Vendors · Profile

Hugging Face Inference Endpoints

Managed self-host

Managed dedicated endpoints for deploying Hub models per instance-hour

Visit Hugging Face Inference Endpoints ↗

Deployment

Deployment models	Dedicated endpoints, Public endpoint, Protected endpoint, Private endpoint (PrivateLink)
Regions	US, Europe

Compliance

SOC 2 Type II huggingface.co ↗ verified 2026-07-07
GDPR DPA huggingface.co ↗ verified 2026-07-07

Pricing

huggingface.co ↗ verified 2026-07-07

Pricing model	Per instance-hour (CPU, GPU, and accelerator instances); dedicated inference from $0.033/hour
Public pricing	Yes

Sovereignty

huggingface.co ↗ verified 2026-07-07

Data residency guarantee	Not verified
Parent jurisdiction	US

Analyst note

Deploys Hub models on managed instances across AWS, Azure, and GCP with public, protected, or private (intra-region AWS/Azure PrivateLink) access. Vendor docs state SOC 2 Type 2 certification and a GDPR DPA via Enterprise Hub subscription, and that payloads are not stored (logs kept 30 days). Privacy policy: data may be stored in the US.