Hugging Face Inference Endpoints
endpoints.huggingface.co
- Web
- API
6.5 Club score Visit endpoints.huggingface.co
Plans
Every plan and priceEnterprise
—
Self-Serve
$0.06/mo
What the maker publishes
- Access requirement
- Access to the Inference Endpoints web application requires a valid payment method on the Hugging Face account or organization. source
- API access
- Endpoints can be called through the UI, cURL, the Hugging Face inference libraries, or another REST client. source
- Autoscaling
- Users can configure minimum and maximum replicas and enable scale-to-zero when inactive. source
- Cloud providers
- The configuration guide lists AWS, Microsoft Azure, and Google Cloud Platform as hosting providers. source
- Compliance
- Hugging Face states that the Hub and Inference Endpoints are SOC 2 Type 2 certified. source
- Hub integration
- Endpoints use model weights and artifacts from Hugging Face Hub repositories. source
- Inference engines
- Native engine support includes vLLM, Text Generation Inference (TGI), SGLang, llama.cpp, and Text Embeddings Inference (TEI), with custom containers also supported. source
- Monitoring
- The web application provides endpoint logs and a metrics dashboard for monitoring deployments. source
- Notable limits
- Available instance types may require a quota request, and paused endpoints do not count against used quota while scale-to-zero endpoints do. source
- Private networking
- Private Endpoints are accessible only through an intra-region AWS or Azure PrivateLink connection and are not internet-accessible. source
- Purpose
- Inference Endpoints is a managed service for deploying AI models to production on infrastructure Hugging Face manages. source
- Security
- Hugging Face says endpoint payloads and tokens are not stored, logs are retained for 30 days, and traffic is encrypted in transit with TLS/SSL. source
- Support
- The product page lists email support for Self-Serve and dedicated support and SLAs for Enterprise. source
Checked against the maker's pages on 2 Oct 2026.