ChatGPT API slowdown on 6 October 2026
ChatGPT API from Montreal: slower than usual; 2026-10-06 08:30 UTC to 2026-10-06 10:00 UTC: peak first visible token 1.84 s vs a usual 1.12 s.
- What our checks saw
- Slower than usual
- Cities affected
- Montreal
- When
- to
- How long
- 90 minutes
- Slowest check
- 1.84 s, usually 1.12 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, San Francisco, Singapore, Tokyo, Mumbai.
Montreal
Every check as a table
| Time (UTC) | Check | Reading |
|---|---|---|
| 05:30 | 1.29 s | Normal |
| 06:00 | 1.36 s | Normal |
| 06:30 | – | No check |
| 07:00 | 2.40 s | No check |
| 07:30 | 1.03 s | Normal |
| 08:00 | 2.64 s | Slower than usual |
| 08:30 | 1.03 s | Normal |
| 09:00 | 875 ms | Normal |
| 09:30 | 1.26 s | Normal |
| 10:00 | 1.27 s | Normal |
| 10:30 | 904 ms | Normal |
| 11:00 | 1.09 s | Normal |
| 11:30 | 954 ms | Normal |
| 12:00 | 1.23 s | Normal |
| 12:30 | 1.20 s | Normal |
| 13:00 | 1.72 s | Slower than usual |
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.