# `HuggingfaceClient.Provider.HfInference`
[🔗](https://github.com/huggingface/huggingface_client/blob/v0.1.0/lib/huggingface_client/provider/hf_inference.ex#L1)

Provider implementation for HuggingFace's own inference router / API.

Routes through `https://router.huggingface.co` when using an HF token,
or directly to `https://api-inference.huggingface.co` for certain tasks.

Handles response normalisation for all 20+ HF inference tasks.

---

*Consult [api-reference.md](api-reference.md) for complete listing*