Is Cohere Down?
Command R+, Command R, Embed, Rerank, Coral, and Cohere API services.
Official status data last reflected here:
[ STATUS AT A GLANCE ]
System Components
Current status of individual Cohere services
Cohere down? Route around it.
When Cohere has issues, Bifrost automatically routes your requests to a healthy alternative provider. Zero code changes. 99.999% effective uptime.
About Cohere
What Cohere does, where the data on this page comes from, and recent reliability
[ ABOUT COHERE ]
About Cohere
Cohere provides Command models, Embed, Rerank, and Coral. Cohere status is especially important for production retrieval and ranking systems where latency and model availability directly shape search relevance and workflow quality.
This page pulls data from Cohere's official status page to show current service health, any active incidents, and a history of recent issues, all in one view.
[ DATA SOURCES ]
Full incident history available
Cohere publishes detailed component status, a full incident archive, and scheduled maintenance data through their official status page.
- Data pulled from Cohere's official status page (status.cohere.com)
- Refreshed every 60 seconds
- Covers Command models, Embed, Rerank, and Coral
- Includes full incident archive and scheduled maintenance history
[ RELIABILITY ]
Recent reliability
- 2 incidents reported over the last 90 days.
- Last reported incident was 1 day ago.
- All 24 monitored components are currently operational.
[ COMMON USE CASES ]
How teams use Cohere
Cohere status is especially important for production retrieval and ranking systems where latency and model availability directly shape search relevance and workflow quality.
Incidents & Maintenance
Active incidents, scheduled maintenance, and incident history for Cohere
Past Incidents
Dashboard Login Service Disruption
Jul 23, 2026 · Resolved Jul 23, 2026
🎉 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 affecting Dashboard login has been resolved ✅. We're monitoring to confirm stability. All Cohere services are operating normally.
🛠️ **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.
🔎 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.
/audio/transcriptions endpoint returns error for audio files with unexpected sampling rate
Jun 1, 2026 · Resolved Jun 1, 2026
🎉 The issue has been resolved and we are back to normal.
/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.
Docs Platform Degraded Performance
Apr 20, 2026 · Resolved Apr 20, 2026
Docs are back up!
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.
Multiple Model Disruptions
Apr 13, 2026 · Resolved Apr 13, 2026
🎉 The issue has been resolved and we are back to normal.
👀 We are monitoring to make sure the incident has been fully resolved.
We are currently investigating Multiple Model Disruptions.
Scheduled DB Maintenance: Model authentication and API access momentarily affected
Apr 11, 2026 · Resolved Apr 11, 2026
🎉 The issue has been resolved and we are back to normal.
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.
Some chat models are unresponsive or timing out
Feb 13, 2026 · Resolved Feb 13, 2026
The issue has been resolved and all models are back to normal operation
We identified and resolved the connectivity problem affecting certain chat models. Affected models are starting to come back online.
We are currently investigating an incident with chat models.
Chat models return 503 service error when /v1/chat requests omit message and chat_history while providing tool_results
Oct 18, 2025 · Resolved Oct 18, 2025
🎉 The issue has been resolved and we are back to normal.
🛠️ 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`
Oct 1, 2025 · Resolved Oct 1, 2025
`logprobs` feature has been correctly marked as unavailable for the specified models.
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.
Command-a-vision-07-2025 degraded performance
Aug 7, 2025 · Resolved Aug 7, 2025
🎉 The issue has been resolved and we are back to normal.
🛠️ We have identified the root cause of the incident, and are working diligently to fix.
Model serving infrastructure outage
Jul 25, 2025 · Resolved Jul 25, 2025
🎉 The issue has been resolved and we are back to normal.
👀 We are monitoring to make sure the incident has been fully resolved.
🛠️ We have identified the root cause of the incident, and are working diligently to fix.
🔎 We are currently investigating this live incident.
Command models are down due to a model serving infrastructure outage
GCP Outage
Jun 12, 2025 · Resolved Jun 12, 2025
🎉 The issue has been resolved and we are back to normal.
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.
Degraded service affecting embed-v4.0
May 21, 2025 · Resolved May 21, 2025
🎉 The issue has been resolved and we are back to normal.
🔎 We are currently investigating this live incident.
Degraded service affecting embedding models
May 8, 2025 · Resolved May 13, 2025
🎉 The issue has been resolved and we are back to normal.
