OpenAI: We are seeing elevated error rates across API models
Is it fixed? Yes.
Resolved after <1 min. First reported Sep 17, 21:50 UTC, resolved Sep 17, 21:50 UTC. The vendor posted it on its status page first.
What happened
Elevated error rates across various OpenAI API models have been resolved. All impacted services are now fully recovered.
What caused it?
Under active investigation. No report has identified a root cause yet.
No verified workaround yet
This incident was resolved upstream without a reported workaround.
Official fixTimeline
- Investigating(done)
- Workaround available(skipped)
- Resolved(done)
- Archived
Evidence
1 report · 1 StatusShow
- [1]Status First reportWe are seeing elevated error rates across API models(opens official status page in a new tab)
Status: Resolved All impacted services have now fully recovered. Affected components Batch (Operational) Moderations (Operational) Responses (Operational) Images (Operational) Chat Completions (Operational) Audio (Operational) Fine-tuning (Operational) Realtime (Operational) Files (Operational) Embeddings (Operational) Login (Operational)
by openai status
FAQ
What happened in the OpenAI outage?
Elevated error rates across various OpenAI API models have been resolved. All impacted services are now fully recovered.
What is affected by the OpenAI outage?
OpenAI.
When did the OpenAI outage start and end?
It started Sep 17, 21:50 UTC and was resolved Sep 17, 21:50 UTC, after <1 min.
How do I get alerts for OpenAI?
Subscribe to the OpenAI RSS feed for every new OpenAI incident, or connect an AI assistant to WhatBrokeToday over MCP and ask whether OpenAI is down. OpenAI feed
Where does this information come from?
WhatBrokeToday collects public status pages, developer community reports and security advisories, groups the ones about the same problem, and links every report under Evidence on this page. This one has 1 report from 1 independent source, including the vendor’s own status page.