Increased rate of errors for Opus 4.5

Timeline

Started: 2026-01-13T07:27:43.824Z

Updated: 2026-01-13T18:58:32.238Z

Resolved: 2026-01-13T07:49:57.861Z

Impact scope

Official sources

Provider: anthropic

Updates

• unknown

  On January 12-13, 2026, Claude Opus 4.5 users experienced elevated error rates and degraded service for approximately 2 hours across two separate incidents. The root cause was a configuration mismatch between our inference servers that caused our load balancing system to route traffic unevenly, overloading a subset of our infrastructure. We have fixed the underlying configuration issue and added safeguards to prevent similar mismatches in the future.

  2026-01-13T18:57:40.340Z

• resolved

  This incident has been resolved.

  2026-01-13T07:49:57.861Z

• monitoring

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

  2026-01-13T07:39:24.494Z

• investigating

  We are currently investigating this issue.

  2026-01-13T07:27:43.996Z