feat(ai): add Moonshot AI provider model support

packages/ai/scripts/generate-models.ts

@@ -733,6 +733,47 @@ async function loadModelsDevData(): Promise<Model<any>[]> {
 			}
 		}
 
+		// Process Moonshot AI models
+		const moonshotVariants = [
+			{ key: "moonshotai", provider: "moonshotai", baseUrl: "https://api.moonshot.ai/v1" },
+			{ key: "moonshotai-cn", provider: "moonshotai-cn", baseUrl: "https://api.moonshot.cn/v1" },
+		] as const;
+		const moonshotCompat: OpenAICompletionsCompat = {
+			supportsStore: false,
+			supportsDeveloperRole: false,
+			supportsReasoningEffort: false,
+			maxTokensField: "max_tokens",
+			supportsStrictMode: false,
+		};
+
+		for (const { key, provider, baseUrl } of moonshotVariants) {
+			if (!data[key]?.models) continue;
+
+			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: "openai-completions",
+					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,
+					compat: moonshotCompat,
+				});
+			}
+		}
+
 		console.log(`Loaded ${models.length} tool-capable models from models.dev`);
 		return models;
 	} catch (error) {

packages/ai/src/env-api-keys.ts

@@ -113,6 +113,8 @@ function getApiKeyEnvVars(provider: string): readonly string[] | undefined {
 		mistral: "MISTRAL_API_KEY",
 		minimax: "MINIMAX_API_KEY",
 		"minimax-cn": "MINIMAX_CN_API_KEY",
+		moonshotai: "MOONSHOT_API_KEY",
+		"moonshotai-cn": "MOONSHOT_API_KEY",
 		huggingface: "HF_TOKEN",
 		fireworks: "FIREWORKS_API_KEY",
 		opencode: "OPENCODE_API_KEY",

