Serval had 40 outages in the last 2 years totaling 60h 36m of downtime — averaging 1.6 incidents per month.
There were 40 Serval outages since October 22, 2025 totaling 60h 36m of downtime. Each is summarised below — incident details, duration, and resolution information.
We are investigating the issue for the listed services.
We are implementing the mitigation.
All impacted services have now fully recovered.
We have identified that users are experiencing elevated latency for the impacted services. We are working on implementing a mitigation.
We have identified that users are experiencing elevated latency for the impacted services. We are working on implementing a mitigation.
We have implemented an initial mitigation and are seeing improvements in API latency. We are continuing to investigate the scope of the issue and apply additional mitigations as needed. Some requests to the Responses and Chat Completions APIs may still experience elevated latency or timeouts.
We have applied the mitigation and are monitoring the recovery.
All impacted services have now fully recovered.
We’re investigating elevated errors affecting ChatGPT, Codex, and the API. Some users may experience failed requests, difficulty logging in or signing up, and tasks that do not complete. We’ll share updates as we learn more.
We’re investigating elevated errors affecting ChatGPT, Codex, and the API including the Agents API. Some users may experience failed requests, difficulty logging in or signing up, and tasks that do not complete. We’ll share updates as we learn more.
We’re still investigating elevated errors affecting ChatGPT, Codex, and the API including the Agents API. Some users may experience failed requests, difficulty logging in or signing up, and tasks that do not complete. We’ll share updates as we learn more.
We have applied the mitigation and are monitoring the recovery.
We have applied the mitigation and are monitoring the recovery.
We have applied the mitigation and are monitoring the recovery.
We have applied the mitigation and are monitoring the recovery.
The issue causing elevated errors across ChatGPT, Codex, and the API has been resolved, and all affected services have recovered. Thank you for your patience while we worked to restore service. The detailed Root Cause Analysis (RCA) will be published in the next 5 business days.
We are continuing to work on a fix for this incident.
We implemented a fix and are currently monitoring the result.
We are experiencing email deliverability issues due to a AWS SES rate-limit issue. We are working with AWS support to get it resolved ASAP.
This was resolved by a rate limit increase.
We are currently investigating issues with SSO-based login. It appears to be an issue with a downstream auth-provider, WorkOS. See
This issue is resolved. WorkOS has recovered from their API errors.
We are currently investigating this incident.
We are continuing to work on a fix for this incident.
This is caused by AWS outage with SNS in us-west-1\. We are still actively monitoring. Some customers are reporting they are now able to create email tickets. 
We are still monitoring. Many customers report being able to create tickets via email and getting fast response times. Some customers will still experience slow response times caused by the outage to AWS Simple Notification Service (SNS).
This incident has been resolved.
We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.
We have applied the mitigation and are monitoring the recovery.
All impacted services have now fully recovered.
We are currently investigating this incident.
We implemented a fix and are currently monitoring the result.
This incident has been resolved.
We are currently investigating this incident.
We are continuing to work on a fix for this incident.
We implemented a fix and are currently monitoring the result.
This incident has been resolved.
We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.
We have brought additional capacity online and are seeing improvements for some GPT-5.6 Sol API traffic. We continue to mitigate elevated errors affecting Chat Completions and Responses and are monitoring recovery
All impacted services have now fully recovered.
We are currently investigating this incident.
We are continuing to work on a fix for this incident.
Latency is recovering after working through a backlog of events. We're monitoring.
This incident has been resolved.
We are currently investigating this incident.
This incident has been resolved.
We are currently investigating this incident.
We have identified a root cause and are implementing a fix.
We implemented a fix and are currently monitoring recovery.
We are observing a return to normal behavior and are continuing to monitor recovery.
This incident has been mitigated. We are working to implement long-term preventative fixes.
Type: Incident Duration: 33 minutes Affected Components: Application Sep 3, 10:30:00 GMT+0 - Investigating - We are currently investigating this incident. Sep 3, 11:03:16 GMT+0 - Resolved - We have observed performance returning to normal baseline. We are implementing longer term fixes to address this class of performance degradation. This incident has been resolved.
We have identified an issue causing elevated latency for some Responses API requests. We are working on implementing a mitigation.
We have applied a mitigation and are monitoring recovery.
We have applied the mitigation and are monitoring the recovery.
We have identified elevated latencies impacting Responses API on the US endpoint.
We are implementing the mitigation.
We have applied the mitigation and are monitoring the recovery.
All impacted services have now fully recovered.
We are currently investigating this incident.
We have identified a root cause and are now implementing a fix.
We have implemented a fix and are observing availability is recovering. We are currently monitoring recovery.
This incident has been resolved.
We have identified an issue causing intermittent connectivity issues with our EU deployment. We are working to implement a fix.
We have deployed a fix and are monitoring for service recovery and stability.
This incident has been resolved.
We are currently investigating this incident.
We have identified the root cause of the availability issue and are implementing a fix.
We are deploying the fix and monitoring the result.
We have deployed the fix and are monitoring service recovery.
We have identified additional contributing factors that are impacting Serval availability. We are working to restore service and will provide updates as they become available.
We have implemented mitigations for issues impacting availability and are monitoring recovery.
This incident has been resolved.
We are currently investigating this incident.
We are currently investigating this incident.
We have applied a fix and are monitoring for service recovery. Service performance is degraded but recovering.
We are continuing to monitor recovery. Performance has recovered to baseline.
This incident has been resolved. We are implementing long term remediations.
Type: Incident Duration: 3 days, 12 hours and 51 minutes Affected Components: Third Party: OpenAI → APIs → Chat Completions Jul 29, 00:55:27 GMT+0 - Investigating - We are investigating the issue for the listed services. Jul 29, 01:39:33 GMT+0 - Monitoring - We have applied the mitigation and are monitoring the recovery. Jul 29, 02:20:19 GMT+0 - Resolved - All impacted services have now fully recovered.
Type: Incident Duration: 1 day, 12 hours and 39 minutes Affected Components: Third Party: OpenAI → APIs → Chat Completions Jul 27, 15:30:00 GMT+0 - Investigating - We are investigating the issue for the listed services. Jul 27, 17:30:00 GMT+0 - Resolved - All impacted services have now fully recovered.
Type: Incident Duration: 21 hours and 37 minutes Affected Components: Third Party: OpenAI → APIs → Responses, Third Party: OpenAI → APIs → Chat Completions Jul 25, 11:35:24 GMT+0 - Identified - We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation. Jul 25, 11:46:39 GMT+0 - Monitoring - We have applied the mitigation and are monitoring the recovery. Jul 25, 11:57:02 GMT+0 - Resolved - All impacted services have now fully recovered.