Cohere Outage History
9 incidents recorded over the last 365 days, 9 of them resolved. Durations are measured from when PulsAPI first saw the problem to when it cleared, which is usually longer than the vendor's own figure.
Every Recorded Cohere Incident
| Date | Incident | Duration | Status |
|---|---|---|---|
| Sep 1, 2026 | Multiple Endpoint Disruptions🎉 The issue has been resolved and we are back to normal. | 4h 22m | Resolved |
| Aug 5, 2026 | Documentation Content Loading Issues🎉 The issue has been resolved and we are back to normal. | 57 min | Resolved |
| Jul 23, 2026 | Dashboard Login Service Disruption🎉 The issue affecting Dashboard login has been resolved. All Cohere services are operating normally. Thank you for your patience while we worked through this. | 50 min | Resolved |
| Jun 1, 2026 | /audio/transcriptions endpoint returns error for audio files with unexpected sampling rate🎉 The issue has been resolved and we are back to normal. | 2h 54m | Resolved |
| Apr 20, 2026 | Docs Platform Degraded PerformanceDocs are back up! | 12 min | Resolved |
| Apr 13, 2026 | Multiple Model Disruptions🎉 The issue has been resolved and we are back to normal. | 1h 24m | Resolved |
| Apr 11, 2026 | Scheduled DB Maintenance: Model authentication and API access momentarily affected🎉 The issue has been resolved and we are back to normal. | 8 min | Resolved |
| Feb 13, 2026 | Some chat models are unresponsive or timing outThe issue has been resolved and all models are back to normal operation | 1h 17m | Resolved |
| Oct 18, 2025 | Chat models return 503 service error when /v1/chat requests omit message and chat_history while providing tool_results🎉 The issue has been resolved and we are back to normal. | 36 min | Resolved |
Hear about the next one while it is open
Everything above is a record written after the fact. We can email you when the next Cohere incident opens instead, at the point where knowing still changes what you do.
Free, no password, no card. Unsubscribe in one click.
How to Read This Cohere Incident Log
Each row is an incident PulsAPI observed, not a summary written afterwards. The duration is wall-clock time between the first failing check and the first clean one, so it includes the window before Cohere acknowledged anything. Vendor post-mortems typically measure from acknowledgement, which is why their numbers are usually shorter.
Incidents still open have no duration yet and are listed as ongoing rather than being given a running total. The archive covers the last 365 days; anything older has aged out of the window rather than never having happened.
The longest single Cohere outage in this window ran 4h 22m, against a mean recovery of 1h 24m. If you depend on Cohere in a customer-facing path, the longest figure is the one to design around. The mean is what happens on a normal bad day; the maximum is what happens on the worst one.