.02145,
 			cacheWrite: 0,
 		},
 		contextWindow: 131072,
@@ -1121,13 +1103,13 @@ export const OPENROUTER_MODELS = {
 		reasoning: true,
 		input: ["text", "image"],
 		cost: {
-			input: 0.12,
+			input: 0.06,
 			output: 0.35,
-			cacheRead: 0.09,
+			cacheRead: 0,
 			cacheWrite: 0,
 		},
 		contextWindow: 262144,
-		maxTokens: 262144,
+		maxTokens: 8192,
 	} satisfies Model<"openai-completions">,
 	"google/gemma-4-31b-it:free": {
 		id: "google/gemma-4-31b-it:free",
@@ -1145,7 +1127,7 @@ export const OPENROUTER_MODELS = {
 			cacheWrite: 0,
 		},
 		contextWindow: 262144,
-		maxTokens: 8192,
+		maxTokens: 32768,
 	} satisfies Model<"openai-completions">,
 	"ibm-granite/granite-4.1-8b": {
 		id: "ibm-granite/granite-4.1-8b",
@@ -1238,6 +1220,24 @@ export const OPENROUTER_MODELS = {
 		contextWindow: 262144,
 		maxTokens: 65536,
 	} satisfies Model<"openai-completions">,
+	"kwaipilot/kat-coder-air-v2.5": {
+		id: "kwaipilot/kat-coder-air-v2.5",
+		name: "Kwaipilot: KAT-Coder-Air V2.5",
+		api: "openai-completions",
+		provider: "openrouter",
+		baseUrl: "https://openrouter.ai/api/v1",
+		compat: {"supportsDeveloperRole":false,"thinkingFormat":"openrouter"},
+		reasoning: false,
+		input: ["text"],
+		cost: {
+			input: 0.15,
+			output: 0.6,
+			cacheRead: 0.03,
+			cacheWrite: 0,
+		},
+		contextWindow: 256000,
+		maxTokens: 80000,
+	} satisfies Model<"openai-completions">,
 	"kwaipilot/kat-coder-pro-v2": {
 		id: "kwaipilot/kat-coder-pro-v2",
 		name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -1256,23 +1256,23 @@ export const OPENROUTER_MODELS = {
 		contextWindow: 256000,
 		maxTokens: 80000,
 	} satisfies Model<"openai-completions">,
-	"liquid/lfm-2.5-1.2b-thinking:free": {
-		id: "liquid/lfm-2.5-1.2b-thinking:free",
-		name: "LiquidAI: LFM2.5-1.2B-Thinking (free)",
+	"kwaipilot/kat-coder-pro-v2.5": {
+		id: "kwaipilot/kat-coder-pro-v2.5",
+		name: "Kwaipilot: KAT-Coder-Pro V2.5",
 		api: "openai-completions",
 		provider: "openrouter",
 		baseUrl: "https://openrouter.ai/api/v1",
 		compat: {"supportsDeveloperRole":false,"thinkingFormat":"openrouter"},
-		reasoning: true,
+		reasoning: false,
 		input: ["text"],
 		cost: {
-			input: 0,
-			output: 0,
-			cacheRead: 0,
+			input: 0.74,
+			output: 2.96,
+			cacheRead: 0.15,
 			cacheWrite: 0,
 		},
-		contextWindow: 32768,
-		maxTokens: 4096,
+		contextWindow: 256000,
+		maxTokens: 80000,
 	} satisfies Model<"openai-completions">,
 	"meta-llama/llama-3.1-70b-instruct": {
 		id: "meta-llama/llama-3.1-70b-instruct",
@@ -1356,8 +1356,8 @@ export const OPENROUTER_MODELS = {
 		reasoning: false,
 		input: ["text", "image"],
 		cost: {
-			input: 0.15,
-			output: 0.6,
+			input: 0.2,
+			output: 0.8,
 			cacheRead: 0,
 			cacheWrite: 0,
 		},
@@ -1878,9 +1878,9 @@ export const OPENROUTER_MODELS = {
 		reasoning: true,
 		input: ["text", "image"],
 		cost: {
-			input: 0.65,
+			input: 0.66,
 			output: 3.41,
-			cacheRead: 0.14,
+			cacheRead: 0.15,
 			cacheWrite: 0,
 		},
 		contextWindow: 262144,
@@ -1896,9 +1896,9 @@ export const OPENROUTER_MODELS = {
 		reasoning: true,
 		input: ["text", "image"],
 		cost: {
-			input: 0.72,
+			input: 0.719,
 			output: 3.49,
-			cacheRead: 0.159,
+			cacheRead: 0.149,
 			cacheWrite: 0,
 		},
 		contextWindow: 262144,
@@ -2456,11 +2456,11 @@ export const OPENROUTER_MODELS = {
