Skip to content
SPECIFICTION
Get listed

Hugging Face Inference Endpoints

endpoints.huggingface.co

From $0.06/mo WebAPI
Visit endpoints.huggingface.co
Spec score 7.3 #7 of 25 in Model Hosting

Spec sheet

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

Plans and prices

Self-Serve $0.06 a month Monthly; compute is priced by the minute, with listed instance rates shown per hour. 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 Custom annual contracts; contact Hugging Face for a quote. Volume-based lower marginal costs · Uptime guarantees · Dedicated support and SLAs Read 2 Oct 2026 · endpoints.huggingface.co

Every Hugging Face Inference Endpoints plan and price →

Where Specifiction places it

Alternatives to Hugging Face Inference EndpointsAll alternatives →