AMD

Access 6 AMD models through Mastra's model router. Authentication is handled automatically using the AMD_API_KEY environment variable.

Learn more in the AMD documentation.

.env

AMD_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: "amd/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);
}

备注

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

Models

6 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
amd/DeepSeek-V4-Flash	1.0M						$0.14	$0.28
amd/DeepSeek-V4-Flash-Vision-Exp	1.0M						$0.14	$0.28
amd/DeepSeek-V4.1-Flash	1.0M						$0.14	$0.28
amd/MiniCPM5-2B	131K						$0.12	$0.74
amd/Qwen3.8-27B	131K						—	—
amd/Qwen3.8-Flash-Next	262K						$0.15	$0.47

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://developer.amd.com.cn/radeon/api/v1",
    id: "amd/DeepSeek-V4-Flash",
    apiKey: process.env.AMD_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
      ? "amd/Qwen3.8-Flash-Next"
      : "amd/DeepSeek-V4-Flash";
  }
});