 		cost: {
 			input: 0.05,
 			output: 0.4,
-			cacheRead: 0.01,
+			cacheRead: 0.005,
 			cacheWrite: 0,
 		},
 		contextWindow: 400000,
-		maxTokens: 4096,
+		maxTokens: 128000,
 	} satisfies Model<"openai-completions">,
 	"openai/gpt-5-pro": {
 		id: "openai/gpt-5-pro",
@@ -2492,7 +2492,7 @@ export const OPENROUTER_MODELS = {
 		cost: {
 			input: 1.25,
 			output: 10,
-			cacheRead: 0.13,
+			cacheRead: 0.125,
 			cacheWrite: 0,
 		},
 		contextWindow: 400000,
@@ -2976,26 +2976,8 @@ export const OPENROUTER_MODELS = {
 		reasoning: true,
 		input: ["text"],
 		cost: {
-			input: 0.036,
-			output: 0.18,
-			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)",
-		api: "openai-completions",
-		provider: "openrouter",
-		baseUrl: "https://openrouter.ai/api/v1",
-		compat: {"thinkingFormat":"openrouter"},
-		reasoning: true,
-		input: ["text"],
-		cost: {
-			input: 0,
-			output: 0,
+			input: 0.03,
+			output: 0.15,
 			cacheRead: 0,
 			cacheWrite: 0,
 		},
@@ -3481,7 +3463,7 @@ export const OPENROUTER_MODELS = {
 		input: ["text"],
 		cost: {
 			input: 0.09,
-			output: 0.1,
+			output: 0.55,
 			cacheRead: 0,
 			cacheWrite: 0,
 		},
@@ -4074,13 +4056,13 @@ export const OPENROUTER_MODELS = {
 		reasoning: true,
 		input: ["text", "image"],
 		cost: {
-			input: 0.285,
+			input: 0.289,
 			output: 2.4,
-			cacheRead: 0.15,
+			cacheRead: 0,
 			cacheWrite: 0,
 		},
 		contextWindow: 262144,
-		maxTokens: 262140,
+		maxTokens: 131072,
 	} satisfies Model<"openai-completions">,
 	"qwen/qwen3.6-35b-a3b": {
 		id: "qwen/qwen3.6-35b-a3b",
@@ -4561,12 +4543,12 @@ export const OPENROUTER_MODELS = {
 		input: ["text"],
 		cost: {
 			input: 0.43,
-			output: 1.74,
+			output: 1.75,
 			cacheRead: 0.08,
 			cacheWrite: 0,
 		},
-		contextWindow: 202752,
-		maxTokens: 131072,
+		contextWindow: 200000,
+		maxTokens: 16384,
 	} satisfies Model<"openai-completions">,
 	"z-ai/glm-4.6v": {
 		id: "z-ai/glm-4.6v",
@@ -4638,7 +4620,7 @@ export const OPENROUTER_MODELS = {
 			cacheWrite: 0,
 		},
 		contextWindow: 202752,
-		maxTokens: 4096,
+		maxTokens: 128000,
 	} satisfies Model<"openai-completions">,
 	"z-ai/glm-5-turbo": {
 		id: "z-ai/glm-5-turbo",
@@ -4687,13 +4669,13 @@ export const OPENROUTER_MODELS = {
 		thinkingLevelMap: {"xhigh":"xhigh"},
 		input: ["text"],
 		cost: {
-			input: 0.54,
-			output: 1.76,
-			cacheRead: 0.1,
+			input: 0.924,
+			output: 2.904,
+			cacheRead: 0.1716,
 			cacheWrite: 0,
 		},
 		contextWindow: 1048576,
-		maxTokens: 101376,
+		maxTokens: 131072,
 	} satisfies Model<"openai-completions">,
 	"z-ai/glm-5v-turbo": {
 		id: "z-ai/glm-5v-turbo",
@@ -4831,9 +4813,9 @@ export const OPENROUTER_MODELS = {
 		reasoning: true,
 		input: ["text", "image"],
 		cost: {
-			input: 0.65,
+			input: 0.66,
 			output: 3.41,
-			cacheRead: 0.14,
+			cacheRead: 0.15,
 			cacheWrite: 0,
 		},
 		contextWindow: 262144,

packages/ai/src/providers/vercel-ai-gateway.models.ts

@@ -497,23 +497,6 @@ export const VERCEL_AI_GATEWAY_MODELS = {
 		contextWindow: 200000,
 		maxTokens: 4096,
 	} satisfies Model<"anthropic-messages">,
-	"anthropic/claude-3.5-haiku": {
-		id: "anthropic/claude-3.5-haiku",
-		name: "Claude 3.5 Haiku",
-		api: "anthropic-messages",
-		provider: "vercel-ai-gateway",
-		baseUrl: "https://ai-gateway.vercel.sh",
