Down since 2026-10-20 07:14 UTC · last checked 08:40 UTC · 534 ms · checked every about 5 minutes
Uptime
24 hours
7.58%
7 days
40.50%
30 days
56.95%
90 days
59.41%
90 days agotoday
Handshake latency p50 1771 ms · p95 3733 ms · mean time to recover 1564 min
Incidents (90 days)
Ongoing outage · 2026-10-20 07:14 UTC · 22.2 h so far · other
Outage · 2026-10-18 13:00 UTC · 25.4 h · other
Outage · 2026-10-16 18:07 UTC · 26.1 h · other
Outage · 2026-10-16 00:16 UTC · 10 min · timeout
Outage · 2026-10-14 16:28 UTC · 26.1 h · other
Outage · 2026-10-12 16:18 UTC · 26.1 h · other
Outage · 2026-10-10 15:59 UTC · 26.1 h · other
Outage · 2026-10-08 15:49 UTC · 26.1 h · other
Outage · 2026-10-06 16:16 UTC · 26.1 h · other
Outage · 2026-10-04 17:36 UTC · 26.1 h · other
Outage · 2026-10-02 16:43 UTC · 26.1 h · other
Outage · 2026-09-29 19:15 UTC · 26.0 h · other
Outage · 2026-09-27 21:11 UTC · 1.1 h · other
Outage · 2026-09-21 18:17 UTC · 26.4 h · other
Outage · 2026-09-20 21:54 UTC · 9 min · other
Outage · 2026-09-18 17:52 UTC · 26.3 h · other
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.