Resolved after 2 hours 25 minutes, affecting claude.ai and Claude Console (platform.claude.com) and 1 more, on June 23, 2026.
We have seen error rates broadly return to normal success levels across all models. We saw elevated error rates on requests to multiple models from 7:08am PT / 14:08 UTC through 8:33am PT / 15:33 UTC.
Affected components
Update timeline
- investigating Jun 23, 2026, 02:19 PM UTC
We are currently investigating this issue.
- identified Jun 23, 2026, 02:25 PM UTC
The issue has been identified and a fix is being implemented.
- monitoring Jun 23, 2026, 02:53 PM UTC
A fix has been implemented and we are monitoring the results.
- monitoring Jun 23, 2026, 03:28 PM UTC
We are continuing to monitor for any further issues.
- monitoring Jun 23, 2026, 04:05 PM UTC
We have seen error rates broadly return to normal success levels across all models. We saw elevated error rates on requests to multiple models from 7:08am PT / 14:08 UTC through 8:33am PT / 15:33 UTC.
- resolved Jun 23, 2026, 04:44 PM UTC
This incident has been resolved.
Your product runs on more than Anthropic
Add the vendors you depend on and get one message when any of them reports trouble. Free for 3 vendors, no card.
Amazon Web Services