-		reasoning: false,
-		input: ["text", "image"],
-		cost: {
-			input: 0.8,
-			output: 4,
-			cacheRead: 0.08,
-			cacheWrite: 1,
-		},
-		contextWindow: 200000,
-		maxTokens: 8192,
-	} satisfies Model<"anthropic-messages">,
 	"anthropic/claude-fable-5": {
 		id: "anthropic/claude-fable-5",
 		name: "Claude Fable 5",
@@ -565,7 +548,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
 			cacheWrite: 18.75,
 		},
 		contextWindow: 200000,
-		maxTokens: 32000,
+		maxTokens: 8192,
 	} satisfies Model<"anthropic-messages">,
 	"anthropic/claude-opus-4.1": {
 		id: "anthropic/claude-opus-4.1",
@@ -673,7 +656,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
 			cacheWrite: 3.75,
 		},
 		contextWindow: 1000000,
-		maxTokens: 64000,
+		maxTokens: 8192,
 	} satisfies Model<"anthropic-messages">,
 	"anthropic/claude-sonnet-4.5": {
 		id: "anthropic/claude-sonnet-4.5",
@@ -730,23 +713,6 @@ export const VERCEL_AI_GATEWAY_MODELS = {
 		contextWindow: 1000000,
 		maxTokens: 128000,
 	} satisfies Model<"anthropic-messages">,
-	"arcee-ai/trinity-large-preview": {
-		id: "arcee-ai/trinity-large-preview",
-		name: "Trinity Large Preview",
-		api: "anthropic-messages",
-		provider: "vercel-ai-gateway",
-		baseUrl: "https://ai-gateway.vercel.sh",
-		reasoning: false,
-		input: ["text"],
-		cost: {
-			input: 0.25,
-			output: 1,
-			cacheRead: 0,
-			cacheWrite: 0,
-		},
-		contextWindow: 131000,
-		maxTokens: 131000,
-	} satisfies Model<"anthropic-messages">,
 	"arcee-ai/trinity-large-thinking": {
 		id: "arcee-ai/trinity-large-thinking",
 		name: "Trinity Large Thinking",
@@ -875,12 +841,12 @@ export const VERCEL_AI_GATEWAY_MODELS = {
 		reasoning: true,
 		input: ["text"],
 		cost: {
-			input: 0.6,
-			output: 1.7,
-			cacheRead: 0,
+			input: 0.21,
+			output: 0.79,
+			cacheRead: 0.13,
 			cacheWrite: 0,
 		},
-		contextWindow: 128000,
+		contextWindow: 163840,
 		maxTokens: 128000,
 	} satisfies Model<"anthropic-messages">,
 	"deepseek/deepseek-v3.1-terminus": {
@@ -945,7 +911,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
 		cost: {
 			input: 0.14,
 			output: 0.28,
-			cacheRead: 0.0028,
+			cacheRead: 0.028,
 			cacheWrite: 0,
 		},
 		contextWindow: 1000000,
@@ -1206,6 +1172,23 @@ export const VERCEL_AI_GATEWAY_MODELS = {
 		contextWindow: 1000000,
 		maxTokens: 32000,
 	} satisfies Model<"anthropic-messages">,
+	"kwaipilot/kat-coder-air-v2.5": {
+		id: "kwaipilot/kat-coder-air-v2.5",
+		name: "Kat Coder Air V2.5",
+		api: "anthropic-messages",
+		provider: "vercel-ai-gateway",
+		baseUrl: "https://ai-gateway.vercel.sh",
+		reasoning: true,
+		input: ["text"],
+		cost: {
+			input: 0.15,
+			output: 0.6,
+			cacheRead: 0.03,
+			cacheWrite: 0,
+		},
+		contextWindow: 256000,
+		maxTokens: 80000,
+	} satisfies Model<"anthropic-messages">,
 	"kwaipilot/kat-coder-pro-v1": {
 		id: "kwaipilot/kat-coder-pro-v1",
 		name: "KAT-Coder-Pro V1",
@@ -1240,39 +1223,22 @@ export const VERCEL_AI_GATEWAY_MODELS = {
 		contextWindow: 256000,
 		maxTokens: 256000,
 	} satisfies Model<"anthropic-messages">,
-	"meituan/longcat-flash-chat": {
-		id: "meituan/longcat-flash-chat",
-		name: "LongCat Flash Chat",
-		api: "anthropic-messages",
-		provider: "vercel-ai-gateway",
-		baseUrl: "https://ai-gateway.vercel.sh",
-		reasoning: false,
