Mistral AI logo

Mistral API slowdown on 7 November 2026

Mistral API from Tokyo: slower than usual; 2026-11-07 14:00 UTC to 2026-11-07 16:00 UTC: peak first visible token 1.02 s vs a usual 484 ms.

What our checks saw
Slower than usual
Cities affected
Tokyo
When
to
How long
2 hours
Slowest check
1.02 s, usually 484 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, Singapore, Mumbai.

Tokyo

Incident0 ms1.00 s2.00 s11:0014:0017:00
Each check (UTC)Usual (485 ms)Much slower, or failingSlow check outside the incidentIncident
Every check as a table
Time (UTC)CheckReading
11:00497 msNormal
11:30906 msSlower than usual
12:00479 msNormal
12:30553 msNormal
13:001.37 sMuch slower, or failing
13:30562 msNormal
14:001.48 sMuch slower, or failing
14:30546 msNormal
15:00440 msNormal
15:30452 msNormal
16:00493 msNormal
16:30674 msNormal
17:00507 msNormal
17:30606 msNormal
18:00690 msNormal
18:30408 msNormal
19:00466 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.