Add Ant Ling provider

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

@@ -99,6 +99,7 @@ function getApiKeyEnvVars(provider: string): readonly string[] | undefined {
 	}
 
 	const envMap: Record<string, string> = {
+		"ant-ling": "ANT_LING_API_KEY",
 		openai: "OPENAI_API_KEY",
 		"azure-openai-responses": "AZURE_OPENAI_API_KEY",
 		nvidia: "NVIDIA_API_KEY",

packages/ai/src/models.generated.ts

@@ -1552,6 +1552,63 @@ export const MODELS = {
 			maxTokens: 101376,
 		} satisfies Model<"bedrock-converse-stream">,
 	},
+	"ant-ling": {
+		"Ling-2.6-1T": {
+			id: "Ling-2.6-1T",
+			name: "Ling 2.6 1T",
+			api: "openai-completions",
+			provider: "ant-ling",
+			baseUrl: "https://api.ant-ling.com/v1",
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false},
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.06,
+				output: 0.25,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 65536,
+		} satisfies Model<"openai-completions">,
+		"Ling-2.6-flash": {
+			id: "Ling-2.6-flash",
+			name: "Ling 2.6 Flash",
+			api: "openai-completions",
+			provider: "ant-ling",
+			baseUrl: "https://api.ant-ling.com/v1",
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false},
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.01,
+				output: 0.02,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 65536,
+		} satisfies Model<"openai-completions">,
+		"Ring-2.6-1T": {
+			id: "Ring-2.6-1T",
+			name: "Ring 2.6 1T",
+			api: "openai-completions",
+			provider: "ant-ling",
+			baseUrl: "https://api.ant-ling.com/v1",
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"thinkingFormat":"ant-ling"},
+			reasoning: true,
+			thinkingLevelMap: {"off":null,"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"xhigh"},
+			input: ["text"],
+			cost: {
+				input: 0.06,
+				output: 0.25,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 65536,
+		} satisfies Model<"openai-completions">,
+	},
 	"anthropic": {
 		"claude-3-5-haiku-20241022": {
 			id: "claude-3-5-haiku-20241022",

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

@@ -578,6 +578,11 @@ function buildParams(
 		} else if (model.thinkingLevelMap?.off !== null) {
 			openRouterParams.reasoning = { effort: model.thinkingLevelMap?.off ?? "none" };
 		}
+	} else if (compat.thinkingFormat === "ant-ling" && model.reasoning && options?.reasoningEffort) {
+		const effort = model.thinkingLevelMap?.[options.reasoningEffort];
+		if (typeof effort === "string") {
+			(params as typeof params & { reasoning?: { effort: string } }).reasoning = { effort };
+		}
 	} else if (compat.thinkingFormat === "together" && model.reasoning) {
 		const togetherParams = params as Omit<typeof params, "reasoning_effort"> & {
 			reasoning?: { enabled: boolean };
@@ -1079,6 +1084,7 @@ function detectCompat(model: Model<"openai-completions">): ResolvedOpenAIComplet
 	const isCloudflareWorkersAI = provider === "cloudflare-workers-ai" || baseUrl.includes("api.cloudflare.com");
 	const isCloudflareAiGateway = provider === "cloudflare-ai-gateway" || baseUrl.includes("gateway.ai.cloudflare.com");
 	const isNvidia = provider === "nvidia" || baseUrl.includes("integrate.api.nvidia.com");
+	const isAntLing = provider === "ant-ling" || baseUrl.includes("api.ant-ling.com");
 
 	const isNonStandard =
 		isNvidia ||
@@ -1094,9 +1100,11 @@ function detectCompat(model: Model<"openai-completions">): ResolvedOpenAIComplet
 		provider === "opencode" ||
 		baseUrl.includes("opencode.ai") ||
 		isCloudflareWorkersAI ||
-		isCloudflareAiGateway;
+		isCloudflareAiGateway ||
+		isAntLing;
 
