Mistral AI logo

Mistral API slowdown on 9 November 2026

Mistral API from Amsterdam: slower than usual; 2026-11-09 20:00 UTC to 2026-11-09 22:00 UTC: peak first visible token 627 ms vs a usual 293 ms.

What our checks saw
Slower than usual
Cities affected
Amsterdam
When
to
How long
2 hours
Slowest check
627 ms, usually 293 ms
Mistral AI's status page
Open it

Where our checks saw it

Each glowing city had slow or failing checks during the incident, shown at its worst. We test from 6 cities, so other places may have been hit too.

Our checks, city by city

Each point is one check every 30 minutes, from three hours before the incident to three hours after. Coloured points are the checks we counted as slower or failing. The shaded area shows how far above the usual time they were. Not affected: San Francisco, Montreal, Singapore, Tokyo, Mumbai.

Amsterdam

Incident0 ms750 ms1.50 s17:0020:0023:00
Each check (UTC)Usual (293 ms)Slower than usualSlow check outside the incidentIncident
Every check as a table
Time (UTC)CheckReading
17:00413 msNormal
17:30308 msNormal
18:00371 msNormal
18:30329 msNormal
19:00945 msMuch slower, or failing
19:30548 msSlower than usual
20:00705 msSlower than usual
20:30535 msSlower than usual
21:00266 msNormal
21:30483 msSlower than usual
22:00248 msNormal
22:30264 msNormal
23:00324 msNormal
23:30409 msNormal
00:00291 msNormal
00:30356 msNormal
01:00283 msNormal

How fast is your API around the world?

Run a free speed test from multiple cities and find out where your users are waiting. No setup, no account required.

Test my API

No account required · Takes about 30 seconds.