OpenAI incident: Elevated latency for some API requests

1. resolvedSep 30, 2026, 20:35 UTC

   All impacted services have now fully recovered.

2. monitoringSep 30, 2026, 18:21 UTC

   We have applied the mitigation and are monitoring the recovery.

3. identifiedSep 30, 2026, 17:51 UTC

   We have implemented an initial mitigation and are seeing improvements in API latency. We are continuing to investigate the scope of the issue and apply additional mitigations as needed. Some requests to the Responses and Chat Completions APIs may still experience elevated latency or timeouts.

4. identifiedSep 30, 2026, 17:13 UTC

   We have identified that users are experiencing elevated latency for the impacted services. We are working on implementing a mitigation.

5. identifiedSep 30, 2026, 17:05 UTC

   We have identified that users are experiencing elevated latency for the impacted services. We are working on implementing a mitigation.

What APIStatus.watch saw

Our 5-minute checks didn't record a change in OpenAI's overall status around this incident. Smaller or regional incidents often leave a provider's overall status green.

Other services with incidents at the same time

Overlapping incidents aren't necessarily related.

• Akamai: Origin Server Connectivity Issues with Elevated Errors in APAC RegionMinor · Sep 22, 2026, 14:28 UTC
• Cloudflare: Cloudflare One Clients are incorrectly challenged on some sitesMinor · Sep 22, 2026, 19:23 UTC
• Zoom: Service Degradation Affecting Customer Using Polycom Devices Going OfflineMinor · Sep 25, 2026, 17:45 UTC
• Twilio: MMS Delivery Delays from a Subset of Twilio Long Codes to GCI United StatesMinor · Sep 26, 2026, 03:16 UTC
• Snyk: Snyk CLI Scans DegradedMinor · Sep 28, 2026, 14:26 UTC
• Clerk: Development instances only - Apple rejecting emailsMinor · Sep 28, 2026, 15:23 UTC
• Supabase: Intermittent latency in Eastern USMinor · Sep 29, 2026, 16:26 UTC
• Twilio: SMS Delivery Delays and Failures from Twilio to Metfone, Viettel, Beeline, and Sotelco CambodiaMinor · Sep 30, 2026, 07:18 UTC
• Cloudflare: Network Performance Issues in MadridMinor · Sep 30, 2026, 10:31 UTC
• Cloudflare: Membership Permission Change DelaysMinor · Sep 30, 2026, 13:36 UTC

How often does OpenAI have incidents?

OpenAI reported 18 incidents in the last 90 days, 4 of them major or critical. A typical incident lasted 52 min. See OpenAI's uptime and incident history