Live / Cohere / Incident
Cohere: Team has implementing a workaround to restore access to impacted accounts
Cohere · cohere.comMajor incidentResolved2025-03-01 05:51 UTC
Public — what happened
Summary
Cohere reported a major incident starting at 03:06 UTC on March 1, 2025, in which some accounts lost access, according to the incident's title. The company said at 04:12 UTC that it had found the root cause, though it did not describe what that cause was, and the title indicates a workaround was put in place to restore access for the affected accounts. Cohere marked the incident resolved at 05:51 UTC, saying service was back to normal.
Timeline
- Started — 2025-03-01 03:06 UTC
- Investigating — 2025-03-01 03:06 UTC
- Identified — 2025-03-01 04:12 UTC (2 updates)
- Resolved — 2025-03-01 05:51 UTC · 2h 46m after it started
With SquidGrid — where it starts on the route
Independent path health
The status page is the symptom. SquidGrid measures the paths that reach Cohere against their own baselines — whether the routes carrying your traffic degraded, at which handoff, and who owns that stretch.
🔒 Sign in to seeCustomers get the live Provider Assessment Report for Cohere: its full incident track record, what tends to break, and recent public reports of problems.
Included with any paid plan.
Open the Cohere report →
More from Cohere