Elevated error rates on requests to some models
A record of the Anthropic incident on May 15, 2026 (Japan time): start time, duration and severity, plus current status, what to do, and alternatives.
Other providers down at the same time
1 other incident(s) at different providers overlapped with this one. It may not have been limited to a single service — several providers were degraded at once.
- CursorService degradation for Opus 4.6 and Opus 4.7
Derived from our own archive of official status pages across 13 providers. Items lasting more than 24 hours and unresolved items are excluded, as they would misrepresent the moment.
How big was this outage?
This outage lasted 88 minutes. Across 54 major incidents recorded for Anthropic, the median duration is 85 minutes, making this the 26th longest.
Longer than a typical outage.
Only incidents recorded as major-or-worse and already resolved are counted.
Current status
Anthropic is operating normally now. This incident has been resolved.
See current Anthropic status →What you can do during an outage
Source: Anthropic's official status page.
Other Anthropic incidents
- Elevated errors for multiple modelsSeptember 3, 2026
- Elevated errors for Claude Sonnet 5September 3, 2026
- Elevated errors for Claude Sonnet 5September 3, 2026
- Delays in credit purchasesSeptember 2, 2026
- Degraded performance on platform.claude.com and Claude for Microsoft Office 365September 2, 2026