Hugging Face

Overview

Hugging Face hosts one of the largest open-source AI model hubs, and its Inference API exposes hosted models for text generation, embeddings, image, audio, and more. Yunxin routes requests to Hugging Face Inference behind a single OpenAI-compatible endpoint.

Official Website: https://huggingface.co Documentation: https://huggingface.co/docs/inference-providers

Key features

• Huge model hub — Access to a large catalog of community- and lab-published models
• Serverless inference — No infrastructure to manage
• Multiple modalities — Chat, embeddings, image generation, and TTS/STT depending on the model
• Vision & tools — Some models support image input and function calling
• Open ecosystem — Models from leading AI labs and the wider community

Using Hugging Face with Yunxin

Address Hugging Face models with the huggingface/<model> prefix in the model field. You use the same Yunxin base URL (https://api.yuhuanstudio.com/v1) and your sk- API key — there is no separate Hugging Face configuration on your side.

Capabilities vary by model. Query GET /v1/models to discover which models are available and what each one supports.

Usage example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["YUNXIN_API_KEY"],
    base_url="https://api.yuhuanstudio.com/v1"
)

response = client.chat.completions.create(
    model="huggingface/model-id",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ]
)

print(response.choices[0].message.content)

Available models

Query the Models API for the current list and per-model capabilities:

curl "https://api.yuhuanstudio.com/v1/models?provider=huggingface" \
  -H "Authorization: Bearer $YUNXIN_API_KEY"

Official resources

• Hugging Face
• Model Hub
• Inference Providers Documentation