Cohere Outage History
25 incidents reported. Data sourced from the official Cohere status page.
25
Total Incidents
6
Major/Critical
17
Minor
25
Resolved
August 2026
Documentation Content Loading Issues
majorAug 5, 07:36 PMāAug 5, 08:33 PMresolved
Aug 5, 08:35 PM
resolved ā š The issue has been resolved and we are back to normal.
Aug 5, 08:33 PM
resolved ā š The issue has been resolved and we are back to normal.
Aug 5, 07:36 PM
investigating ā 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 ...
July 2026
Dashboard Login Service Disruption
majorJul 23, 10:56 PMāJul 23, 11:46 PMresolved
Jul 23, 11:46 PM
resolved ā š The issue affecting Dashboard login has been resolved. All Cohere services are operating normally. Thank you for your patience while we worked through this.
Jul 23, 11:36 PM
monitoring ā š The issue affecting Dashboard login has been resolved ā
. We're monitoring to confirm stability. All Cohere services are operating normally.
Jul 23, 11:27 PM
identified ā š ļø **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 s...
+1 more updates
June 2026
/audio/transcriptions endpoint returns error for audio files with unexpected sampling rate
noneJun 1, 01:51 PMāJun 1, 04:46 PMresolved
Jun 1, 04:46 PM
resolved ā š The issue has been resolved and we are back to normal.
Jun 1, 01:51 PM
identified ā /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...
April 2026
Docs Platform Degraded Performance
criticalApr 20, 10:16 PMāApr 20, 10:28 PMresolved
Apr 20, 10:28 PM
resolved ā Docs are back up!
Apr 20, 10:16 PM
investigating ā 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 pro...
Multiple Model Disruptions
minorApr 13, 07:36 PMāApr 13, 09:00 PMresolved
Apr 13, 09:00 PM
resolved ā š The issue has been resolved and we are back to normal.
Apr 13, 07:45 PM
monitoring ā š We are monitoring to make sure the incident has been fully resolved.
Apr 13, 07:36 PM
investigating ā We are currently investigating Multiple Model Disruptions.
Scheduled DB Maintenance: Model authentication and API access momentarily affected
minorApr 11, 03:31 PMāApr 11, 03:39 PMresolved
Apr 11, 03:39 PM
resolved ā š The issue has been resolved and we are back to normal.
Apr 11, 03:31 PM
identified ā 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...
February 2026
Some chat models are unresponsive or timing out
majorFeb 13, 04:34 AMāFeb 13, 05:51 AMresolved
Feb 13, 05:51 AM
resolved ā The issue has been resolved and all models are back to normal operation
Feb 13, 05:35 AM
monitoring ā We identified and resolved the connectivity problem affecting certain chat models. Affected models are starting to come back online.
Feb 13, 04:34 AM
investigating ā We are currently investigating an incident with chat models.
October 2025
Chat models return 503 service error when /v1/chat requests omit message and chat_history while providing tool_results
noneOct 18, 09:46 PMāOct 18, 10:23 PMresolved
Oct 18, 10:23 PM
resolved ā š The issue has been resolved and we are back to normal.
Oct 18, 09:46 PM
identified ā š ļø We have identified the root cause of the incident, and are working diligently to fix.
logprobs param degeraded for `command-a-03-2025` and `command-a-reasoning-08-2025`
minorOct 1, 03:56 PMāOct 1, 07:46 PMresolved
Oct 1, 07:46 PM
resolved ā `logprobs` feature has been correctly marked as unavailable for the specified models.
Oct 1, 03:56 PM
investigating ā We have identified that the `logprobs` parameter is not working as expected for the following models:
ā¢ `command-a-03-2025`
ā¢ `command-a-reasoning-08-2025`
The team is investigating the incident.
August 2025
Command-a-vision-07-2025 degraded performance
minorAug 7, 08:46 PMāAug 7, 08:56 PMresolved
Aug 7, 08:56 PM
resolved ā š The issue has been resolved and we are back to normal.
Aug 7, 08:46 PM
identified ā š ļø We have identified the root cause of the incident, and are working diligently to fix.
July 2025
Model serving infrastructure outage
criticalJul 25, 03:54 PMāJul 25, 07:52 PMresolved
Jul 25, 07:52 PM
resolved ā š The issue has been resolved and we are back to normal.
Jul 25, 07:12 PM
monitoring ā š We are monitoring to make sure the incident has been fully resolved.
Jul 25, 06:25 PM
identified ā š ļø We have identified the root cause of the incident, and are working diligently to fix.
+2 more updates
June 2025
GCP Outage
minorJun 12, 07:02 PMāJun 12, 10:44 PMresolved
Jun 12, 10:44 PM
resolved ā š The issue has been resolved and we are back to normal.
