Skip to main content
mistral.health
Hugging Face

Is Hugging Face down? Live hub & inference status

The open ML hub · models, datasets, Spaces

Live Hugging Face status — the model hub, Inference API and Spaces checked from your browser against huggingface.co.

HuggingFace API Status

Live, in-browser checks against HuggingFace's public APIs. Refreshes every 15s.

Checking…

Hub & Inference

Reachability of huggingface.co & inference endpoints

3 endpoints
  • Hub
    huggingface.co root
    —ms
    warming up
  • Hub API
    huggingface.co/api/models
    —ms
    warming up
  • Inference API
    api-inference.huggingface.co
    —ms
    warming up
Polling every 15s · Last updated — · Next in 15sOpen HuggingFace ↗

These checks confirm DNS, TCP and TLS reachability. Spaces cold-starts and per-model inference queues are not visible from the browser — see the official status page.

Sponsored · Hugging Face
Ask Hugo
Hub · Inference

I'm Hugo — your Hugging Face guide. Ask about the Hub, Inference API, Endpoints, or Spaces.

Visit Hugging Face

Sponsored content. mistral.health may earn a referral reward when you sign up via this widget. Answers are informational only.

Official HuggingFace status page

Open ↗

About HuggingFace

Hugging Face is the de-facto model and dataset hub for open ML, plus a Serverless Inference API, Inference Endpoints (dedicated), and Spaces (hosted app runtime). It's the connective tissue between open weights and running code.

HuggingFace at a glance

Founded
2016
HQ
New York / Paris
Products
Hub, Inference API, Endpoints, Spaces
Open models
1M+ on the hub

Frequently asked

Is Hugging Face down?
We probe huggingface.co and the inference edges from your browser. Green means the edges respond; individual models can still queue or cold-start.
What's the difference between Inference API and Endpoints?
Serverless Inference API is a shared, rate-limited surface. Inference Endpoints are dedicated GPU/CPU instances you provision — no cold-start after warmup, priced per hour.

About this check

All data is provided on a best-effort basis with no guarantees about accuracy or availability. This is an unofficial status page and is not affiliated with, endorsed by, or sponsored by HuggingFace.

Checks run client-side from your browser against HuggingFace's public endpoints. Latency reflects your network path, not the server's health alone. See our resources for more on how to read these checks.

Related on mistral.health