Add NVIDIA NIM provider

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

@@ -101,6 +101,7 @@ function getApiKeyEnvVars(provider: string): readonly string[] | undefined {
 	const envMap: Record<string, string> = {
 		openai: "OPENAI_API_KEY",
 		"azure-openai-responses": "AZURE_OPENAI_API_KEY",
+		nvidia: "NVIDIA_API_KEY",
 		deepseek: "DEEPSEEK_API_KEY",
 		google: "GEMINI_API_KEY",
 		"google-vertex": "GOOGLE_CLOUD_API_KEY",

packages/ai/src/models.generated.ts

@@ -6335,6 +6335,369 @@ export const MODELS = {
 			maxTokens: 262144,
 		} satisfies Model<"openai-completions">,
 	},
+	"nvidia": {
+		"meta/llama-3.1-70b-instruct": {
+			id: "meta/llama-3.1-70b-instruct",
+			name: "Llama 3.1 70b Instruct",
+			api: "openai-completions",
+			provider: "nvidia",
+			baseUrl: "https://integrate.api.nvidia.com/v1",
+			headers: {"NVCF-POLL-SECONDS":"3600"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"meta/llama-3.1-8b-instruct": {
+			id: "meta/llama-3.1-8b-instruct",
+			name: "Llama 3.1 8B Instruct",
+			api: "openai-completions",
+			provider: "nvidia",
+			baseUrl: "https://integrate.api.nvidia.com/v1",
+			headers: {"NVCF-POLL-SECONDS":"3600"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 16000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"meta/llama-3.2-11b-vision-instruct": {
+			id: "meta/llama-3.2-11b-vision-instruct",
+			name: "Llama 3.2 11b Vision Instruct",
+			api: "openai-completions",
+			provider: "nvidia",
+			baseUrl: "https://integrate.api.nvidia.com/v1",
+			headers: {"NVCF-POLL-SECONDS":"3600"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"meta/llama-3.2-90b-vision-instruct": {
+			id: "meta/llama-3.2-90b-vision-instruct",
+			name: "Llama-3.2-90B-Vision-Instruct",
+			api: "openai-completions",
+			provider: "nvidia",
+			baseUrl: "https://integrate.api.nvidia.com/v1",
+			headers: {"NVCF-POLL-SECONDS":"3600"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"meta/llama-3.3-70b-instruct": {
+			id: "meta/llama-3.3-70b-instruct",
+			name: "Llama 3.3 70b Instruct",
+			api: "openai-completions",
+			provider: "nvidia",
+			baseUrl: "https://integrate.api.nvidia.com/v1",
+			headers: {"NVCF-POLL-SECONDS":"3600"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"mistralai/mistral-large-3-675b-instruct-2512": {
+			id: "mistralai/mistral-large-3-675b-instruct-2512",
+			name: "Mistral Large 3 675B Instruct 2512",
+			api: "openai-completions",
+			provider: "nvidia",
+			baseUrl: "https://integrate.api.nvidia.com/v1",
+			headers: {"NVCF-POLL-SECONDS":"3600"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"mistralai/mistral-small-4-119b-2603": {
+			id: "mistralai/mistral-small-4-119b-2603",
+			name: "mistral-small-4-119b-2603",
+			api: "openai-completions",
+			provider: "nvidia",
+			baseUrl: "https://integrate.api.nvidia.com/v1",
+			headers: {"NVCF-POLL-SECONDS":"3600"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"moonshotai/kimi-k2.6": {
+			id: "moonshotai/kimi-k2.6",
+			name: "Kimi K2.6",
+			api: "openai-completions",
+			provider: "nvidia",
+			baseUrl: "https://integrate.api.nvidia.com/v1",
+			headers: {"NVCF-POLL-SECONDS":"3600"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"nvidia/llama-3.3-nemotron-super-49b-v1": {
+			id: "nvidia/llama-3.3-nemotron-super-49b-v1",
+			name: "Llama 3.3 Nemotron Super 49B v1",
+			api: "openai-completions",
+			provider: "nvidia",
+			baseUrl: "https://integrate.api.nvidia.com/v1",
+			headers: {"NVCF-POLL-SECONDS":"3600"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+		"nvidia/llama-3.3-nemotron-super-49b-v1.5": {
+			id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
+			name: "Llama 3.3 Nemotron Super 49B v1.5",
+			api: "openai-completions",
+			provider: "nvidia",
+			baseUrl: "https://integrate.api.nvidia.com/v1",
+			headers: {"NVCF-POLL-SECONDS":"3600"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+		"nvidia/nemotron-3-nano-30b-a3b": {
+			id: "nvidia/nemotron-3-nano-30b-a3b",
+			name: "nemotron-3-nano-30b-a3b",
+			api: "openai-completions",
+			provider: "nvidia",
+			baseUrl: "https://integrate.api.nvidia.com/v1",
+			headers: {"NVCF-POLL-SECONDS":"3600"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+		"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": {
+			id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
+			name: "Nemotron 3 Nano Omni",
+			api: "openai-completions",
+			provider: "nvidia",
+			baseUrl: "https://integrate.api.nvidia.com/v1",
+			headers: {"NVCF-POLL-SECONDS":"3600"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 65536,
+		} satisfies Model<"openai-completions">,
+		"nvidia/nemotron-3-super-120b-a12b": {
+			id: "nvidia/nemotron-3-super-120b-a12b",
+			name: "Nemotron 3 Super",
+			api: "openai-completions",
+			provider: "nvidia",
+			baseUrl: "https://integrate.api.nvidia.com/v1",
+			headers: {"NVCF-POLL-SECONDS":"3600"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.2,
+				output: 0.8,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"nvidia/nvidia-nemotron-nano-9b-v2": {
+			id: "nvidia/nvidia-nemotron-nano-9b-v2",
+			name: "nvidia-nemotron-nano-9b-v2",
+			api: "openai-completions",
+			provider: "nvidia",
+			baseUrl: "https://integrate.api.nvidia.com/v1",
+			headers: {"NVCF-POLL-SECONDS":"3600"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-oss-20b": {
+			id: "openai/gpt-oss-20b",
+			name: "GPT OSS 20B",
+			api: "openai-completions",
+			provider: "nvidia",
+			baseUrl: "https://integrate.api.nvidia.com/v1",
+			headers: {"NVCF-POLL-SECONDS":"3600"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 32768,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen3-coder-480b-a35b-instruct": {
+			id: "qwen/qwen3-coder-480b-a35b-instruct",
+			name: "Qwen3 Coder 480B A35B Instruct",
+			api: "openai-completions",
+			provider: "nvidia",
+			baseUrl: "https://integrate.api.nvidia.com/v1",
+			headers: {"NVCF-POLL-SECONDS":"3600"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 66536,
+		} satisfies Model<"openai-completions">,
+		"stepfun-ai/step-3.5-flash": {
+			id: "stepfun-ai/step-3.5-flash",
+			name: "Step 3.5 Flash",
+			api: "openai-completions",
+			provider: "nvidia",
+			baseUrl: "https://integrate.api.nvidia.com/v1",
+			headers: {"NVCF-POLL-SECONDS":"3600"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"stepfun-ai/step-3.7-flash": {
+			id: "stepfun-ai/step-3.7-flash",
+			name: "Step 3.7 Flash",
+			api: "openai-completions",
+			provider: "nvidia",
+			baseUrl: "https://integrate.api.nvidia.com/v1",
+			headers: {"NVCF-POLL-SECONDS":"3600"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"z-ai/glm-5.1": {
+			id: "z-ai/glm-5.1",
+			name: "GLM-5.1",
+			api: "openai-completions",
+			provider: "nvidia",
+			baseUrl: "https://integrate.api.nvidia.com/v1",
+			headers: {"NVCF-POLL-SECONDS":"3600"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+	},
 	"openai": {
 		"gpt-4": {
 			id: "gpt-4",

