OpenReason

Access 3 OpenReason models through Mastra's model router. Authentication is handled automatically using the OPENREASON_API_KEY environment variable.

Learn more in the OpenReason documentation.

.env

OPENREASON_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: "openreason/deepseek-ai/deepseek-v4-flash-0731"
});

// 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 OpenReason documentation for details.

Models

3 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
openreason/deepseek-ai/deepseek-v4-flash-0731	1.0M						$0.14	$0.27
openreason/moonshotai/kimi-k2.7-code	262K						$1	$4
openreason/openai/gpt-oss-120b	131K						$0.11	$0.42

Advanced configuration

Custom headers

src/mastra/agents/my-agent.ts

const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://api.openreason.app/v1",
    id: "openreason/deepseek-ai/deepseek-v4-flash-0731",
    apiKey: process.env.OPENREASON_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
      ? "openreason/openai/gpt-oss-120b"
      : "openreason/deepseek-ai/deepseek-v4-flash-0731";
  }
});