Skip to main content
Providers

Hugging Face

Use huggingface/<model> with VoltAgent's model router.

Quick start​

import { Agent } from "@voltagent/core";

const agent = new Agent({
  name: "huggingface-agent",
  instructions: "You are a helpful assistant",
  model: "huggingface/MiniMaxAI/MiniMax-M2.1",
});

Environment variables​

  • HF_TOKEN

Provider package​

@ai-sdk/openai-compatible

This provider uses the OpenAI-compatible adapter.

Default base URL​

https://router.huggingface.co/v1

You can override the base URL by setting HUGGINGFACE_BASE_URL.

Provider docs​

Models​

Show models (14)
  • MiniMaxAI/MiniMax-M2.1
  • Qwen/Qwen3-235B-A22B-Thinking-2507
  • Qwen/Qwen3-Coder-480B-A35B-Instruct
  • Qwen/Qwen3-Embedding-4B
  • Qwen/Qwen3-Embedding-8B
  • Qwen/Qwen3-Next-80B-A3B-Instruct
  • Qwen/Qwen3-Next-80B-A3B-Thinking
  • XiaomiMiMo/MiMo-V2-Flash
  • deepseek-ai/DeepSeek-R1-0528
  • deepseek-ai/DeepSeek-V3.2
  • moonshotai/Kimi-K2-Instruct
  • moonshotai/Kimi-K2-Instruct-0905
  • moonshotai/Kimi-K2-Thinking
  • zai-org/GLM-4.7

Table of Contents