- Level
- confirmed
- Worst impact
- Degraded
- Down Index
- 15of 100
What to do
Check whether your product depends on OpenAI. Check your stack
Paste a package.json, lockfile, Terraform or a list of domains at down.guide/stack to see every provider you depend on.Confirm your retries, queues and scheduled jobs caught up after the 19m it lasted.
Anything that failed between 2026-09-14 23:20 UTC and 2026-09-14 23:39 UTC may need a replay.Subscribe to OpenAI's feed to hear about the next one first. RSS feed
https://down.guide/feed?provider=openai works in Slack (/feed subscribe), Discord feed bots and any RSS reader.
Updates from OpenAI 3
- monitoring
Since 1:30 PM Pacific Time on September 14, customers using the Agents API have experienced delays or been unable to start turns in managed sessions.
provider
- monitoring
We have applied mitigations and are seeing recovery, but the service has not fully recovered. We are continuing to monitor recovery.
provider
- resolved
The issue affecting the Agents API has been resolved. Managed sessions are now processing turns normally.
provider
Reports count in aggregate; nothing about you is shown.
Corrections
None so far.
Something wrong on this page? Report an error or send us a note. Every fix is listed here.
Questions about DWN-0f0e09a22c
Is OpenAI still down?
No, this incident was resolved 2026-09-14 23:39 UTC. For OpenAI's live state, see https://down.guide/openai.
How long did it last?
19m, from 2026-09-14 23:20 UTC to 2026-09-14 23:39 UTC, by the times OpenAI posted.
What caused it?
OpenAI hasn't published a root cause. If it does, it shows here.
Where does this come from?
OpenAI's official status page, https://status.openai.com, quoted verbatim. down.guide's own probes, reports and social counts are labeled as ours.