Jun 12, 07:02 PM
monitoring ā 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
Degraded service affecting embed-v4.0
minorMay 21, 04:53 PMāMay 21, 07:15 PMresolved
May 21, 07:15 PM
resolved ā š The issue has been resolved and we are back to normal.
May 21, 04:53 PM
investigating ā š We are currently investigating this live incident.
Degraded service affecting embedding models
minorMay 8, 02:25 PMāMay 13, 03:01 PMresolved
May 13, 03:01 PM
resolved ā š The issue has been resolved and we are back to normal.
May 8, 05:14 PM
monitoring ā š We are monitoring to make sure the incident has been fully resolved.
May 8, 02:25 PM
investigating ā š We are currently investigating this live incident.
April 2025
Degraded Performance - Increased Latency - Command-a-03-2025/command-r-plus-08-2024
minorApr 3, 05:29 PMāApr 4, 08:58 PMresolved
Apr 4, 08:58 PM
resolved ā š The issue has been resolved and we are back to normal.
Apr 4, 08:58 PM
resolved ā š The issue has been resolved and we are back to normal.
Apr 3, 09:11 PM
monitoring ā š We are monitoring to make sure the incident has been fully resolved.
+2 more updates
Degraded Performance: command-a-03-2025 - Increased Latency
minorApr 2, 10:20 PMāApr 3, 01:49 AMresolved
Apr 3, 01:49 AM
resolved ā š The issue has been resolved and we are back to normal.
Apr 2, 10:20 PM
monitoring ā š We are monitoring to make sure the incident has been fully resolved.
March 2025
High latency
minorMar 29, 07:03 PMāMar 29, 07:14 PMresolved
Mar 29, 07:14 PM
resolved ā š The issue has been resolved and we are back to normal.
Mar 29, 07:03 PM
investigating ā š We are currently investigating this live incident.
Increased Latency
minorMar 28, 08:40 PMāMar 28, 11:58 PMresolved
Mar 28, 11:58 PM
resolved ā š The issue has been resolved and we are back to normal.
Mar 28, 08:40 PM
investigating ā š We are currently investigating this live incident.
Increased Latency
minorMar 28, 07:17 PMāMar 28, 07:38 PMresolved
Mar 28, 07:38 PM
resolved ā š The issue has been resolved and we are back to normal.
Mar 28, 07:17 PM
investigating ā š We are currently investigating this live incident.
Elevated Latency
minorMar 27, 05:51 PMāMar 27, 06:02 PMresolved
Mar 27, 06:02 PM
resolved ā š The issue has been resolved and we are back to normal.
Mar 27, 05:51 PM
investigating ā š We are currently investigating this live incident.
CommandR / CommandR plus: Elevated Error Rate
minorMar 24, 06:33 PMāMar 24, 08:26 PMresolved
Mar 24, 08:26 PM
resolved ā š The issue has been resolved and we are back to normal.
Mar 24, 06:33 PM
monitoring ā š We are monitoring to make sure the incident has been fully resolved.
Rerank Endpoint: Degraded Service
minorMar 20, 06:00 PMāMar 20, 07:29 PMresolved
Mar 20, 07:29 PM
resolved ā š The issue has been resolved and we are back to normal.
Mar 20, 06:00 PM
investigating ā š We are currently investigating this live incident.
Chat Endpoint: Encountering Increased Error rate
minorMar 19, 01:12 AMāMar 19, 11:46 AMresolved
Mar 19, 11:46 AM
resolved ā š The issue has been resolved and we are back to normal.
Mar 19, 01:35 AM
monitoring ā š We are monitoring to make sure the incident has been fully resolved.
Mar 19, 01:12 AM
investigating ā š We are currently investigating this live incident.
Team has implementing a workaround to restore access to impacted accounts
majorMar 1, 03:06 AMāMar 1, 05:51 AMresolved
Mar 1, 05:51 AM
resolved ā š The issue has been resolved and we are back to normal.
Mar 1, 04:52 AM
identified ā š ļø We have identified the root cause of the incident, and are working diligently to fix.
Mar 1, 04:12 AM
identified ā š ļø We have identified the root cause of the incident, and are working diligently to fix.
+1 more updates
February 2025
Embedding: Investigating Degraded Service
minorFeb 21, 07:51 AMāFeb 21, 05:05 PMresolved
Feb 21, 05:05 PM
resolved ā š The issue has been resolved and we are back to normal.
Feb 21, 08:18 AM
monitoring ā š We are monitoring to make sure the incident has been fully resolved.
Feb 21, 07:51 AM
investigating ā š We are currently investigating this live incident.
Related Incident Histories
Get Cohere Outage Alerts
Be the first to know when Cohere go down.