Anthropic outage: Elevated errors across many models

Affected components

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

1. resolvedAug 4, 2026, 21:59 UTC

   This issue has been resolved.

2. investigatingAug 4, 2026, 21:04 UTC

   We have identified an issue which resulted in some users experiencing issues when attempting to log into Anthropic services, including Claude.ai and Claude Code via oAuth. Additionally, some users saw errors when making requests to models. At this time, we have seen success rates recover and are monitoring closely to ensure there are no further issues.

3. investigatingAug 4, 2026, 20:48 UTC

   We are currently investigating this issue.

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.

• Grafana Cloud: Some Grafana Instances UnavailableCritical · Aug 4, 2026, 19:11 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
• DigitalOcean: Spaces Cold Storage BillingMinor · Aug 4, 2026, 16:13 UTC
• Expo: Elevated Android build failuresMinor · Aug 4, 2026, 17:54 UTC
• CircleCI: Increased Job Queue Times: Windows, Android, and GPUMinor · Aug 4, 2026, 19:27 UTC
• LiveKit: Elevated timeouts on LiveKit Inference (google/gemma-4-31b-it)Minor · Aug 4, 2026, 20:45 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