Friendli

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

Learn more in the Friendli documentation.

.env

FRIENDLI_TOKEN=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: "friendli/MiniMaxAI/MiniMax-M2.1"
});

// 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);
}

info

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

Models

7 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
friendli/meta-llama/Llama-3.1-8B-Instruct	131K						$0.10	$0.10
friendli/meta-llama/Llama-3.3-70B-Instruct	131K						$0.60	$0.60
friendli/MiniMaxAI/MiniMax-M2.1	197K						$0.30	$1
friendli/MiniMaxAI/MiniMax-M2.5	197K						$0.30	$1
friendli/Qwen/Qwen3-235B-A22B-Instruct-2507	262K						$0.20	$0.80
friendli/zai-org/GLM-4.7	203K						—	—
friendli/zai-org/GLM-5	203K						$1	$3

Advanced configuration

Custom headers

src/mastra/agents/my-agent.ts

const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://api.friendli.ai/serverless/v1",
    id: "friendli/MiniMaxAI/MiniMax-M2.1",
    apiKey: process.env.FRIENDLI_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
      ? "friendli/zai-org/GLM-5"
      : "friendli/MiniMaxAI/MiniMax-M2.1";
  }
});