Free APILLMAPI keyOfficial
Hugging Face Inference Providers
One key routes to many providers; small free monthly credit, huge model choice
Hugging Face Inference Providers is a serverless router that forwards a single OpenAI-compatible request to third-party inference backends (Cerebras, SambaNova, Together, fal, Replicate, and others) for thousands of open models. Every account gets a small monthly credit allowance applied automatically, billed at the underlying provider's rate with no markup.
Free tier
Free accounts get $0.10/month in Inference Provider credits (verified June 2026, subject to change); PRO ($9/mo) gets $2/month, Team/Enterprise $2/seat. Beyond the credit you pay the provider's pass-through rate with no markup added by Hugging Face.Rate limits
Not published as fixed RPM; effectively bounded by your monthly credit balance and the upstream provider's own limits. The free credit is small, so heavy use exhausts it quickly.Auth
API keyBase URL
https://router.huggingface.co/v1What you'd build with it
- Reach thousands of open models through one key without per-provider signups
- Quickly test a niche or new open-weights model for a Claude Skill
- Route the same code across backends to compare cost and speed
- Embeddings and specialized models for a RAG prototype
Key endpoints
- POST
/chat/completionsOpenAI-compatible chat completion routed to a chosen provider - POST
/embeddingsGenerate embeddings via a routed provider - GET
/modelsList models served through Inference Providers
Members
Members get the runnable recipe
Sign in free to copy the example request, see a sample response, and read the gotchas.
Tags
llmgatewayopenai-compatibleopen-weightsembeddings