NaN

Access 7 NaN models through Mastra's model router. Authentication is handled automatically using the NAN_API_KEY environment variable.

Learn more in the NaN documentation.

.env

NAN_API_KEY=your-api-key

src/mastra/agents/my-agent.ts

import { Agent } from "@mastra/core/agent";

const agent = new Agent({
  id: "my-agent",
  name: "My Agent",
  instructions: "You are a helpful assistant",
  model: "nan/deepseek-v4-flash"
});

// 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);
}

note

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

Models

7 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
nan/deepseek-v4-flash	1.0M						—	—
nan/gemma4	262K						—	—
nan/glm5.3	1.0M						—	—
nan/glm5.3-flash	1.0M						—	—
nan/mimo-v2.5	1.0M						—	—
nan/qwen3.6	262K						—	—
nan/qwen3.8-flash	262K						—	—

Model availability, capabilities, context windows, and pricing are sourced from models.dev and may change.

Advanced configuration

Custom headers

src/mastra/agents/my-agent.ts

const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://api.nan.builders/v1",
    id: "nan/deepseek-v4-flash",
    apiKey: process.env.NAN_API_KEY,
    headers: {
      "X-Custom-Header": "value"
    }
  }
});

Dynamic model selection

src/mastra/agents/my-agent.ts

const agent = new Agent({
  id: "dynamic-agent",
  name: "Dynamic Agent",
  model: ({ requestContext }) => {
    const useAdvanced = requestContext.task === "complex";
    return useAdvanced
      ? "nan/qwen3.8-flash"
      : "nan/deepseek-v4-flash";
  }
});