Incident

Updates

1. investigating Jul 30, 2026, 3:49 AM GMT+08:00

   We are currently investigating this issue.

2. identified Jul 30, 2026, 4:33 AM GMT+08:00

   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.

3. identified Jul 30, 2026, 5:38 AM GMT+08:00

   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.

4. monitoring Jul 30, 2026, 6:20 AM GMT+08:00

   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.

5. resolved Jul 30, 2026, 6:36 AM GMT+08:00

   This issue has been resolved.