Operational · last checked 17:31 UTC · 407 ms · checked every about 5 minutes
Uptime
24 hours
100.000%
7 days
99.86%
30 days
99.967%
90 days
91.29%
90 days agotoday
Handshake latency p50 1795 ms · p95 3623 ms · mean time to recover 108 min
Incidents (90 days)
Outage · 2026-10-13 10:30 UTC · 14 min · timeout
Outage · 2026-09-11 13:19 UTC · 5 d · rate_limit
Outage · 2026-09-10 18:57 UTC · 18.1 h · rate_limit
Outage · 2026-09-10 00:30 UTC · 18.2 h · rate_limit
Outage · 2026-09-09 18:23 UTC · 6.0 h · rate_limit
Outage · 2026-09-09 10:57 UTC · 6.1 h · rate_limit
Outage · 2026-09-08 18:23 UTC · 6.1 h · rate_limit
Outage · 2026-09-08 15:42 UTC · 7 min · redirect
Outage · 2026-09-08 01:12 UTC · 1.8 h · timeout
Outage · 2026-09-07 21:02 UTC · 1.8 h · timeout
Outage · 2026-09-07 07:45 UTC · 5 min · timeout
Outage · 2026-09-06 19:11 UTC · 12 min · timeout
Outage · 2026-09-06 15:06 UTC · 2.1 h · timeout
Outage · 2026-08-29 16:10 UTC · 6 d · parse
Outage · 2026-08-29 04:28 UTC · 1.6 h · timeout
Outage · 2026-08-28 19:41 UTC · 1.8 h · timeout
Outage · 2026-08-28 17:42 UTC · 1.6 h · timeout
Outage · 2026-08-28 14:41 UTC · 1.7 h · timeout
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.