packages/ai/src/models.generated.ts

@@ -6010,6 +6010,262 @@ export const MODELS = {
 			maxTokens: 128000,
 		} satisfies Model<"mistral-conversations">,
 	},
+	"moonshotai": {
+		"kimi-k2-0711-preview": {
+			id: "kimi-k2-0711-preview",
+			name: "Kimi K2 0711",
+			api: "openai-completions",
+			provider: "moonshotai",
+			baseUrl: "https://api.moonshot.ai/v1",
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.6,
+				output: 2.5,
+				cacheRead: 0.15,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"kimi-k2-0905-preview": {
+			id: "kimi-k2-0905-preview",
+			name: "Kimi K2 0905",
+			api: "openai-completions",
+			provider: "moonshotai",
+			baseUrl: "https://api.moonshot.ai/v1",
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.6,
+				output: 2.5,
+				cacheRead: 0.15,
+				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: "moonshotai",
+			baseUrl: "https://api.moonshot.ai/v1",
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.6,
+				output: 2.5,
+				cacheRead: 0.15,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"kimi-k2-thinking-turbo": {
+			id: "kimi-k2-thinking-turbo",
+			name: "Kimi K2 Thinking Turbo",
+			api: "openai-completions",
+			provider: "moonshotai",
+			baseUrl: "https://api.moonshot.ai/v1",
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 1.15,
+				output: 8,
+				cacheRead: 0.15,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"kimi-k2-turbo-preview": {
+			id: "kimi-k2-turbo-preview",
+			name: "Kimi K2 Turbo",
+			api: "openai-completions",
+			provider: "moonshotai",
+			baseUrl: "https://api.moonshot.ai/v1",
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 2.4,
+				output: 10,
+				cacheRead: 0.6,
+				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: "moonshotai",
+			baseUrl: "https://api.moonshot.ai/v1",
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.6,
+				output: 3,
+				cacheRead: 0.1,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"kimi-k2.6": {
+			id: "kimi-k2.6",
+			name: "Kimi K2.6",
+			api: "openai-completions",
+			provider: "moonshotai",
+			baseUrl: "https://api.moonshot.ai/v1",
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.95,
+				output: 4,
+				cacheRead: 0.16,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+	},
+	"moonshotai-cn": {
+		"kimi-k2-0711-preview": {
+			id: "kimi-k2-0711-preview",
+			name: "Kimi K2 0711",
+			api: "openai-completions",
+			provider: "moonshotai-cn",
+			baseUrl: "https://api.moonshot.cn/v1",
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.6,
+				output: 2.5,
+				cacheRead: 0.15,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"kimi-k2-0905-preview": {
+			id: "kimi-k2-0905-preview",
+			name: "Kimi K2 0905",
+			api: "openai-completions",
+			provider: "moonshotai-cn",
+			baseUrl: "https://api.moonshot.cn/v1",
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.6,
+				output: 2.5,
+				cacheRead: 0.15,
+				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: "moonshotai-cn",
+			baseUrl: "https://api.moonshot.cn/v1",
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.6,
+				output: 2.5,
+				cacheRead: 0.15,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"kimi-k2-thinking-turbo": {
+			id: "kimi-k2-thinking-turbo",
+			name: "Kimi K2 Thinking Turbo",
+			api: "openai-completions",
+			provider: "moonshotai-cn",
+			baseUrl: "https://api.moonshot.cn/v1",
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 1.15,
+				output: 8,
+				cacheRead: 0.15,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"kimi-k2-turbo-preview": {
+			id: "kimi-k2-turbo-preview",
+			name: "Kimi K2 Turbo",
+			api: "openai-completions",
+			provider: "moonshotai-cn",
+			baseUrl: "https://api.moonshot.cn/v1",
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 2.4,
+				output: 10,
+				cacheRead: 0.6,
+				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: "moonshotai-cn",
+			baseUrl: "https://api.moonshot.cn/v1",
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.6,
+				output: 3,
+				cacheRead: 0.1,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"kimi-k2.6": {
+			id: "kimi-k2.6",
+			name: "Kimi K2.6",
+			api: "openai-completions",
+			provider: "moonshotai-cn",
+			baseUrl: "https://api.moonshot.cn/v1",
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.95,
+				output: 4,
+				cacheRead: 0.16,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+	},
 	"openai": {
 		"gpt-4": {
 			id: "gpt-4",
@@ -9585,13 +9841,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0.75,
+				input: 0.74,
-				output: 3.5,
+				output: 3.49,
-				cacheRead: 0.15,
+				cacheRead: 0.14,
 				cacheWrite: 0,
 			},
-			contextWindow: 262144,
+			contextWindow: 262142,
-			maxTokens: 16384,
+			maxTokens: 262142,
 		} satisfies Model<"openai-completions">,
 		"nex-agi/deepseek-v3.1-nex-n1": {
 			id: "nex-agi/deepseek-v3.1-nex-n1",
@@ -10766,6 +11022,23 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
+		"openrouter/owl-alpha": {
+			id: "openrouter/owl-alpha",
+			name: "Owl Alpha",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048756,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
 		"poolside/laguna-m.1:free": {
 			id: "poolside/laguna-m.1:free",
 			name: "Poolside: Laguna M.1 (free)",
@@ -12339,13 +12612,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0.75,
+				input: 0.74,
-				output: 3.5,
+				output: 3.49,
-				cacheRead: 0.15,
+				cacheRead: 0.14,
 				cacheWrite: 0,
 			},
-			contextWindow: 262144,
+			contextWindow: 262142,
-			maxTokens: 16384,
+			maxTokens: 262142,
 		} satisfies Model<"openai-completions">,
 		"~openai/gpt-latest": {
 			id: "~openai/gpt-latest",

