OpenAI logo

OpenAI Decisions API slowdown on 25 October 2026

OpenAI Decisions API full response from Mumbai, Montreal: slower than usual; 2026-10-25 21:30 UTC onwards: peak full response 531 ms vs a usual 344 ms.

What our checks saw
Slower than usual
Cities affected
Mumbai, Montreal
When
, still ongoing at our last check
How long
about an hour so far
Slowest check
531 ms, usually 344 ms
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.

Montreal

Incident0 ms250 ms500 ms18:3021:30
Each check (UTC)Usual (167 ms)Slower than usualSlow check outside the incidentIncident
Every check as a table
Time (UTC)CheckReading
18:30200 msNormal
19:00166 msNormal
19:30186 msNormal
20:00209 msNormal
20:30372 msSlower than usual
21:00209 msNormal
21:30372 msSlower than usual
22:00241 msNormal
22:30161 msNormal

Mumbai

Incident0 ms750 ms1.50 s18:3021:30
Each check (UTC)Usual (344 ms)Slow check outside the incidentIncident
Every check as a table
Time (UTC)CheckReading
18:30125 msNormal
19:00306 msNormal
19:30111 msNormal
20:00778 msSlower than usual
20:30928 msMuch slower, or failing
21:00943 msMuch slower, or failing
21:30118 msNormal
22:00119 msNormal
22:30122 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.