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

@@ -1078,8 +1078,10 @@ function detectCompat(model: Model<"openai-completions">): ResolvedOpenAIComplet
 	const isOpenRouter = provider === "openrouter" || baseUrl.includes("openrouter.ai");
 	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 isNonStandard =
+		isNvidia ||
 		provider === "cerebras" ||
 		baseUrl.includes("cerebras.ai") ||
 		provider === "xai" ||
@@ -1094,7 +1096,7 @@ function detectCompat(model: Model<"openai-completions">): ResolvedOpenAIComplet
 		isCloudflareWorkersAI ||
 		isCloudflareAiGateway;
 
-	const useMaxTokens = baseUrl.includes("chutes.ai") || isMoonshot || isCloudflareAiGateway || isTogether;
+	const useMaxTokens = baseUrl.includes("chutes.ai") || isMoonshot || isCloudflareAiGateway || isTogether || isNvidia;
 
 	const isGrok = provider === "xai" || baseUrl.includes("api.x.ai");
 	const isDeepSeek = provider === "deepseek" || baseUrl.includes("deepseek.com");
@@ -1103,7 +1105,7 @@ function detectCompat(model: Model<"openai-completions">): ResolvedOpenAIComplet
 	return {
 		supportsStore: !isNonStandard,
 		supportsDeveloperRole: !isNonStandard && !isOpenRouter,
-		supportsReasoningEffort: !isGrok && !isZai && !isMoonshot && !isTogether && !isCloudflareAiGateway,
+		supportsReasoningEffort: !isGrok && !isZai && !isMoonshot && !isTogether && !isCloudflareAiGateway && !isNvidia,
 		supportsUsageInStreaming: true,
 		maxTokensField: useMaxTokens ? "max_tokens" : "max_completion_tokens",
 		requiresToolResultName: false,
@@ -1122,10 +1124,10 @@ function detectCompat(model: Model<"openai-completions">): ResolvedOpenAIComplet
 		openRouterRouting: {},
 		vercelGatewayRouting: {},
 		zaiToolStream: false,
-		supportsStrictMode: !isMoonshot && !isTogether && !isCloudflareAiGateway,
+		supportsStrictMode: !isMoonshot && !isTogether && !isCloudflareAiGateway && !isNvidia,
 		cacheControlFormat,
 		sendSessionAffinityHeaders: false,
-		supportsLongCacheRetention: !(isTogether || isCloudflareWorkersAI || isCloudflareAiGateway),
+		supportsLongCacheRetention: !(isTogether || isCloudflareWorkersAI || isCloudflareAiGateway || isNvidia),
 	};
 }
 

packages/ai/src/types.ts

@@ -28,6 +28,7 @@ export type KnownProvider =
 	| "openai"
 	| "azure-openai-responses"
 	| "openai-codex"
+	| "nvidia"
 	| "deepseek"
 	| "github-copilot"
 	| "xai"