Skip to main content

Hugging Face logoHugging Face

Access 14 Hugging Face models through Mastra's model router. Authentication is handled automatically using the HF_TOKEN environment variable.

Learn more in the Hugging Face documentation.

HF_TOKEN=your-api-key
import { Agent } from "@mastra/core";

const agent = new Agent({
name: "my-agent",
instructions: "You are a helpful assistant",
model: "huggingface/MiniMaxAI/MiniMax-M2"
});

// 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 Hugging Face documentation for details.

Models

ModelImageAudioVideoToolsStreamingContext Window
huggingface/deepseek-ai/DeepSeek-R1-0528163,840
huggingface/deepseek-ai/Deepseek-V3-032416,384
huggingface/MiniMaxAI/MiniMax-M2204,800
huggingface/moonshotai/Kimi-K2-Instruct131,072
huggingface/moonshotai/Kimi-K2-Instruct-0905262,144
huggingface/Qwen/Qwen3-235B-A22B-Thinking-2507262,144
huggingface/Qwen/Qwen3-Coder-480B-A35B-Instruct262,144
huggingface/Qwen/Qwen3-Embedding-4B32,000
huggingface/Qwen/Qwen3-Embedding-8B32,000
huggingface/Qwen/Qwen3-Next-80B-A3B-Instruct262,144
huggingface/Qwen/Qwen3-Next-80B-A3B-Thinking262,144
huggingface/zai-org/GLM-4.5131,072
huggingface/zai-org/GLM-4.5-Air128,000
huggingface/zai-org/GLM-4.6200,000

Advanced Configuration

Custom Headers

const agent = new Agent({
name: "custom-agent",
model: {
url: "https://router.huggingface.co/v1",
id: "huggingface/MiniMaxAI/MiniMax-M2",
apiKey: process.env.HF_TOKEN,
headers: {
"X-Custom-Header": "value"
}
}
});

Dynamic Model Selection

const agent = new Agent({
name: "dynamic-agent",
model: ({ runtimeContext }) => {
const useAdvanced = runtimeContext.task === "complex";
return useAdvanced
? "huggingface/zai-org/GLM-4.6"
: "huggingface/MiniMaxAI/MiniMax-M2";
}
});

On this page