Hugging Face Inference Providers

The router at router.huggingface.co/v1 picks a provider for the model (or append :provider).

LLM_CHAIN=huggingface,anthropic   # failover to a second endpoint is one more name
LLM_HUGGINGFACE_API_KEY=hf_…
LLM_HUGGINGFACE_MODEL=meta-llama/Llama-3.3-70B-Instruct

Every endpoint takes the same knobs: LLM_<NAME>_TEMPERATURE (none omits it), LLM_<NAME>_BODY (JSON merged into every request), LLM_<NAME>_PRICE (input,cached,output per million, for the cost ledger), LLM_<NAME>_NOTES (a per-model notes file). Two models of one provider: LLM_FAST_PRESET=huggingface under another name. Environment has the full list.

Check it: npm run gateway, then curl localhost:8787/api/health — the llm.chain entry shows the endpoint, whether its key is set, and its state.

Provider docs: https://huggingface.co/docs/inference-providers

---

Source: docs/providers/huggingface.md — edit it there; the site mirrors the repository.