C

Cohere Outage History

Past incidents and downtime events

Complete history of Cohere outages, incidents, and service disruptions. Showing 25 most recent incidents.

August 2026(1 incident)

majorresolvedAug 5, 07:36 PM — Resolved Aug 5, 08:33 PM

Documentation Content Loading Issues

3 updates
resolvedAug 5, 08:35 PM

🎉 The issue has been resolved and we are back to normal.

resolvedAug 5, 08:33 PM

🎉 The issue has been resolved and we are back to normal.

investigatingAug 5, 07:36 PM

We are investigating a partial outage affecting our documentation site. Some documentation pages may not load correctly due to an ongoing issue with our upstream documentation provider (Fern). We are monitoring the incident and will share updates as they become available.

July 2026(1 incident)

majorresolvedJul 23, 10:56 PM — Resolved Jul 23, 11:46 PM

Dashboard Login Service Disruption

4 updates
resolvedJul 23, 11:46 PM

🎉 The issue affecting Dashboard login has been resolved. All Cohere services are operating normally. Thank you for your patience while we worked through this.

monitoringJul 23, 11:36 PM

👀 The issue affecting Dashboard login has been resolved ✅. We're monitoring to confirm stability. All Cohere services are operating normally.

identifiedJul 23, 11:27 PM

🛠️ **Update:** We have identified the cause of login issues affecting the Cohere Dashboard, preventing successful logins. A fix is being implemented now and we expect Dashboard login to be restored shortly. **Note:** API access, model inference, and all other Cohere services are **unaffected** and operating normally.

investigatingJul 23, 10:56 PM

🔎 We are currently investigating an issue affecting the Cohere Dashboard ([dashboard.cohere.com](http://dashboard.cohere.com "dashboard.cohere.com")). Users may experience a continuous refresh loop on the login page, preventing successful authentication.

June 2026(1 incident)

noneresolvedJun 1, 01:51 PM — Resolved Jun 1, 04:46 PM

/audio/transcriptions endpoint returns error for audio files with unexpected sampling rate

2 updates
resolvedJun 1, 04:46 PM

🎉 The issue has been resolved and we are back to normal.

identifiedJun 1, 01:51 PM

/audio/transcriptions endpoints availability is affected now due to the Cohere ASR model backing the endpoint throws error for any audio inputs that are in the expected sampling rate. Previously these sampling rate audio files were accepted and processed, marking this as a regression type incident. :hammer_and_wrench: We have identified the root cause of the incident, and are working diligently to fix.

April 2026(3 incidents)

criticalresolvedApr 20, 10:16 PM — Resolved Apr 20, 10:28 PM

Docs Platform Degraded Performance

2 updates
resolvedApr 20, 10:28 PM

Docs are back up!

investigatingApr 20, 10:16 PM

We are currently experiencing an outage affecting our documentation site due to an issue with our third-party documentation provider, Fern. Our team is actively monitoring the situation while the provider investigates and works on a fix.

minorresolvedApr 13, 07:36 PM — Resolved Apr 13, 09:00 PM

Multiple Model Disruptions

3 updates
resolvedApr 13, 09:00 PM

🎉 The issue has been resolved and we are back to normal.

monitoringApr 13, 07:45 PM

👀 We are monitoring to make sure the incident has been fully resolved.

investigatingApr 13, 07:36 PM

We are currently investigating Multiple Model Disruptions.

minorresolvedApr 11, 03:31 PM — Resolved Apr 11, 03:39 PM

Scheduled DB Maintenance: Model authentication and API access momentarily affected

2 updates
resolvedApr 11, 03:39 PM

🎉 The issue has been resolved and we are back to normal.

identifiedApr 11, 03:31 PM

There is a scheduled DB maintenance in progress. All the API authentication when accessing models are affected momentarily. The auth and API services is coming back online and should be fully up very soon.

