Mistral AI logo

Mistral API slowdown on 4 November 2026

Mistral API from Singapore: slower than usual; 2026-11-04 00:00 UTC to 2026-11-04 02:30 UTC: peak first visible token 945 ms vs a usual 450 ms.

What our checks saw
Slower than usual
Cities affected
Singapore
When
to
How long
2.5 hours
Slowest check
945 ms, usually 450 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: Amsterdam, San Francisco, Montreal, Tokyo, Mumbai.

Singapore

Incident0 ms1.00 s2.00 s21:0000:0003:00
Each check (UTC)Usual (450 ms)Much slower, or failingSlow check outside the incidentIncident
Every check as a table
Time (UTC)CheckReading
21:00922 msSlower than usual
21:30429 msNormal
22:00632 msNormal
22:30575 msNormal
23:001.06 sSlower than usual
23:301.11 sSlower than usual
00:00355 msNormal
00:301.46 sMuch slower, or failing
01:00433 msNormal
01:30403 msNormal
02:00380 msNormal
02:30410 msNormal
03:00476 msNormal
03:30428 msNormal
04:00450 msNormal
04:30413 msNormal
05:00426 msNormal
05:30405 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.