Anthropic outage: Elevated errors for multiple models

Affected components

• Claude API (api.anthropic.com)
• Claude Code
• Claude Cowork
• claude.ai

1. resolvedSep 3, 2026, 16:23 UTC

   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.

2. monitoringSep 3, 2026, 16:06 UTC

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

3. identifiedSep 3, 2026, 15:25 UTC

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

4. identifiedSep 3, 2026, 14:49 UTC

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

5. identifiedSep 3, 2026, 13:50 UTC

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

6. identifiedSep 3, 2026, 13:41 UTC

   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.

7. investigatingSep 3, 2026, 13:26 UTC

   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.

What APIStatus.watch saw

Our 5-minute checks didn't record a change in Anthropic's overall status around this incident. Smaller or regional incidents often leave a provider's overall status green.

Other services with incidents at the same time

Overlapping incidents aren't necessarily related.

• Cursor: Investigating service degradationCritical · Sep 3, 2026, 13:41 UTC
• Intercom: Fin failures in Australia regionCritical · Sep 3, 2026, 14:29 UTC
• Elasticsearch: Replication bug causing slow recoveriesMajor · Sep 1, 2026, 08:16 UTC
• OVHcloud: [GLOBAL][Databases] - MongoDB incident notificationMajor · Sep 3, 2026, 10:18 UTC
• Cursor: Elevated errors for Anthropic ModelsMajor · Sep 3, 2026, 14:17 UTC
• Discord: Some servers unavailableMajor · Sep 3, 2026, 14:35 UTC
• OVHcloud: [EU-SOUTH-MIL][Containers & Orchestration] - Managed Private Registry incident notificationMinor · Aug 26, 2026, 15:00 UTC
• Snowflake: INC20000150Minor · Aug 28, 2026, 00:07 UTC
• Telnyx: Intermittent delays for some outbound messagesMinor · Sep 2, 2026, 21:33 UTC
• Notion: Promotional offers may not apply correctly to subscriptionsMinor · Sep 3, 2026, 11:32 UTC

How often does Anthropic have incidents?

Anthropic reported 47 incidents in the last 90 days, 21 of them major or critical. A typical incident lasted 1h 4m. See Anthropic's uptime and incident history