Multiple Endpoint Disruptions
Degraded🎉 The issue has been resolved and we are back to normal.
Cohere is up and running. Cohere runs language models and embeddings through an API.
Worked out from the incidents Cohere reported, so it is an estimate and not a measurement.
Last incident: “Multiple Endpoint Disruptions”, 51 days ago.
🎉 The issue has been resolved and we are back to normal.
🎉 The issue has been resolved and we are back to normal.
🎉 The issue affecting Dashboard login has been resolved. All Cohere services are operating normally. Thank you for your patience while we worked through this.
🎉 The issue has been resolved and we are back to normal.
Docs are back up!
Cohere’s official status page says: All Systems Operational. This page checks it again when you load it, at most every 5 minutes.
The most recent incident Cohere reported was “Multiple Endpoint Disruptions”, 51 days ago (2026-09-01 15:41 UTC). Its last full outage started 78 days ago.
Cohere reports 25 components on its status page, including All Endpoints, embeddings, All Models, command-a-plus-05-2026, command-a-reasoning-08-2025. Each is checked again whenever this page refreshes.
Retry with exponential backoff, fall back to another model or provider if your product allows it, and avoid hammering the API while it recovers.
Expected — status.cohere.com lists each model family as its own component (command-r, embed-v4, rerank…). An incident on one model's endpoint doesn't touch the others.
Embeddings and rerank are separate model rows on the status page; check the rerank row specifically rather than 'All Endpoints'.
If the status above is operational but Cohere still fails for you, the cause is probably on your side: try another network, clear the cache, or check your own connection. If it shows a degradation or an outage, others are affected too.
OpenUptime checks your site every minute and sends an alert to Slack, Telegram, email or a webhook the moment it stops responding. It is open source and free to start.