Apr 3, 15:54 PDT
Resolved - This incident has been resolved.
Apr 3, 14:40 PDT
Monitoring - From 21:27–21:37 UTC, requests to all models received significantly elevated error rates. At this time, success rates have returned to normal and we are closely monitoring to ensure no further recurrence.
Apr 3, 14:34 PDT
Investigating - We are currently investigating this issue.
