Inference service · Managed inference host
Hugging Face Inference Endpoints
Hugging Face's managed dedicated and autoscaling deployment service for models and custom handlers sourced from Hub repositories.
- Operator
- Hugging Face
- Delivery
- Dedicated endpoint · Reserved capacity
- Model sources
- Open-weight models · Customer-supplied models
- API styles
- Service-native · OpenAI-compatible
- Boundary
- Represents customer-created Inference Endpoints, not Inference Providers routing, the Hub repository alone, Spaces, or self-hosted inference engines.
Open in the directory → Open official service documentation ↗
Editorial ratings appear in the directory beside the profile they belong to and are never compared across collections.