February 2026(1 incident)

majorresolvedFeb 13, 04:34 AM — Resolved Feb 13, 05:51 AM

Some chat models are unresponsive or timing out

3 updates
resolvedFeb 13, 05:51 AM

The issue has been resolved and all models are back to normal operation

monitoringFeb 13, 05:35 AM

We identified and resolved the connectivity problem affecting certain chat models. Affected models are starting to come back online.

investigatingFeb 13, 04:34 AM

We are currently investigating an incident with chat models.

October 2025(2 incidents)

noneresolvedOct 18, 09:46 PM — Resolved Oct 18, 10:23 PM

Chat models return 503 service error when /v1/chat requests omit message and chat_history while providing tool_results

2 updates
resolvedOct 18, 10:23 PM

🎉 The issue has been resolved and we are back to normal.

identifiedOct 18, 09:46 PM

🛠️ We have identified the root cause of the incident, and are working diligently to fix.

minorresolvedOct 1, 03:56 PM — Resolved Oct 1, 07:46 PM

logprobs param degeraded for `command-a-03-2025` and `command-a-reasoning-08-2025`

2 updates
resolvedOct 1, 07:46 PM

`logprobs` feature has been correctly marked as unavailable for the specified models.

investigatingOct 1, 03:56 PM

We have identified that the `logprobs` parameter is not working as expected for the following models: • `command-a-03-2025` • `command-a-reasoning-08-2025` The team is investigating the incident.

August 2025(1 incident)

minorresolvedAug 7, 08:46 PM — Resolved Aug 7, 08:56 PM

Command-a-vision-07-2025 degraded performance

2 updates
resolvedAug 7, 08:56 PM

🎉 The issue has been resolved and we are back to normal.

identifiedAug 7, 08:46 PM

🛠️ We have identified the root cause of the incident, and are working diligently to fix.

July 2025(1 incident)

criticalresolvedJul 25, 03:54 PM — Resolved Jul 25, 07:52 PM

Model serving infrastructure outage

5 updates
resolvedJul 25, 07:52 PM

🎉 The issue has been resolved and we are back to normal.

monitoringJul 25, 07:12 PM

👀 We are monitoring to make sure the incident has been fully resolved.

identifiedJul 25, 06:25 PM

🛠️ We have identified the root cause of the incident, and are working diligently to fix.

investigatingJul 25, 04:33 PM

🔎 We are currently investigating this live incident.

investigatingJul 25, 03:54 PM

Command models are down due to a model serving infrastructure outage

June 2025(1 incident)

minorresolvedJun 12, 07:02 PM — Resolved Jun 12, 10:44 PM

GCP Outage

2 updates
resolvedJun 12, 10:44 PM

🎉 The issue has been resolved and we are back to normal.

monitoringJun 12, 07:02 PM

We are currently experiencing an outage with Google Cloud Platform (GCP), which may impact some of our services. Our team is actively monitoring the situation.

May 2025(2 incidents)

minorresolvedMay 21, 04:53 PM — Resolved May 21, 07:15 PM

Degraded service affecting embed-v4.0

2 updates
resolvedMay 21, 07:15 PM

🎉 The issue has been resolved and we are back to normal.

investigatingMay 21, 04:53 PM

🔎 We are currently investigating this live incident.

minorresolvedMay 8, 02:25 PM — Resolved May 13, 03:01 PM

Degraded service affecting embedding models

3 updates
resolvedMay 13, 03:01 PM

🎉 The issue has been resolved and we are back to normal.

monitoringMay 8, 05:14 PM

👀 We are monitoring to make sure the incident has been fully resolved.

investigatingMay 8, 02:25 PM

🔎 We are currently investigating this live incident.

April 2025(2 incidents)

minorresolvedApr 3, 05:29 PM — Resolved Apr 4, 08:58 PM

Degraded Performance - Increased Latency - Command-a-03-2025/command-r-plus-08-2024

5 updates
resolvedApr 4, 08:58 PM

🎉 The issue has been resolved and we are back to normal.

resolvedApr 4, 08:58 PM

🎉 The issue has been resolved and we are back to normal.

monitoringApr 3, 09:11 PM

👀 We are monitoring to make sure the incident has been fully resolved.

identifiedApr 3, 05:34 PM

🛠️ We have identified the root cause of the incident, and are working diligently to fix.

investigatingApr 3, 05:29 PM

🔎 We are currently investigating this live incident.

minorresolvedApr 2, 10:20 PM — Resolved Apr 3, 01:49 AM

Degraded Performance: command-a-03-2025 - Increased Latency

2 updates
resolvedApr 3, 01:49 AM

🎉 The issue has been resolved and we are back to normal.

monitoringApr 2, 10:20 PM

👀 We are monitoring to make sure the incident has been fully resolved.

