Add NVIDIA NIM provider

packages/ai/CHANGELOG.md

@@ -2,6 +2,10 @@
 
 ## [Unreleased]
 
+### Added
+
+- Added NVIDIA NIM as a built-in OpenAI-compatible provider, exposing public NIM models that support tool use.
+
 ### Fixed
 
 - Fixed Amazon Bedrock requests to replace blank required user/tool-result text with a placeholder and skip blank replay text blocks ([#4975](https://github.com/earendil-works/pi/issues/4975)).

packages/ai/README.md

@@ -54,6 +54,7 @@ Unified LLM API with automatic model discovery, provider configuration, token an
 - **Azure OpenAI (Responses)**
 - **OpenAI Codex** (ChatGPT Plus/Pro subscription, requires OAuth, see below)
 - **DeepSeek**
+- **NVIDIA NIM**
 - **Anthropic**
 - **Google**
 - **Vertex AI** (Gemini via Vertex AI)
@@ -801,7 +802,7 @@ A **provider** offers models through a specific API. For example:
 - **Google** models use the `google-generative-ai` API
 - **OpenAI** models use the `openai-responses` API
 - **Mistral** models use the `mistral-conversations` API
-- **xAI, Cerebras, Groq, Together AI, etc.** models use the `openai-completions` API (OpenAI-compatible)
+- **xAI, Cerebras, Groq, NVIDIA NIM, Together AI, etc.** models use the `openai-completions` API (OpenAI-compatible)
 
