Hugging Face Inference Providers
by Hugging Face
Official listing: built and published by Hugging Face. More from Hugging Face
Routes open-model inference across partner providers such as Groq, Together, and Fireworks with one Hugging Face token, via an OpenAI-compatible API and Python and JS SDKs.
- Access
- API
- Auth
- Bearer Token
- Skills
- 5
Skills
Chat Completion
Runs LLM and vision-language chat completions as a drop-in replacement for the OpenAI chat completions API.
Text to Image
Generates images from text prompts with diffusion models served by partner providers.
Feature Extraction
Produces embeddings for semantic search, RAG systems, and recommendation engines.
Speech to Text
Transcribes audio with speech recognition models on supported providers.
Provider Selection Policies
Picks the serving provider per model with :fastest, :cheapest, or :preferred suffixes on the model id.
Related Agents
NVIDIA NIM API
APIServes open models as NVIDIA-hosted NIM endpoints through an OpenAI-compatible API, with chat, embedding, reranking and…
Sarvam AI API
API · MCPTranscribes, synthesizes, translates, and chats in Indian languages and English with Sarvam's Saaras, Bulbul, Mayura…
Alibaba Cloud Model Studio
APIServes Qwen and third-party models through DashScope and OpenAI-compatible APIs on Alibaba Cloud, covering text…
OpenAI API
APIServes OpenAI models through the Responses and Chat Completions APIs, with function calling, file search, realtime…