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

@@ -1027,6 +1027,7 @@ function detectCompat(model: Model<"openai-completions">): ResolvedOpenAIComplet
 	const baseUrl = model.baseUrl;
 
 	const isZai = provider === "zai" || baseUrl.includes("api.z.ai");
+	const isMoonshot = provider === "moonshotai" || provider === "moonshotai-cn" || baseUrl.includes("api.moonshot.");
 	const isCloudflareWorkersAI = provider === "cloudflare-workers-ai" || baseUrl.includes("api.cloudflare.com");
 
 	const isNonStandard =
@@ -1037,11 +1038,12 @@ function detectCompat(model: Model<"openai-completions">): ResolvedOpenAIComplet
 		baseUrl.includes("chutes.ai") ||
 		baseUrl.includes("deepseek.com") ||
 		isZai ||
+		isMoonshot ||
 		provider === "opencode" ||
 		baseUrl.includes("opencode.ai") ||
 		isCloudflareWorkersAI;
 
-	const useMaxTokens = baseUrl.includes("chutes.ai");
+	const useMaxTokens = baseUrl.includes("chutes.ai") || isMoonshot;
 
 	const isGrok = provider === "xai" || baseUrl.includes("api.x.ai");
 	const isGroq = provider === "groq" || baseUrl.includes("groq.com");
@@ -1068,7 +1070,7 @@ function detectCompat(model: Model<"openai-completions">): ResolvedOpenAIComplet
 	return {
 		supportsStore: !isNonStandard,
 		supportsDeveloperRole: !isNonStandard,
-		supportsReasoningEffort: !isGrok && !isZai,
+		supportsReasoningEffort: !isGrok && !isZai && !isMoonshot,
 		reasoningEffortMap,
 		supportsUsageInStreaming: true,
 		maxTokensField: useMaxTokens ? "max_tokens" : "max_completion_tokens",
@@ -1086,7 +1088,7 @@ function detectCompat(model: Model<"openai-completions">): ResolvedOpenAIComplet
 		openRouterRouting: {},
 		vercelGatewayRouting: {},
 		zaiToolStream: false,
-		supportsStrictMode: true,
+		supportsStrictMode: !isMoonshot,
 		cacheControlFormat,
 		sendSessionAffinityHeaders: false,
 		supportsLongCacheRetention: true,

packages/ai/src/types.ts

@@ -37,6 +37,8 @@ export type KnownProvider =
 	| "mistral"
 	| "minimax"
 	| "minimax-cn"
+	| "moonshotai"
+	| "moonshotai-cn"
 	| "huggingface"
 	| "fireworks"
 	| "opencode"

packages/coding-agent/src/cli/args.ts

@@ -314,6 +314,7 @@ ${chalk.bold("Environment Variables:")}
   ZAI_API_KEY                      - ZAI API key
   MISTRAL_API_KEY                  - Mistral API key
   MINIMAX_API_KEY                  - MiniMax API key
+  MOONSHOT_API_KEY                 - Moonshot AI API key
   OPENCODE_API_KEY                 - OpenCode Zen/OpenCode Go API key
   KIMI_API_KEY                     - Kimi For Coding API key
   CLOUDFLARE_API_KEY               - Cloudflare API token (Workers AI)

packages/coding-agent/src/core/model-resolver.ts

@@ -32,6 +32,8 @@ export const defaultModelPerProvider: Record<KnownProvider, string> = {
 	mistral: "devstral-medium-latest",
 	minimax: "MiniMax-M2.7",
 	"minimax-cn": "MiniMax-M2.7",
+	moonshotai: "kimi-k2.6",
+	"moonshotai-cn": "kimi-k2.6",
 	huggingface: "moonshotai/Kimi-K2.6",
 	fireworks: "accounts/fireworks/models/kimi-k2p6",
 	opencode: "kimi-k2.6",

packages/coding-agent/src/core/provider-display-names.ts

@@ -14,6 +14,8 @@ export const BUILT_IN_PROVIDER_DISPLAY_NAMES: Record<string, string> = {
 	mistral: "Mistral",
 	minimax: "MiniMax",
 	"minimax-cn": "MiniMax (China)",
+	moonshotai: "Moonshot AI",
+	"moonshotai-cn": "Moonshot AI (China)",
 	opencode: "OpenCode Zen",
 	"opencode-go": "OpenCode Go",
 	openai: "OpenAI",