Down since 2026-10-21 03:39 UTC · last checked 05:15 UTC · 406 ms · checked every about 5 minutes
Uptime
24 hours
71.59%
7 days
81.94%
30 days
74.35%
90 days
74.71%
90 days agotoday
Handshake latency p50 2453 ms · p95 4312 ms · mean time to recover 13 min
Incidents (90 days)
Ongoing outage · 2026-10-21 03:39 UTC · 4.7 h so far · http_4xx
Outage · 2026-10-19 08:51 UTC · 25.6 h · http_4xx
Outage · 2026-10-12 16:51 UTC · 8 min · timeout
Outage · 2026-10-12 07:46 UTC · 8 min · http_5xx
Outage · 2026-10-10 03:41 UTC · 26.3 h · http_4xx
Outage · 2026-10-09 09:14 UTC · 7 min · http_4xx
Outage · 2026-10-07 21:47 UTC · 13 min · http_4xx
Outage · 2026-10-06 11:31 UTC · 26.2 h · http_4xx
Outage · 2026-10-06 05:33 UTC · 17 min · http_5xx
Outage · 2026-10-02 18:06 UTC · 3 d · http_4xx
Outage · 2026-09-27 03:53 UTC · 26.6 h · http_4xx
Outage · 2026-09-26 16:00 UTC · 10 min · http_4xx
Outage · 2026-09-25 19:26 UTC · 7 min · http_4xx
Outage · 2026-09-24 05:01 UTC · 14 min · http_4xx
Outage · 2026-09-22 10:37 UTC · 6 min · http_4xx
Outage · 2026-09-21 01:53 UTC · 10 min · http_5xx
How this is measured
Checked by Glimind's probe (initialize + tools/list, never a tool call) from one region. Uptime counts a server as up when it completes the handshake, including when it asks for credentials. An outage starts at the first failed check, so short blips between checks are not seen. Every server is measured the same way; an owner's plan never changes these numbers. Owner updates are the owner's own words and sit next to the measurements, not in place of them.