Upfirst Status - Incident history

We’re seeing elevated latency, timeouts, and interrupted streaming across gpt 5.1 mini model and gpt 4.1 mini

2026-07-27T18:06:39.536+00:00

Type: Incident

Duration: 6 days, 21 hours and 39 minutes

Affected Components: OpenAI → Chat Completions API

Jul 27, 20:52:18 GMT+0
Resolved - All impacted services have now fully recovered..

Elevated error rates

2026-07-25T11:35:24.966+00:00

Type: Incident

Duration: 21 hours and 37 minutes

Affected Components: OpenAI → Chat Completions API, OpenAI → Realtime API

Jul 25, 11:46:39 GMT+0
Monitoring - We have applied the mitigation and are monitoring the recovery..

Jul 25, 11:57:02 GMT+0
Resolved - All impacted services have now fully recovered..

Elevated error rates

2026-07-25T09:17:49.024+00:00

Type: Incident

Duration: 4 days, 14 hours and 47 minutes

Affected Components: OpenAI → Chat Completions API, OpenAI → Realtime API

Jul 25, 10:02:52 GMT+0
Monitoring - We have applied the mitigation and are monitoring the recovery..

Jul 25, 11:08:36 GMT+0
Resolved - All impacted services have now fully recovered..

Elevated Error Rates

2026-07-23T15:36:02.973+00:00

Type: Incident

Duration: 10 days, 21 hours and 19 minutes

Affected Components: OpenAI → Chat Completions API, OpenAI → Realtime API

Jul 23, 17:36:32 GMT+0
Identified - We are continuing to work on implementing a mitigation..

Jul 23, 17:53:36 GMT+0
Identified - We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation..

Jul 23, 17:58:26 GMT+0
Identified - We are continuing to work on implementing a mitigation..

Jul 23, 18:50:34 GMT+0
Monitoring - We have applied the mitigation and are monitoring the recovery..

Jul 23, 19:37:21 GMT+0
Investigating - We are investigating the issue for the listed services..

Jul 24, 10:06:05 GMT+0
Investigating - We are investigating the issue for the listed services..

Jul 23, 20:22:48 GMT+0
Monitoring - We have applied the mitigation and are monitoring the recovery..

Jul 24, 19:33:22 GMT+0
Resolved - All impacted services have now fully recovered..

Jul 23, 15:56:57 GMT+0
Identified - We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation..

Jul 23, 16:08:37 GMT+0
Identified - We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation..

Jul 23, 16:48:54 GMT+0
Identified - We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation with the downstream infrastructure provider..

Google SSO auth doesn't work

2026-06-25T15:20:00.000+00:00

Type: Incident

Duration: 1 day, 1 hour and 21 minutes

Affected Components: Web App

Jun 25, 16:41:00 GMT+0
Resolved - This incident has been resolved..

Jun 25, 15:20:00 GMT+0
Investigating - We are currently investigating this incident..

The call list is not loading

2026-06-23T13:28:00.000+00:00

Type: Incident

Duration: 1 day, 23 hours and 50 minutes

Affected Components: Web App

Jun 23, 13:28:00 GMT+0
Investigating - We are currently investigating this incident..

Jun 23, 15:18:00 GMT+0
Resolved - This incident has been resolved..

Jun 23, 15:00:00 GMT+0
Identified - We are continuing to work on a fix for this incident..

Small number of Eleven V3 TTS generations returning 429s on the Global Residency Server

2026-05-28T11:53:00.000+00:00

Type: Incident

Duration: 17 hours

Affected Components: ElevenLabs → Text to Speech API

May 28, 11:53:00 GMT+0
Identified - We recently identified an issue where a smaller number of Eleven V3 TTS generations were returning 429s on the global residency server. This affected users on lower priority tiers. The service has since been fully restored and is operating normally..

May 28, 12:10:00 GMT+0
Resolved - The incident was resolved..

