- Home
- Model Hosting
- Hugging Face Inference Endpoints
On the recordRead 2 Oct 202613 facts
Hugging Face Inference Endpoints
Plans and prices
Self-Serve
$0.06usage-based
Pay as you use · Starting at $0.06/hour on product page · Email support
Read 2 Oct 2026 · endpoints.huggingface.co
Enterprise
Priced on request
Volume-based lower marginal costs · Uptime guarantees · Dedicated support and SLAs
Read 2 Oct 2026 · endpoints.huggingface.co
On the record
- Access requirement
- Access to the Inference Endpoints web application requires a valid payment method on the Hugging Face account or organization.huggingface.co · read 2 Oct 2026
- API access
- Endpoints can be called through the UI, cURL, the Hugging Face inference libraries, or another REST client.huggingface.co · read 2 Oct 2026
- Autoscaling
- Users can configure minimum and maximum replicas and enable scale-to-zero when inactive.huggingface.co · read 2 Oct 2026
- Cloud providers
- The configuration guide lists AWS, Microsoft Azure, and Google Cloud Platform as hosting providers.huggingface.co · read 2 Oct 2026
- Compliance
- Hugging Face states that the Hub and Inference Endpoints are SOC 2 Type 2 certified.huggingface.co · read 2 Oct 2026
- Hub integration
- Endpoints use model weights and artifacts from Hugging Face Hub repositories.huggingface.co · read 2 Oct 2026
- Inference engines
- Native engine support includes vLLM, Text Generation Inference (TGI), SGLang, llama.cpp, and Text Embeddings Inference (TEI), with custom containers also supported.huggingface.co · read 2 Oct 2026
- Monitoring
- The web application provides endpoint logs and a metrics dashboard for monitoring deployments.huggingface.co · read 2 Oct 2026
- 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.huggingface.co · read 2 Oct 2026
- Private networking
- Private Endpoints are accessible only through an intra-region AWS or Azure PrivateLink connection and are not internet-accessible.huggingface.co · read 2 Oct 2026
- Purpose
- Inference Endpoints is a managed service for deploying AI models to production on infrastructure Hugging Face manages.huggingface.co · read 2 Oct 2026
- 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.huggingface.co · read 2 Oct 2026
- Support
- The product page lists email support for Self-Serve and dedicated support and SLAs for Enterprise.endpoints.huggingface.co · read 2 Oct 2026