👀 We are monitoring to make sure the incident has been fully resolved.
🔎 We are currently investigating this live incident.
Degraded Performance - Increased Latency - Command-a-03-2025/command-r-plus-08-2024
Apr 3, 2025 · Resolved Apr 4, 2025
🎉 The issue has been resolved and we are back to normal.
🎉 The issue has been resolved and we are back to normal.
👀 We are monitoring to make sure the incident has been fully resolved.
🛠️ We have identified the root cause of the incident, and are working diligently to fix.
🔎 We are currently investigating this live incident.
Degraded Performance: command-a-03-2025 - Increased Latency
Apr 2, 2025 · Resolved Apr 3, 2025
🎉 The issue has been resolved and we are back to normal.
👀 We are monitoring to make sure the incident has been fully resolved.
High latency
Mar 29, 2025 · Resolved Mar 29, 2025
🎉 The issue has been resolved and we are back to normal.
🔎 We are currently investigating this live incident.
Increased Latency
Mar 28, 2025 · Resolved Mar 28, 2025
🎉 The issue has been resolved and we are back to normal.
🔎 We are currently investigating this live incident.
Increased Latency
Mar 28, 2025 · Resolved Mar 28, 2025
🎉 The issue has been resolved and we are back to normal.
🔎 We are currently investigating this live incident.
Elevated Latency
Mar 27, 2025 · Resolved Mar 27, 2025
🎉 The issue has been resolved and we are back to normal.
🔎 We are currently investigating this live incident.
CommandR / CommandR plus: Elevated Error Rate
Mar 24, 2025 · Resolved Mar 24, 2025
🎉 The issue has been resolved and we are back to normal.
👀 We are monitoring to make sure the incident has been fully resolved.
Frequently Asked Questions
Is Cohere down right now?
Check the status indicator at the top of this page. It pulls directly from Cohere's official status page. If Cohere is experiencing any issues, you'll see it reflected here. This real-time monitoring helps teams quickly identify whether performance problems are caused by Cohere infrastructure or their own systems.
What does this Cohere status page track?
This page tracks Command models, Embed, Rerank, and Coral using data from Cohere's official status page. You can see current component health, active incidents, and a history of past issues. This visibility is crucial for teams building resilient AI applications that need to route around provider outages.
How often is Cohere status updated here?
We check Cohere's status page every 60 seconds to ensure you get near real-time status updates. How quickly issues show up here depends on how fast Cohere updates their own official status. For production systems that need instant failover, Bifrost can automatically detect and route around degraded providers.
Why monitor Cohere status?
Cohere status is especially important for production retrieval and ranking systems where latency and model availability directly shape search relevance and workflow quality. Real-time status monitoring enables proactive incident response and helps teams decide when to route traffic to alternative providers for maximum uptime.
What should I do when Cohere goes down?
When Cohere experiences an outage, the best practice is automatic failover to alternative AI providers. Bifrost is an open-source AI gateway that automatically detects Cohere degradation and routes LLM traffic to healthy alternatives like OpenAI, Anthropic, Azure OpenAI, keeping your application running with zero manual intervention. This intelligent routing ensures your users never experience downtime from a single provider's issues.
How can I prevent Cohere downtime from affecting my application?
Production AI applications should never depend on a single provider. Bifrost AI Gateway provides automatic multi-provider failover, intelligent load balancing, and health-based routing. When Cohere degrades, Bifrost instantly routes requests to operational alternatives while maintaining API compatibility. This architecture approach is used by teams running mission-critical AI features.
What are common causes of Cohere outages and degraded performance?
Common causes of Cohere issues include infrastructure scaling challenges, regional cloud provider problems, API gateway overload, and deployment errors. Monitor this page to stay informed, and consider implementing automatic failover with Bifrost to maintain uptime during Cohere incidents.
Alternative Providers for Automatic Failover
When Cohere experiences issues, Bifrost AI Gateway can automatically route your LLM traffic to these alternatives
💡 Build resilient AI apps: Configure Bifrost to automatically detect Cohere outages and route requests to healthy alternatives. This multi-provider approach ensures your application maintains uptime even when individual providers experience issues. Learn more about Bifrost AI Gateway
Cohere Models & Pricing
Cohere offers 17 models across 3 modes (8 embedding, 7 chat, 2 completion)