Elevated Latency and Errors on API

2026-05-27T14:47:02.293+00:00

Type: Incident

Duration: 6 days, 1 hour and 53 minutes

Affected Components: OpenAI → Chat Completions API

May 27, 14:47:02 GMT+0
Investigating - We are investigating the issue for the listed services..

May 27, 15:21:59 GMT+0
Investigating - We are investigating the issue for the listed services..

May 27, 15:45:05 GMT+0
Identified - We are still implementing the mitigation..

May 27, 15:59:22 GMT+0
Monitoring - We have applied the mitigation and are monitoring the recovery..

May 27, 17:12:55 GMT+0
Resolved - All impacted services have now fully recovered..

May 27, 17:54:42 GMT+0
Monitoring - We have received additional reports of elevated latency and errors after our previous recovery update. Mitigation remains in place, and we are monitoring recovery while we validate the remaining impact..

May 27, 20:06:53 GMT+0
Resolved - All impacted services have now fully recovered..

Intermittent 500 Errors in Text-to-Speech (TTS) Generation

2026-05-25T09:47:35.033+00:00

Type: Incident

Duration: 12 hours and 35 minutes

Affected Components: ElevenLabs → Text to Speech API

May 25, 09:02:00 GMT+0
Monitoring - We are currently investigating an issue affecting TTS, where some generations are failing with a 500 error..

May 25, 09:35:00 GMT+0
Resolved - The issue affecting Text-to-Speech (TTS) generation, which was causing intermittent 500 errors, has been resolved. The service is now operating normally..

Outbound networking issues affecting STT, TTS streaming and batch service

2026-05-22T21:00:01.824+00:00

Type: Incident

Affected Components: Deepgram → Text to Speech API

May 22, 21:00:01 GMT+0
Resolved - Some API requests may have experienced elevated error rates for approximately 2-3 minutes starting at 16:43 UTC on May 22, 2026. The issue has been resolved now..

API users may see increased error rates for GPT-5.4 and GPT-5.5

2026-05-19T23:32:19.885+00:00

Type: Incident

Duration: 2 days, 17 hours and 22 minutes

Affected Components: OpenAI → Chat Completions API

May 20, 00:37:42 GMT+0
Resolved - All impacted services have now fully recovered..

May 19, 23:32:19 GMT+0
Identified - We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation..

May 19, 23:38:09 GMT+0
Monitoring - We have applied the mitigation and are monitoring the recovery..

May 19, 23:59:03 GMT+0
Monitoring - We have applied the mitigation and are monitoring the recovery..

EU Residency - Issue with the Agents platform, TTS and Scribe in the EU residency server

2026-05-15T09:12:36.949+00:00

Type: Incident

Duration: 1 day, 6 hours and 14 minutes

Affected Components: ElevenLabs → Text to Speech API

May 15, 09:12:36 GMT+0
Investigating - We are currently investigating an issue with the Agents platform, TTS and Scribe in the EU residency server..

May 15, 09:30:13 GMT+0
Monitoring - We have released an update, and the error rate is back to normal. We are currently monitoring the situation..

May 15, 09:42:51 GMT+0
Resolved - The issue has been resolved. We will publish a public write-up on this status page once the investigation is completed..

Elevated error rates with GPT 5.5

2026-05-11T17:02:24.928+00:00

Type: Incident

Duration: 2 days, 8 hours and 35 minutes

Affected Components: OpenAI → Chat Completions API

May 11, 16:11:00 GMT+0
Investigating - We are investigating the issue for the listed services..

May 11, 16:35:00 GMT+0
Identified - We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation..

May 11, 17:59:00 GMT+0
Resolved - All impacted services have now fully recovered..

May 11, 16:54:00 GMT+0
Monitoring - We have applied the mitigation and are monitoring the recovery..

