Anthropic incident: Degraded performance of multiple models

Affected components

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

1. resolvedAug 5, 2026, 14:14 UTC

   This incident has been resolved.

2. monitoringAug 5, 2026, 13:08 UTC

   A fix has been deployed for the issue affecting Claude services and we are monitoring for recovery.

3. identifiedAug 5, 2026, 09:13 UTC

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

4. identifiedAug 5, 2026, 07:05 UTC

   We have identified the cause of elevated errors on requests to Claude Mythos 5, Claude Fable 5, and Claude Opus 5, Claude Sonnet 5 and are working on a fix. 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.

• MongoDB Atlas: GCP capacity constraints affecting Atlas deploymentsMajor · Aug 5, 2026, 05:17 UTC
• Supabase: Project Upgrade DelaysMinor · Aug 3, 2026, 15:28 UTC
• OVHcloud: [EU-WEST-PAR][Storage] - Object storage incident notificationMinor · Aug 4, 2026, 14:08 UTC
• Snyk: Degraded performance on Security.snyk.io with 502 responses.Minor · Aug 5, 2026, 04:28 UTC
• GitHub: Some Copilot Cloud Agent jobs not startingMinor · Aug 5, 2026, 11:38 UTC
• Grafana Cloud: o11y requests too large for nods in the prod-eu-west-2 region.Minor · Aug 5, 2026, 11:41 UTC
• Claude: Degraded performance for Claude Opus 5Minor · Aug 5, 2026, 13:51 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