Modal

Access 4 Modal models through Mastra's model router. Authentication is handled automatically using the MODAL_PROXY_TOKEN environment variable.

Learn more in the Modal documentation.

.env

MODAL_PROXY_TOKEN=your-api-token

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: "modal/Qwen/Qwen3.8-2.4T-A95B"
});

// 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 Modal documentation for details.

Models

4 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
modal/moonshotai/Kimi-K3	1.0M						$3	$15
modal/Qwen/Qwen3.8-2.4T-A95B	1.0M						$2	$6
modal/thinkingmachines/Inkling-NVFP4	1.0M						$1	$5
modal/zai-org/GLM-5.3-Flash	1.0M						$0.45	$2

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://inference.us-west.modal.direct/v1",
    id: "modal/Qwen/Qwen3.8-2.4T-A95B",
    apiKey: process.env.MODAL_PROXY_TOKEN,
    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
      ? "modal/zai-org/GLM-5.3-Flash"
      : "modal/Qwen/Qwen3.8-2.4T-A95B";
  }
});