About Hugging Face Inference
Hugging Face Inference (Inference API and Inference Endpoints) provides hosted inference for models from the Hugging Face Hub, plus dedicated endpoints, Inference Providers integrations, and SDKs to run language, vision, and multimodal models.
Key Features
- Serverless Inference API to call thousands of Hub models with SDKs and HTTP endpoints.
- Dedicated Inference Endpoints (managed deployments) and Inference Providers partnerships.
- Support for embeddings, text generation, vision, and provider-backed infrastructure choices.
Use Cases & Best For
Developers who want hosted access to models from the Hugging Face Hub with easy SDKs.
Teams requiring dedicated managed endpoints or multi-provider inference via Hugging Face integrations.
About LLM Development
Tools for building with large language models