OpenAI logo

ChatGPT API slowdown on 30 September 2026

ChatGPT API from San Francisco: slower than usual; 2026-09-30 07:30 UTC to 2026-09-30 09:30 UTC: peak first visible token 1.93 s vs a usual 1.09 s.

What our checks saw
Slower than usual
Cities affected
San Francisco
When
to
How long
2 hours
Slowest check
1.93 s, usually 1.09 s
OpenAI'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, Montreal, Singapore, Tokyo, Mumbai.

San Francisco

Incident0 ms1.25 s2.50 s04:3007:3010:30
Each check (UTC)Usual (1.09 s)Slower than usualSlow check outside the incidentIncident
Every check as a table
Time (UTC)CheckReading
04:301.32 sNormal
05:001.35 sNormal
05:301.41 sNormal
06:001.70 sSlower than usual
06:301.70 sSlower than usual
07:001.82 sSlower than usual
07:302.03 sSlower than usual
08:001.39 sNormal
08:301.23 sNormal
09:001.55 sNormal
09:301.00 sNormal
10:001.33 sNormal
10:301.06 sNormal
11:001.34 sNormal
11:30937 msNormal
12:001.02 sNormal
12:301.34 sNormal

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.