Skip to main content

Hugging Face API key setup

Inference Endpoints from Hugging Face. Managed deployment for open models.

Get your key

  1. Open the Hugging Face API keys page: huggingface.co/settings/tokens
  2. Create an account and generate an API key.
  3. Paste it into the Dracon BYOK provider keys — stored encrypted (AES-256-GCM), used browser-direct, works in every Dracon tool.

Free tier

Yes. Free inference providers via HF Hub; small monthly credit allotment no credit card required

Rate limits: ~$0.10/month free credits

Connection details

Base URL
https://router.huggingface.co/v1
API shape
OpenAI-compatible
Env var
HUGGINGFACE_API_KEY
Models
meta-llama/Llama-3.3-70B-Instruct
Model lineup
Llama 3.3 70B, Qwen 2.5 72B, Gemma 2 9B, Mistral 7B, FLUX.1

Our verdicts on this kind of provider

Independent comparisons we keep current as pricing and free tiers shift. A guide is setup; a verdict is whether it's worth setting up.

Add your Hugging Face key Add this provider to a fallback list Compare free tiers