-	const useMaxTokens = baseUrl.includes("chutes.ai") || isMoonshot || isCloudflareAiGateway || isTogether || isNvidia;
+	const useMaxTokens =
+		baseUrl.includes("chutes.ai") || isMoonshot || isCloudflareAiGateway || isTogether || isNvidia || isAntLing;
 
 	const isGrok = provider === "xai" || baseUrl.includes("api.x.ai");
 	const isDeepSeek = provider === "deepseek" || baseUrl.includes("deepseek.com");
@@ -1107,7 +1115,8 @@ function detectCompat(model: Model<"openai-completions">): ResolvedOpenAIComplet
 	return {
 		supportsStore: !isNonStandard,
 		supportsDeveloperRole: isOpenRouterDeveloperRoleModel || (!isNonStandard && !isOpenRouter),
-		supportsReasoningEffort: !isGrok && !isZai && !isMoonshot && !isTogether && !isCloudflareAiGateway && !isNvidia,
+		supportsReasoningEffort:
+			!isGrok && !isZai && !isMoonshot && !isTogether && !isCloudflareAiGateway && !isNvidia && !isAntLing,
 		supportsUsageInStreaming: true,
 		maxTokensField: useMaxTokens ? "max_tokens" : "max_completion_tokens",
 		requiresToolResultName: false,
@@ -1120,16 +1129,24 @@ function detectCompat(model: Model<"openai-completions">): ResolvedOpenAIComplet
 				? "zai"
 				: isTogether
 					? "together"
-					: isOpenRouter
-						? "openrouter"
-						: "openai",
+					: isAntLing
+						? "ant-ling"
+						: isOpenRouter
+							? "openrouter"
+							: "openai",
 		openRouterRouting: {},
 		vercelGatewayRouting: {},
 		zaiToolStream: false,
 		supportsStrictMode: !isMoonshot && !isTogether && !isCloudflareAiGateway && !isNvidia,
 		cacheControlFormat,
 		sendSessionAffinityHeaders: false,
-		supportsLongCacheRetention: !(isTogether || isCloudflareWorkersAI || isCloudflareAiGateway || isNvidia),
+		supportsLongCacheRetention: !(
+			isTogether ||
+			isCloudflareWorkersAI ||
+			isCloudflareAiGateway ||
+			isNvidia ||
+			isAntLing
+		),
 	};
 }
 

packages/ai/src/types.ts

@@ -22,6 +22,7 @@ export type ImagesApi = KnownImagesApi | (string & {});
 
 export type KnownProvider =
 	| "amazon-bedrock"
+	| "ant-ling"
 	| "anthropic"
 	| "google"
 	| "google-vertex"
@@ -390,7 +391,7 @@ export interface OpenAICompletionsCompat {
 	requiresThinkingAsText?: boolean;
 	/** Whether all replayed assistant messages must include an empty reasoning_content field when reasoning is enabled. Default: auto-detected from URL. */
 	requiresReasoningContentOnAssistantMessages?: boolean;
-	/** Format for reasoning/thinking parameter. "openai" uses reasoning_effort, "openrouter" uses reasoning: { effort }, "deepseek" uses thinking: { type } plus reasoning_effort when supported, "together" uses reasoning: { enabled } plus reasoning_effort when supported, "zai" uses top-level enable_thinking: boolean, "qwen" uses top-level enable_thinking: boolean, "qwen-chat-template" uses chat_template_kwargs.enable_thinking, and "string-thinking" uses top-level thinking: string. Default: "openai". */
+	/** Format for reasoning/thinking parameter. "openai" uses reasoning_effort, "openrouter" uses reasoning: { effort }, "deepseek" uses thinking: { type } plus reasoning_effort when supported, "together" uses reasoning: { enabled } plus reasoning_effort when supported, "zai" uses top-level enable_thinking: boolean, "qwen" uses top-level enable_thinking: boolean, "qwen-chat-template" uses chat_template_kwargs.enable_thinking, "string-thinking" uses top-level thinking: string, and "ant-ling" uses reasoning: { effort } only when the mapped effort is non-null. Default: "openai". */
 	thinkingFormat?:
 		| "openai"
 		| "openrouter"
@@ -399,7 +400,8 @@ export interface OpenAICompletionsCompat {
 		| "zai"
 		| "qwen"
 		| "qwen-chat-template"
-		| "string-thinking";
+		| "string-thinking"
+		| "ant-ling";
 	/** OpenRouter-specific routing preferences. Only used when baseUrl points to OpenRouter. */
 	openRouterRouting?: OpenRouterRouting;
 	/** Vercel AI Gateway routing preferences. Only used when baseUrl points to Vercel AI Gateway. */