Tinfoil

Access 8 Tinfoil models through Mastra's model router. Authentication is handled automatically using the TINFOIL_API_KEY environment variable.

Learn more in the Tinfoil documentation.

.env

TINFOIL_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: "tinfoil/deepseek-v4-1-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 Tinfoil documentation for details.

Models

8 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
tinfoil/deepseek-v4-1-flash	1.0M						$0.65	$1
tinfoil/gemma4-31b	262K						$0.40	$1
tinfoil/glm-5-3	1.0M						$2	$6
tinfoil/gpt-oss-120b	131K						$0.15	$0.60
tinfoil/gpt-oss-safeguard-120b	131K						$0.15	$0.60
tinfoil/kimi-k3	262K						$4	$20
tinfoil/llama3-3-70b	131K						$2	$3
tinfoil/nomic-embed-text	8K						$0.05	—

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.tinfoil.sh/v1",
    id: "tinfoil/deepseek-v4-1-flash",
    apiKey: process.env.TINFOIL_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
      ? "tinfoil/nomic-embed-text"
      : "tinfoil/deepseek-v4-1-flash";
  }
});