Get email notifications whenever GroqCloud creates, updates or resolves an incident.
Get text message notifications whenever GroqCloud creates or resolves an incident.
Get incident updates and maintenance status messages in Slack.
Subscribe via Slack
By subscribing you acknowledge our Privacy Policy. In addition, you agree to the Atlassian Cloud Terms of Service and acknowledge Atlassian's Privacy Policy.
Get incident updates and maintenance status messages in Microsoft Teams channel.
By subscribing you acknowledge our Privacy Policy. In addition, you agree to the Atlassian Cloud Terms of Service and acknowledge Atlassian's Privacy Policy.
Get webhook notifications whenever GroqCloud creates an incident, updates an incident, resolves an incident or changes a component status.
Visit our support site.
All Systems Operational
About This Site
Reach out to us via live chat by clicking the "Chat with us" button on https://console.groq.com.
Uptime over the past 90 days. View historical uptime.
API
Operational
90 days ago
99.78
% uptime
Today
Website
?
Operational
90 days ago
99.93
% uptime
Today
Operational
Degraded Performance
Partial Outage
Major Outage
Maintenance
Major outage
Partial outage
No downtime recorded on this day.
No data exists for this day.
had a major outage.
had a partial outage.
Related
No incidents or maintenance related to this downtime.
Past Incidents
Jul 19, 2025
Resolved -
This incident has been resolved.
Jul 19, 00:03 UTC
Jul 19, 00:03 UTC
Update -
We are continuing to work on a fix for this issue.
Jul 19, 00:02 UTC
Jul 19, 00:02 UTC
Identified -
The issue has been identified and a fix is being implemented.
Jul 18, 22:25 UTC
Jul 18, 22:25 UTC
Update -
We've spotted that something has gone wrong. We're currently investigating the issue, and will provide an update soon.
Jul 18, 21:32 UTC
Jul 18, 21:32 UTC
Investigating -
moonshotai/kimi-k2-instruct is currently experiencing slow response times and increased errors.
We are currently investigating this incident.
Jul 18, 20:55 UTC
We are currently investigating this incident.
Jul 18, 20:55 UTC
Jul 18, 2025
Resolved -
We have resolved the issue affecting API key requests in our US Central region. We have confirmed stability and do not expect further impact. Thank you for your patience while we worked to restore functionality.
Jul 18, 19:23 UTC
Jul 18, 19:23 UTC
Monitoring -
A fix has been implemented and we are monitoring the results.
Jul 18, 18:57 UTC
Jul 18, 18:57 UTC
Identified -
The issue has been identified, and a workaround is in place while we implement a permanent solution.
Jul 18, 18:52 UTC
Jul 18, 18:52 UTC
Update -
We've identified that the issue only affects API keys calling our US Central region. Our team is actively investigating the root cause.
Jul 18, 18:39 UTC
Jul 18, 18:39 UTC
Update -
We have validated the issue with intermittent 401 errors using valid API keys is not model specific. The team is continue to investigate.
Jul 18, 18:00 UTC
Jul 18, 18:00 UTC
Investigating -
We are currently investigating reports of intermittent 401 errors when using valid API keys.
Jul 18, 17:42 UTC
Jul 18, 17:42 UTC
Jul 17, 2025
No incidents reported.
Jul 16, 2025
Resolved -
This incident has been resolved.
Jul 16, 21:55 UTC
Jul 16, 21:55 UTC
Monitoring -
We are seeing improvements on Deepseek-R1-Distll-Llama-70B. We are monitoring while we ensure service has consistently returned.
Jul 16, 21:42 UTC
Jul 16, 21:42 UTC
Identified -
Our deepseek-r1-distill-llama-70b model is partially degraded causing increased error rates and latency. The team is currently working to remediate.
Jul 16, 21:04 UTC
Jul 16, 21:04 UTC
Resolved -
This incident has been resolved.
As a result of a lightning strike, one of our primary data centers in the US central region experienced cooling issues that resulted in an urgent powering down of all servers in the facility. Our global model scheduler was running on general-purpose compute in the impaired data center and the decision was made to re-locate it.
The actions taken resulted in all model instances globally being re-created causing significant degradation of service between 02:08 UTC and 02:24 UTC. Unfortunately, the scheduler isn't currently optimized for rapid model bringup in multiple regions at the same and manual intervention was required which delayed the recovery. By 02:27 UTC errors rates had dropped for ~3% and by 03:34 UTC had returned to standard levels.
Jul 16, 03:57 UTC
As a result of a lightning strike, one of our primary data centers in the US central region experienced cooling issues that resulted in an urgent powering down of all servers in the facility. Our global model scheduler was running on general-purpose compute in the impaired data center and the decision was made to re-locate it.
The actions taken resulted in all model instances globally being re-created causing significant degradation of service between 02:08 UTC and 02:24 UTC. Unfortunately, the scheduler isn't currently optimized for rapid model bringup in multiple regions at the same and manual intervention was required which delayed the recovery. By 02:27 UTC errors rates had dropped for ~3% and by 03:34 UTC had returned to standard levels.
Jul 16, 03:57 UTC
Update -
We are seeing performance improvement across the impacted models as the team continues to remediate the issue.
Jul 16, 02:45 UTC
Jul 16, 02:45 UTC
Update -
We are continuing to work on a fix for this issue.
Jul 16, 02:17 UTC
Jul 16, 02:17 UTC
Update -
The team has identified the issue causing varying outage, elevated error rates, and latency across several models. They are working to implement a fix.
Jul 16, 02:02 UTC
Jul 16, 02:02 UTC
Identified -
The team is currently investigating an issue that may be causing errors across various models.
Jul 16, 01:31 UTC
Jul 16, 01:31 UTC
Jul 15, 2025
No incidents reported.
Jul 14, 2025
Resolved -
meta-llama/llama-4-scout-17b-16e-instruct experienced elevated error rates and increased queue times from 05:33 -> 05:34 UTC. Within our me-central1 region, the model was degraded from 03:15 -> 03:19 UTC and 05:33 -> 05:37 UTC.
Jul 14, 03:00 UTC
Jul 14, 03:00 UTC
Jul 13, 2025
No incidents reported.
Jul 12, 2025
No incidents reported.
Jul 11, 2025
No incidents reported.
Jul 10, 2025
No incidents reported.
Jul 9, 2025
Resolved -
This incident has been resolved.
Jul 9, 07:00 UTC
Jul 9, 07:00 UTC
Monitoring -
Our search partner has mitigated the issue and we are seeing regular performance and monitoring.
Jul 9, 06:51 UTC
Jul 9, 06:51 UTC
Investigating -
We are currently working with our search partner to resolve slow search capabilities for compound beta models
Jul 9, 04:18 UTC
Jul 9, 04:18 UTC
Jul 8, 2025
Resolved -
This incident has been resolved.
Jul 8, 04:04 UTC
Jul 8, 04:04 UTC
Monitoring -
We are no longer seeing 500 errors on whisper-large-v3-turbo. The team is continuing to monitor.
Jul 7, 19:56 UTC
Jul 7, 19:56 UTC
Investigating -
We are experiencing increased 500 errors on whisper-large-v3-turbo
We are currently investigating this incident
Jul 7, 18:42 UTC
We are currently investigating this incident
Jul 7, 18:42 UTC
Jul 7, 2025
Jul 6, 2025
No incidents reported.
Jul 5, 2025
No incidents reported.