{"host":"router.huggingface.co","name":"Hugging Face Inference Providers","probe_path":"/v1/models","expected_status":[200,401,403],"note":"public listing","vantage":"werk-nl","days":30,"last_probe":"2026-11-19T02:30:01+00:00","daily":[{"day":"2026-11-18","samples":277,"up":277,"degraded":0,"down":0,"unexpected":0,"probe_fault":0,"uptime_pct":100.0,"p50_ms":871.2,"p95_ms":1283.7},{"day":"2026-11-19","samples":31,"up":31,"degraded":0,"down":0,"unexpected":0,"probe_fault":0,"uptime_pct":100.0,"p50_ms":836.3,"p95_ms":1386.3}],"incidents":[],"limits":"What this proves: from this vantage (one IPv4 network, one location) the provider's DNS, TCP, TLS and edge or gateway answered, and how fast. What it does NOT prove: that a model generates, that your key, quota or region works, that other regions or IP ranges are up, or that a failure we saw is global. A provider can be fully up for this probe while inference is failing, and the reverse. Treat a down window as 'unreachable from here', and use several sources (and the provider's own status page) for a claim.","incident_definition":"2 or more consecutive down windows","license":"CC BY 4.0","query":{"host":"router.huggingface.co","days":30,"vantage":null},"as_of":"2026-11-19T02:31:16+00:00"}