March 2025(8 incidents)

minorresolvedMar 29, 07:03 PM — Resolved Mar 29, 07:14 PM

High latency

2 updates
resolvedMar 29, 07:14 PM

🎉 The issue has been resolved and we are back to normal.

investigatingMar 29, 07:03 PM

🔎 We are currently investigating this live incident.

minorresolvedMar 28, 08:40 PM — Resolved Mar 28, 11:58 PM

Increased Latency

2 updates
resolvedMar 28, 11:58 PM

🎉 The issue has been resolved and we are back to normal.

investigatingMar 28, 08:40 PM

🔎 We are currently investigating this live incident.

minorresolvedMar 28, 07:17 PM — Resolved Mar 28, 07:38 PM

Increased Latency

2 updates
resolvedMar 28, 07:38 PM

🎉 The issue has been resolved and we are back to normal.

investigatingMar 28, 07:17 PM

🔎 We are currently investigating this live incident.

minorresolvedMar 27, 05:51 PM — Resolved Mar 27, 06:02 PM

Elevated Latency

2 updates
resolvedMar 27, 06:02 PM

🎉 The issue has been resolved and we are back to normal.

investigatingMar 27, 05:51 PM

🔎 We are currently investigating this live incident.

minorresolvedMar 24, 06:33 PM — Resolved Mar 24, 08:26 PM

CommandR / CommandR plus: Elevated Error Rate

2 updates
resolvedMar 24, 08:26 PM

🎉 The issue has been resolved and we are back to normal.

monitoringMar 24, 06:33 PM

👀 We are monitoring to make sure the incident has been fully resolved.

minorresolvedMar 20, 06:00 PM — Resolved Mar 20, 07:29 PM

Rerank Endpoint: Degraded Service

2 updates
resolvedMar 20, 07:29 PM

🎉 The issue has been resolved and we are back to normal.

investigatingMar 20, 06:00 PM

🔎 We are currently investigating this live incident.

minorresolvedMar 19, 01:12 AM — Resolved Mar 19, 11:46 AM

Chat Endpoint: Encountering Increased Error rate

3 updates
resolvedMar 19, 11:46 AM

🎉 The issue has been resolved and we are back to normal.

monitoringMar 19, 01:35 AM

👀 We are monitoring to make sure the incident has been fully resolved.

investigatingMar 19, 01:12 AM

🔎 We are currently investigating this live incident.

majorresolvedMar 1, 03:06 AM — Resolved Mar 1, 05:51 AM

Team has implementing a workaround to restore access to impacted accounts

4 updates
resolvedMar 1, 05:51 AM

🎉 The issue has been resolved and we are back to normal.

identifiedMar 1, 04:52 AM

🛠️ We have identified the root cause of the incident, and are working diligently to fix.

identifiedMar 1, 04:12 AM

🛠️ We have identified the root cause of the incident, and are working diligently to fix.

investigatingMar 1, 03:06 AM

🔎 We are currently investigating this live incident.

February 2025(1 incident)

minorresolvedFeb 21, 07:51 AM — Resolved Feb 21, 05:05 PM

Embedding: Investigating Degraded Service

3 updates
resolvedFeb 21, 05:05 PM

🎉 The issue has been resolved and we are back to normal.

monitoringFeb 21, 08:18 AM

👀 We are monitoring to make sure the incident has been fully resolved.

investigatingFeb 21, 07:51 AM

🔎 We are currently investigating this live incident.

📡 Tired of checking Cohere status manually?

Better Stack monitors uptime every 30 seconds and alerts you instantly when Cohere goes down.

Start Free Monitoring →