← Live dashboard

Elevated errors for multiple models

ResolvedmajorOfficial source confirmedSpecific component onlyFirst recorded update Sep 3, 2026, 01:26 PM · Resolved Sep 3, 2026, 04:23 PM

The issue affecting Claude Mythos 5.1, Claude Fable 5.1, and Claude Opus 5 has been resolved. Impact has ended as of 9:16 PT / 16:16 UTC.

Anthropic live status →

What visitors reported during this incident

No visitor reports were filed for this incident.

Having problems with Anthropic now? Check the current status

Affected services

Claude Coworkclaude.aiClaude CodeClaude API (api.anthropic.com)

Updates (7)

  1. Sep 3, 2026, 04:23 PM
    Elevated errors for multiple models

    The issue affecting Claude Mythos 5.1, Claude Fable 5.1, and Claude Opus 5 has been resolved. Impact has ended as of 9:16 PT / 16:16 UTC.

    Anthropic ↗
  2. Sep 3, 2026, 04:06 PM
    Elevated errors for multiple models

    A fix has been deployed for Claude Mythos 5.1, Claude Fable 5.1, and Claude Opus 5 and we are monitoring for recovery.

    Anthropic ↗
  3. Sep 3, 2026, 03:25 PM
    Elevated errors for multiple models

    The only affected models right now are Opus 4.8 and Opus 5. The rest of the models have recovered to baseline error rate.

    Anthropic ↗
  4. Sep 3, 2026, 02:49 PM
    Elevated errors for multiple models

    We are continuing to work on a fix for this issue.

    Anthropic ↗
  5. Sep 3, 2026, 01:50 PM
    Elevated errors for multiple models

    An exhaustive list of affected models: Mythos/Fable 5.1, Mythos/Fable 5, Opus 5, Opus 4.8, Opus 4.6.

    Anthropic ↗
  6. Sep 3, 2026, 01:41 PM
    Elevated errors for multiple models

    We have identified the cause of elevated errors on requests to Claude Mythos 5.1, Claude Fable 5.1, and Claude Opus 5 and are working on a fix. We will provide an update as soon as possible.

    Anthropic ↗
  7. Sep 3, 2026, 01:26 PM
    Elevated errors for multiple models

    We are investigating elevated errors on requests to Claude Mythos 5.1, Claude Fable 5.1, and Claude Opus 5. We will provide an update as soon as possible.

    Anthropic ↗

What to do next

  • Verify your own services recovered cleanly. Some upstream outages leave queues or caches in a degraded state, run smoke tests before declaring green internally.
  • Save the post-mortem. Vendors usually publish a detailed RCA 1-3 days later. We'll add it to this page when it appears.
  • Watch the provider going forward. Follow Anthropic's status feed →

GlobalOutageMap aggregates publicly reported signals. We never claim authoritative status, always cross-check the provider's official channel before making business decisions.