Okou - Notice history

API performance has remained stable following mitigation. This incident has been resolved.

Mitigation has been applied and API performance has stabilized. We've deployed additional safeguards and are monitoring to confirm continued stability.

We identified elevated traffic affecting the Backend API and user-related requests, causing increased latency and intermittent failures. We've applied mitigation and are monitoring its effect. We'll provide another update once we confirm service stability.

This issue has been resolved. From 9:50pm PT / 04:50 UTC through 00:36am PT / 07:36 UTC, users saw elevated errors on requests to Claude models, including Claude Opus 5 and Fable 5.

At this time, we have seen errors stabilize on Opus 5 and Fable 5, and are working to fully resolve success rates on all affected models. We will provide an update as soon as possible.

We are continuing to work to resolve issues causing elevated requests on multiple models. We will provide an update as soon as possible.

We have identified the cause of elevated errors on requests to Claude Mythos 5, Claude Fable 5, Claude Opus 5, and other Claude models and are working on a fix. We will provide an update as soon as possible.

This incident has been resolved.

A fix has been implemented and we are monitoring the results.

This incident has been resolved.

This incident has been resolved.

A fix has been implemented and we are monitoring the results.

We've noticed that Cloudflare has confirmed the outage. We are currently trying to redeploy to resolve the issue.

We are continuing our attempts to deploy the code on Cloudflare. We can confirm that there will be no data loss during this process. The empty content in chat thread is just a temporary frontend issue.

We are continuing to work on a fix for this incident. We believe this was caused by the API backend service deployment and the web frontend deployment failing to sync during the most recent release. The web deployment is currently delayed due to a Cloudflare outage, which is preventing us from pushing new updates on time. We are waiting for Cloudflare to resolve the deployment issue.

This incident has been resolved.

This incident has been resolved.

This incident has been resolved.

We are also investigating issues with Opus 4.7 and Opus 4.5.

As of 2:58 PT / 9:58 UTC the errors are back to baseline.

As of 01:33 PT / 08:33 UTC we are back to errors across all models.

As of 8:05 UTC / 1:05 PT, Sonnet 5 errors are back to baseline, but we're seeing an increased error rate on Fable 5.

As of 7:32 UTC / 0:32 PT, Opus 5 errors are back to baseline but we're seeing again Sonnet 5's errors up.

All models except Opus 5 have recovered. We're working to recover Opus 5 as well.

This issue has been resolved.

From 12:45 PT / 19:45 UTC through to 1:26 PT / 21:26 UTC, we saw elevated rates of errors across Claude models. We have seen recovery in success rates across all models and are monitoring closely to ensure no further issues.

We are continuing to work to fully resolve issues resulting in elevated requests and latency to Claude models. At this time, we are seeing recovery across most models. We will provide an additional update as soon as possible.

We have identified an issue resulting in elevated errors across multiple models, and are working to resolve this. We will provide an update as soon as possible.

All impacted services have now fully recovered.

A fix has been published and confirmed it's now resolving SVGs correctly

A fix has been deployed and we're seeing improved rates of resolution on the SVGs

All impacted services have now fully recovered.

We have applied the mitigation and are monitoring the recovery.

We are continuing to investigate the issue regarding elevated 431 errors and are working on the mitigation.