Increased Error Rate for gpt-5.5 model in the API

2026-05-08T12:31:00.183+00:00

Type: Incident

Duration: 4 days, 7 hours and 41 minutes

Affected Components: OpenAI → Chat Completions API

May 8, 12:31:00 GMT+0
Investigating - We are investigating the issue for the listed services..

May 8, 13:26:14 GMT+0
Investigating - We are seeing partial recovery, but are still working on implementing additional mitigations..

May 8, 13:42:57 GMT+0
Identified - We implemented the mitigations and are observing reduction in error rates, but are still seeing higher than normal latency..

May 8, 13:57:35 GMT+0
Monitoring - We have applied the mitigation and are monitoring the recovery..

May 8, 14:14:41 GMT+0
Resolved - All impacted services have now fully recovered..

Users may experience elevated error rate for gpt-4o-mini in the API

2026-04-29T05:12:25.584+00:00

Type: Incident

Duration: 1 day, 4 hours and 39 minutes

Affected Components: OpenAI → Chat Completions API

Apr 29, 05:12:25 GMT+0
Identified - We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation..

Apr 29, 05:19:19 GMT+0
Monitoring - We have applied the mitigation and are monitoring the recovery..

Apr 29, 05:41:04 GMT+0
Resolved - All impacted services have now fully recovered..

Elevated 401 errors for API endpoints

2026-04-12T20:40:24.206+00:00

Type: Incident

Duration: 1 hour and 18 minutes

Affected Components: OpenAI → Chat Completions API

Apr 14, 01:26:24 GMT+0
Monitoring - We have applied the mitigation and are monitoring the recovery..

Apr 14, 08:41:42 GMT+0
Resolved - All impacted services have now fully recovered..

Apr 12, 20:40:24 GMT+0
Investigating - We are investigating the issue for the listed services..

Apr 13, 05:55:20 GMT+0
Investigating - We are investigating the issue for the listed services..

Apr 13, 17:10:06 GMT+0
Identified - We've identified that intermittent 401 errors on some API endpoints are being caused by timeouts. We have applied mitigations that reduced impact in parts of the system and are continuing to deploy additional fixes and monitor recovery until error rates return to expected levels..

Apr 12, 22:28:22 GMT+0
Monitoring - We have applied the mitigation and are monitoring the recovery..

Apr 13, 06:34:30 GMT+0
Monitoring - We have applied the mitigation and are monitoring the recovery..

Apr 13, 12:57:32 GMT+0
Identified - We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation..

Apr 13, 20:14:02 GMT+0
Identified - We've identified that intermittent 401 errors on some API endpoints are being caused by timeouts. We have applied mitigations that reduced impact in parts of the system and are continuing to deploy additional fixes and monitor recovery until error rates return to expected levels..

Apr 13, 23:26:27 GMT+0
Identified - We've identified that intermittent 401 errors on some API endpoints are being caused by timeouts. We have applied mitigations that reduced impact in parts of the system and are continuing to deploy additional fixes and monitor recovery until error rates return to expected levels..

Outbound networking issues affecting STT PreRecorded API requests with callbacks, TTS Batch (HTTP) requests with callbacks, and Voice Agent API BYO 3rd party providers (LLM and TTS)

2026-04-10T17:27:56.000+00:00

Type: Incident

Duration: 4 days, 19 hours and 35 minutes

Affected Components: Deepgram → Text to Speech API

Apr 10, 17:27:56 GMT+0
Identified - A networking incident was identified which resulted in failed callbacks on STT PreRecorded API requests and TTS Batch requests. The issue also affected Voice Agent API sessions with LLM and TTS providers. We have identified a fix and are monitoring traffic. The source of the issue is being investigated..

Apr 10, 18:15:26 GMT+0
Monitoring - A network infrastructure fix was implemented at 18:15 UTC and the behavior was immediately resolved. We are continuing to monitor carefully..

Apr 13, 19:47:31 GMT+0
Resolved - This incident has been resolved..