Gemini API status

Over the 60 days of a 90-day window up24 has measured so far, Gemini's REST API answered 99.94% of 3,003,498 checks, with a typical p95 of 596ms and a typical p50 of 256ms. Its worst day was 25 SEP 2026, at 98.67%. up24 opened 421 incidents against it in that window — uptime counts REST checks only, and an incident is as often a WebSocket feed that stalled or a socket that dropped. Is Gemini down right now? →

Latency is measured from each region separately and never averaged between them — the distance is the measurement. Uptime, incidents and the 90-day bars above are the opposite: they combine every region by quorum, so one probe box losing its route to an exchange is not recorded as that exchange going down. Quorum is a counting rule and it only holds while a majority can still see the venue; where a vantage point cannot measure this venue at all, its refusals are named below and left out of every number on the page rather than being left to a vote.

421 incidents over 60 measured days, grouped into 9 distinct faults. A component that fails the same way twice a week has one fault many times, not many faults, and a list that prints it once per firing hides the difference behind its own length.

WORST · 90D

BY FAULTranked by how often each fired · every occurrence links to its own page

Incidents are opened by up24's own state machine over its own measurements, not by Gemini's status page. One WebSocket carries every stream a venue publishes, so a dropped socket is recorded once, against the connection, rather than once per stream.