Skip to main content

Nvidia logoNvidia

Access 66 Nvidia models through Mastra's model router. Authentication is handled automatically using the NVIDIA_API_KEY environment variable.

Learn more in the Nvidia documentation.

NVIDIA_API_KEY=your-api-key
import { Agent } from "@mastra/core/agent";

const agent = new Agent({
  id: "my-agent",
  name: "My Agent",
  instructions: "You are a helpful assistant",
  model: "nvidia/black-forest-labs/flux.1-dev"
});

// Generate a response
const response = await agent.generate("Hello!");

// Stream a response
const stream = await agent.stream("Tell me a story");
for await (const chunk of stream) {
  console.log(chunk);
}
info

Mastra uses the OpenAI-compatible /chat/completions endpoint. Some provider-specific features may not be available. Check the Nvidia documentation for details.

Models
Direct link to Models

ModelContextToolsReasoningImageAudioVideoInput $/1MOutput $/1M
nvidia/black-forest-labs/flux.1-dev4K——
nvidia/deepseek-ai/deepseek-coder-6.7b-instruct128K——
nvidia/deepseek-ai/deepseek-r1128K——
nvidia/deepseek-ai/deepseek-r1-0528128K——
nvidia/deepseek-ai/deepseek-v3.1128K——
nvidia/deepseek-ai/deepseek-v3.1-terminus128K——
nvidia/google/codegemma-1.1-7b128K——
nvidia/google/codegemma-7b128K——
nvidia/google/gemma-2-27b-it128K——
nvidia/google/gemma-2-2b-it128K——
nvidia/google/gemma-3-12b-it128K——
nvidia/google/gemma-3-1b-it128K——
nvidia/google/gemma-3-27b-it131K——
nvidia/google/gemma-3n-e2b-it128K——
nvidia/google/gemma-3n-e4b-it128K——
nvidia/meta/codellama-70b128K——
nvidia/meta/llama-3.1-405b-instruct128K——
nvidia/meta/llama-3.1-70b-instruct128K——
nvidia/meta/llama-3.2-11b-vision-instruct128K——
nvidia/meta/llama-3.2-1b-instruct128K——
nvidia/meta/llama-3.3-70b-instruct128K——
nvidia/meta/llama-4-maverick-17b-128e-instruct128K——
nvidia/meta/llama-4-scout-17b-16e-instruct128K——
nvidia/meta/llama3-70b-instruct128K——
nvidia/meta/llama3-8b-instruct128K——
nvidia/microsoft/phi-3-medium-128k-instruct128K——
nvidia/microsoft/phi-3-medium-4k-instruct4K——
nvidia/microsoft/phi-3-small-128k-instruct128K——
nvidia/microsoft/phi-3-small-8k-instruct8K——
nvidia/microsoft/phi-3-vision-128k-instruct128K——
nvidia/microsoft/phi-3.5-moe-instruct128K——
nvidia/microsoft/phi-3.5-vision-instruct128K——
nvidia/microsoft/phi-4-mini-instruct131K——
nvidia/minimaxai/minimax-m2128K——
nvidia/mistralai/codestral-22b-instruct-v0.1128K——
nvidia/mistralai/devstral-2-123b-instruct-2512262K——
nvidia/mistralai/mamba-codestral-7b-v0.1128K——
nvidia/mistralai/ministral-14b-instruct-2512262K——
nvidia/mistralai/mistral-large-2-instruct128K——
nvidia/mistralai/mistral-large-3-675b-instruct-2512262K——
nvidia/mistralai/mistral-small-3.1-24b-instruct-2503128K——
nvidia/moonshotai/kimi-k2-instruct128K——
nvidia/moonshotai/kimi-k2-instruct-0905262K——
nvidia/moonshotai/kimi-k2-thinking262K——
nvidia/nvidia/cosmos-nemotron-34b131K——
nvidia/nvidia/llama-3.1-nemotron-51b-instruct128K——
nvidia/nvidia/llama-3.1-nemotron-70b-instruct128K——
nvidia/nvidia/llama-3.1-nemotron-ultra-253b-v1131K——
nvidia/nvidia/llama-3.3-nemotron-super-49b-v1128K——
nvidia/nvidia/llama-3.3-nemotron-super-49b-v1.5128K——
nvidia/nvidia/llama-embed-nemotron-8b33K——
nvidia/nvidia/llama3-chatqa-1.5-70b128K——
nvidia/nvidia/nemoretriever-ocr-v1———
nvidia/nvidia/nemotron-3-nano-30b-a3b131K——
nvidia/nvidia/nemotron-4-340b-instruct128K——
nvidia/nvidia/nvidia-nemotron-nano-9b-v2131K——
nvidia/nvidia/parakeet-tdt-0.6b-v2———
nvidia/openai/gpt-oss-120b128K——
nvidia/openai/whisper-large-v3———
nvidia/qwen/qwen2.5-coder-32b-instruct128K——
nvidia/qwen/qwen2.5-coder-7b-instruct128K——
nvidia/qwen/qwen3-235b-a22b131K——
nvidia/qwen/qwen3-coder-480b-a35b-instruct262K——
nvidia/qwen/qwen3-next-80b-a3b-instruct262K——
nvidia/qwen/qwen3-next-80b-a3b-thinking262K——
nvidia/qwen/qwq-32b128K——
66 available models

Advanced Configuration
Direct link to Advanced Configuration

Custom Headers
Direct link to Custom Headers

const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://integrate.api.nvidia.com/v1",
    id: "nvidia/black-forest-labs/flux.1-dev",
    apiKey: process.env.NVIDIA_API_KEY,
    headers: {
      "X-Custom-Header": "value"
    }
  }
});

Dynamic Model Selection
Direct link to Dynamic Model Selection

const agent = new Agent({
  id: "dynamic-agent",
  name: "Dynamic Agent",
  model: ({ requestContext }) => {
    const useAdvanced = requestContext.task === "complex";
    return useAdvanced
      ? "nvidia/qwen/qwq-32b"
      : "nvidia/black-forest-labs/flux.1-dev";
  }
});

On this page