Incident report · read from OpenAI's status page
OpenAI incident: We are seeing elevated error rates across API models
Resolved after 21 m (17 Sep 2026, 21:29–21:50 UTC), impact minor, affecting Images, Batch, Chat Completions, Audio, Fine-tuning, Realtime, Files, Embeddings, Moderations, Responses, Login and Sora.
Timeline
- identified
We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.
- monitoring
We have applied the mitigation and are monitoring the recovery.
- resolved
All impacted services have now fully recovered.
Affected components
- APIs · Images: degraded for 1 h
- APIs · Batch: degraded for 1 h
- APIs · Chat Completions: degraded for 1 h
- APIs · Audio: degraded for 1 h
- APIs · Fine-tuning: degraded for 1 h
- APIs · Realtime: degraded for 1 h
- APIs · Files: degraded for 1 h
- APIs · Embeddings: degraded for 1 h
- APIs · Moderations: degraded for 1 h
- APIs · Responses: degraded for 1 h
- APIs · Login: degraded for 1 h
- APIs · Sora: degraded for 1 h
Source
OpenAI's own report of this incident, on OpenAI's status page. This page is a record of OpenAI's own report; where the two disagree, theirs is right.
Last checked .
Must Have AI is a parody and is not affiliated with, endorsed by or connected to OpenAI, Anthropic or Google. Every outage shown here is read from the provider's own public status page.