Nvidia

Access 20 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";

const agent = new 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

20 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
nvidia/black-forest-labs/flux.1-dev	4K						—	—
nvidia/deepseek-ai/deepseek-v3.1	128K						—	—
nvidia/deepseek-ai/deepseek-v3.1-terminus	128K						—	—
nvidia/google/gemma-3-27b-it	131K						—	—
nvidia/microsoft/phi-4-mini-instruct	131K						—	—
nvidia/minimaxai/minimax-m2	128K						—	—
nvidia/moonshotai/kimi-k2-instruct	128K						—	—
nvidia/moonshotai/kimi-k2-instruct-0905	262K						—	—
nvidia/nvidia/cosmos-nemotron-34b	131K						—	—
nvidia/nvidia/llama-3.1-nemotron-ultra-253b-v1	131K						—	—
nvidia/nvidia/llama-embed-nemotron-8b	33K						—	—
nvidia/nvidia/nemoretriever-ocr-v1	—						—	—
nvidia/nvidia/nvidia-nemotron-nano-9b-v2	131K						—	—
nvidia/nvidia/parakeet-tdt-0.6b-v2	—						—	—
nvidia/openai/gpt-oss-120b	128K						—	—
nvidia/openai/whisper-large-v3	—						—	—
nvidia/qwen/qwen3-235b-a22b	131K						—	—
nvidia/qwen/qwen3-coder-480b-a35b-instruct	262K						—	—
nvidia/qwen/qwen3-next-80b-a3b-instruct	262K						—	—
nvidia/qwen/qwen3-next-80b-a3b-thinking	262K						—	—

Advanced Configuration

Custom Headers

const agent = new 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

const agent = new Agent({
  name: "dynamic-agent",
  model: ({ runtimeContext }) => {
    const useAdvanced = runtimeContext.task === "complex";
    return useAdvanced
      ? "nvidia/qwen/qwen3-next-80b-a3b-thinking"
      : "nvidia/black-forest-labs/flux.1-dev";
  }
});