HuggingFace (gateway)

Route HuggingFace Inference API calls through the Respan gateway after the HuggingFace model you want is available in your Respan model list.

Setup

Live verification with the tested gateway key returned model unavailable for the previous HuggingFace example. Use a current HuggingFace model ID from your Respan model list.

Install packages

$ pip install openai

Set environment variables

$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

Point an OpenAI-compatible client to the Respan gateway

1 import os
2 from openai import OpenAI
3 
4 client = OpenAI(
5     api_key=os.environ["RESPAN_API_KEY"],
6     base_url="https://api.respan.ai/api",
7 )
8 
9 response = client.chat.completions.create(
10     model="YOUR_HUGGINGFACE_MODEL_ID",
11     messages=[{"role": "user", "content": "Say hello in three languages."}],
12 )
13 print(response.choices[0].message.content)

Switch models

Change the model parameter to use 250+ models from different providers through the same gateway.

1 response = client.chat.completions.create(model="YOUR_HUGGINGFACE_MODEL_ID", messages=messages)
2 response = client.chat.completions.create(model="gpt-5.5", messages=messages)

See the full model list.