 ### Querying Providers and Models
 
@@ -923,7 +924,7 @@ const ollamaReasoningModel: Model<'openai-completions'> = {
 
 ### OpenAI Compatibility Settings
 
-The `openai-completions` API is implemented by many providers with minor differences. By default, the library auto-detects compatibility settings based on `baseUrl` for a small set of known OpenAI-compatible providers (Cerebras, xAI, Chutes, DeepSeek, Together AI, zAi, OpenCode, Cloudflare Workers AI, etc.). For custom proxies or unknown endpoints, you can override these settings via the `compat` field. For `openai-responses` models, the compat field only supports Responses-specific flags.
+The `openai-completions` API is implemented by many providers with minor differences. By default, the library auto-detects compatibility settings based on `baseUrl` for a small set of known OpenAI-compatible providers (Cerebras, xAI, Chutes, DeepSeek, NVIDIA NIM, Together AI, zAi, OpenCode, Cloudflare Workers AI, etc.). For custom proxies or unknown endpoints, you can override these settings via the `compat` field. For `openai-responses` models, the compat field only supports Responses-specific flags.
 
 ```typescript
 interface OpenAICompletionsCompat {
@@ -1102,6 +1103,7 @@ In Node.js environments, you can set environment variables to avoid passing API
 | Azure OpenAI | `AZURE_OPENAI_API_KEY` + `AZURE_OPENAI_BASE_URL` (e.g. `https://{resource}.openai.azure.com`) or `AZURE_OPENAI_RESOURCE_NAME`. Supports `*.openai.azure.com` and `*.cognitiveservices.azure.com`; root endpoints auto-normalize to `/openai/v1`. Optional: `AZURE_OPENAI_API_VERSION` (default `v1`), `AZURE_OPENAI_DEPLOYMENT_NAME_MAP`. |
 | Anthropic | `ANTHROPIC_API_KEY` or `ANTHROPIC_OAUTH_TOKEN` |
 | DeepSeek | `DEEPSEEK_API_KEY` |
+| NVIDIA NIM | `NVIDIA_API_KEY` |
 | Google | `GEMINI_API_KEY` |
 | Vertex AI | `GOOGLE_CLOUD_API_KEY` or `GOOGLE_CLOUD_PROJECT` (or `GCLOUD_PROJECT`) + `GOOGLE_CLOUD_LOCATION` + ADC |
 | Mistral | `MISTRAL_API_KEY` |

packages/ai/scripts/generate-models.ts

@@ -32,12 +32,17 @@ interface ModelsDevModel {
 	};
 	modalities?: {
 		input?: string[];
+		output?: string[];
 	};
 	provider?: {
 		npm?: string;
 	};
 }
 
+interface NvidiaNimModelListItem {
+	id: string;
+}
+
 interface AiGatewayModel {
 	id: string;
 	name?: string;
@@ -117,6 +122,39 @@ const TOGETHER_TOGGLE_REASONING_LEVEL_MAP = {
 
 const AI_GATEWAY_MODELS_URL = "https://ai-gateway.vercel.sh/v1";
 const AI_GATEWAY_BASE_URL = "https://ai-gateway.vercel.sh";
+const NVIDIA_BASE_URL = "https://integrate.api.nvidia.com/v1";
+const NVIDIA_HEADERS = {
+	"NVCF-POLL-SECONDS": "3600",
+} as const;
+const NVIDIA_OPENAI_COMPAT: OpenAICompletionsCompat = {
+	supportsStore: false,
+	supportsDeveloperRole: false,
+	supportsReasoningEffort: false,
+	maxTokensField: "max_tokens",
+	supportsStrictMode: false,
+	supportsLongCacheRetention: false,
+};
+const NVIDIA_NIM_UNSUPPORTED_MODELS = new Set([
+	"abacusai/dracarys-llama-3.1-70b-instruct",
+	"bytedance/seed-oss-36b-instruct",
+	"deepseek-ai/deepseek-v4-flash",
+	"deepseek-ai/deepseek-v4-pro",
+	"google/gemma-2-2b-it",
+	"google/gemma-3n-e2b-it",
+	"google/gemma-3n-e4b-it",
+	"google/gemma-4-31b-it",
+	"meta/llama-3.2-1b-instruct",
+	"meta/llama-4-maverick-17b-128e-instruct",
+	"microsoft/phi-4-mini-instruct",
+	"minimaxai/minimax-m2.7",
+	"mistralai/mistral-nemotron",
+	"nvidia/nemotron-mini-4b-instruct",
+	"qwen/qwen3-next-80b-a3b-instruct",
+	"qwen/qwen3.5-122b-a10b",
+	"qwen/qwen3.5-397b-a17b",
+	"sarvamai/sarvam-m",
+	"upstage/solar-10.7b-instruct",
+]);
 const ZAI_TOOL_STREAM_UNSUPPORTED_MODELS = new Set(["glm-4.5", "glm-4.5-air", "glm-4.5-flash", "glm-4.5v"]);
 const EAGER_TOOL_INPUT_STREAMING_UNSUPPORTED_ANTHROPIC_MODELS = new Set([
 	"github-copilot:claude-haiku-4.5",
@@ -312,6 +350,30 @@ function getBedrockBaseUrl(modelId: string): string {
 		: "https://bedrock-runtime.us-east-1.amazonaws.com";
 }
 
+function normalizeNvidiaModelId(modelId: string): string {
+	return modelId.toLowerCase().replaceAll("_", ".");
+}
+
+async function fetchNvidiaNimModelIds(): Promise<Map<string, string>> {
+	try {
+		console.log("Fetching models from NVIDIA NIM API...");
+		const response = await fetch(`${NVIDIA_BASE_URL}/models`);
+		const data = (await response.json()) as { data?: NvidiaNimModelListItem[] };
+		const modelIds = new Map<string, string>();
+
+		for (const model of data.data ?? []) {
+			modelIds.set(model.id, model.id);
+			modelIds.set(normalizeNvidiaModelId(model.id), model.id);
+		}
+
+		console.log(`Fetched ${data.data?.length ?? 0} model IDs from NVIDIA NIM`);
+		return modelIds;
+	} catch (error) {
+		console.error("Failed to fetch NVIDIA NIM models:", error);
+		return new Map();
+	}
+}
+
 async function fetchOpenRouterModels(): Promise<Model<any>[]> {
 	try {
 		console.log("Fetching models from OpenRouter API...");
@@ -435,6 +497,7 @@ async function loadModelsDevData(): Promise<Model<any>[]> {
 		const data = await response.json();
 
 		const models: Model<any>[] = [];
+		const nvidiaNimModelIds = data.nvidia?.models ? await fetchNvidiaNimModelIds() : new Map<string, string>();
 
 		// Process Amazon Bedrock models
 		if (data["amazon-bedrock"]?.models) {
@@ -836,6 +899,40 @@ async function loadModelsDevData(): Promise<Model<any>[]> {
 			}
 		}
 
+		// Process NVIDIA NIM models
+		if (data.nvidia?.models) {
+			for (const [modelId, model] of Object.entries(data.nvidia.models)) {
+				const m = model as ModelsDevModel;
+				if (m.tool_call !== true) continue;
+				if (!m.modalities?.input?.includes("text")) continue;
+				if (!m.modalities?.output?.includes("text")) continue;
+
+				const liveModelId = nvidiaNimModelIds.get(modelId) ?? nvidiaNimModelIds.get(normalizeNvidiaModelId(modelId));
+				if (!liveModelId) continue;
+				if (NVIDIA_NIM_UNSUPPORTED_MODELS.has(liveModelId)) continue;
+
+				models.push({
+					id: liveModelId,
+					name: m.name || liveModelId,
+					api: "openai-completions",
+					provider: "nvidia",
+					baseUrl: NVIDIA_BASE_URL,
+					headers: { ...NVIDIA_HEADERS },
+					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: NVIDIA_OPENAI_COMPAT,
+					contextWindow: m.limit?.context || 4096,
+					maxTokens: m.limit?.output || 4096,
+				});
+			}
+		}
+
 		// Process Together AI models
 		const togetherProvider = data.together ?? data.togetherai ?? data["together-ai"];
 		if (togetherProvider?.models) {

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"

packages/ai/test/stream.test.ts

@@ -787,6 +787,30 @@ describe("Generate E2E Tests", () => {
 		});
 	});
 
+	describe.skipIf(!process.env.NVIDIA_API_KEY)("NVIDIA NIM Provider (Nemotron 3 Super via OpenAI Completions)", () => {
+		const llm = getModel("nvidia", "nvidia/nemotron-3-super-120b-a12b");
+
+		it("should complete basic text generation", { retry: 3 }, async () => {
+			await basicTextGeneration(llm);
+		});
+
+		it("should handle tool calling", { retry: 3 }, async () => {
+			await handleToolCall(llm);
+		});
+
+		it("should handle streaming", { retry: 3 }, async () => {
+			await handleStreaming(llm);
+		});
+
+		it("should handle thinking mode", { retry: 3 }, async () => {
+			await handleThinking(llm, { reasoningEffort: "high" });
+		});
+
+		it("should handle multi-turn with thinking and tools", { retry: 3 }, async () => {
+			await multiTurn(llm, { reasoningEffort: "high" });
+		});
+	});
+
 	describe.skipIf(!process.env.OPENROUTER_API_KEY)("OpenRouter Provider (glm-4.5v via OpenAI Completions)", () => {
 		const llm = getModel("openrouter", "z-ai/glm-4.5v");