Anthropic outage: Elevated errors on requests to multiple models

Affected components

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

1. resolvedAug 20, 2026, 19:42 UTC

   This issue has been resolved.

2. investigatingAug 20, 2026, 19:16 UTC

   We are investigating elevated errors on requests to some Claude models. We will provide additional updates 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.

• GitHub: Intermittent failures creating agent tasksCritical · Aug 20, 2026, 14:43 UTC
• Render: Deployment IssuesMajor · Aug 20, 2026, 15:47 UTC
• Confluent Cloud: Elevated error rates and latency in GCP us-west1Major · Aug 20, 2026, 17:10 UTC
• Supabase: 401 errors due to JWT rejectionsMinor · Aug 14, 2026, 02:23 UTC
• Telnyx: Programmable Wireless data loss in AustraliaMinor · Aug 17, 2026, 19:27 UTC
• Akamai: Reporting data availability issues in 'Traffic by Hostname' reportMinor · Aug 20, 2026, 16:43 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