-		input: ["text"],
-		cost: {
-			input: 0,
-			output: 0,
-			cacheRead: 0,
-			cacheWrite: 0,
-		},
-		contextWindow: 128000,
-		maxTokens: 100000,
-	} satisfies Model<"anthropic-messages">,
-	"meituan/longcat-flash-thinking-2601": {
-		id: "meituan/longcat-flash-thinking-2601",
-		name: "LongCat Flash Thinking 2601",
+	"kwaipilot/kat-coder-pro-v2.5": {
+		id: "kwaipilot/kat-coder-pro-v2.5",
+		name: "Kat Coder Pro V2.5",
 		api: "anthropic-messages",
 		provider: "vercel-ai-gateway",
 		baseUrl: "https://ai-gateway.vercel.sh",
 		reasoning: true,
 		input: ["text"],
 		cost: {
-			input: 0,
-			output: 0,
-			cacheRead: 0,
+			input: 0.74,
+			output: 2.96,
+			cacheRead: 0.15,
 			cacheWrite: 0,
 		},
-		contextWindow: 32768,
-		maxTokens: 32768,
+		contextWindow: 256000,
+		maxTokens: 80000,
 	} satisfies Model<"anthropic-messages">,
 	"meta/llama-3.1-70b": {
 		id: "meta/llama-3.1-70b",
@@ -1400,7 +1366,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
 		provider: "vercel-ai-gateway",
 		baseUrl: "https://ai-gateway.vercel.sh",
 		reasoning: true,
-		input: ["text"],
+		input: ["text", "image"],
 		cost: {
 			input: 1.25,
 			output: 4.25,
@@ -1580,23 +1546,6 @@ export const VERCEL_AI_GATEWAY_MODELS = {
 		contextWindow: 256000,
 		maxTokens: 256000,
 	} satisfies Model<"anthropic-messages">,
-	"mistral/devstral-small": {
-		id: "mistral/devstral-small",
-		name: "Devstral Small 1.1",
-		api: "anthropic-messages",
-		provider: "vercel-ai-gateway",
-		baseUrl: "https://ai-gateway.vercel.sh",
-		reasoning: false,
-		input: ["text"],
-		cost: {
-			input: 0.1,
-			output: 0.3,
-			cacheRead: 0,
-			cacheWrite: 0,
-		},
-		contextWindow: 128000,
-		maxTokens: 64000,
-	} satisfies Model<"anthropic-messages">,
 	"mistral/devstral-small-2": {
 		id: "mistral/devstral-small-2",
 		name: "Devstral Small 2",
@@ -1801,23 +1750,6 @@ export const VERCEL_AI_GATEWAY_MODELS = {
 		contextWindow: 128000,
 		maxTokens: 4000,
 	} satisfies Model<"anthropic-messages">,
-	"mistral/pixtral-large": {
-		id: "mistral/pixtral-large",
-		name: "Pixtral Large",
-		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,
-			cacheWrite: 0,
-		},
-		contextWindow: 128000,
-		maxTokens: 4000,
-	} satisfies Model<"anthropic-messages">,
 	"moonshotai/kimi-k2": {
 		id: "moonshotai/kimi-k2",
 		name: "Kimi K2 Instruct",
@@ -2972,40 +2904,6 @@ export const VERCEL_AI_GATEWAY_MODELS = {
 		contextWindow: 256000,
 		maxTokens: 256000,
 	} satisfies Model<"anthropic-messages">,
-	"xiaomi/mimo-v2-flash": {
-		id: "xiaomi/mimo-v2-flash",
-		name: "MiMo V2 Flash",
-		api: "anthropic-messages",
-		provider: "vercel-ai-gateway",
-		baseUrl: "https://ai-gateway.vercel.sh",
-		reasoning: true,
-		input: ["text"],
-		cost: {
-			input: 0.1,
-			output: 0.3,
-			cacheRead: 0.01,
-			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: 0.2,
-			cacheWrite: 0,
-		},
-		contextWindow: 1000000,
-		maxTokens: 128000,
-	} satisfies Model<"anthropic-messages">,
 	"xiaomi/mimo-v2.5": {
 		id: "xiaomi/mimo-v2.5",
 		name: "MiMo M2.5",
@@ -3270,9 +3168,9 @@ export const VERCEL_AI_GATEWAY_MODELS = {
 		reasoning: true,
 		input: ["text"],
 		cost: {
-			input: 3,
-			output: 10.25,
-			cacheRead: 0.5,
+			input: 2.1,
+			output: 6.6,
+			cacheRead: 0.21,
 			cacheWrite: 0,
 		},
 		contextWindow: 1000000,