OpenAI API status
OpenAI is operating normally
Updated Fri, 06 Nov 2026 07:39:06 UTC · regions: ap-south-1, eu-west-1, us-east-1
Show
Fastgpt-6-luna
952 msOperational- Mumbaiap-south-11110 ms · p95 2172 msOperational
- Irelandeu-west-1918 ms · p95 1439 msOperational
- N. Virginiaus-east-1723 ms · p95 1205 msOperational
Everydaygpt-6.1-sol
960 msOperational- Mumbaiap-south-1988 ms · p95 1964 msOperational
- Irelandeu-west-11062 ms · p95 1653 msOperational
- N. Virginiaus-east-1828 ms · p95 1194 msOperational
Frontiergpt-6-astra
1039 msOperational- Mumbaiap-south-11079 ms · p95 2241 msOperational
- Irelandeu-west-1846 ms · p95 1380 msOperational
- N. Virginiaus-east-1978 ms · p95 1373 msOperational
Recent incidents
- OpenAI: Degraded performanceResolved
Started Fri, 06 Nov 2026 00:00:00 UTC · resolved Fri, 06 Nov 2026 01:00:00 UTC
- OpenAI: Degraded performanceResolved
Started Thu, 05 Nov 2026 11:00:00 UTC · resolved Thu, 05 Nov 2026 12:00:00 UTC
Incidents are judged across all regions, whichever region is shown above.
Each point on the history bars is one hour (UTC). Latency is the time to the first byte of the response to a one-token request, measured from AWS data centres in the regions listed, not from your location. A failed probe counts against a provider only when the failure is on the provider's side; rate limits and credential problems on our own account are never shown as outages.