Anthropic outage: Elevated errors across all models

Affected components

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

1. resolvedJul 29, 2026, 22:36 UTC

   This issue has been resolved.

2. monitoringJul 29, 2026, 22:20 UTC

   From 12:45 PT / 19:45 UTC through to 1:26 PT / 21:26 UTC, we saw elevated rates of errors across Claude models. We have seen recovery in success rates across all models and are monitoring closely to ensure no further issues.

3. identifiedJul 29, 2026, 21:38 UTC

   We are continuing to work to fully resolve issues resulting in elevated requests and latency to Claude models. At this time, we are seeing recovery across most models. We will provide an additional update as soon as possible.

4. identifiedJul 29, 2026, 20:33 UTC

   We have identified an issue resulting in elevated errors across multiple models, and are working to resolve this. We will provide an update as soon as possible.

5. investigatingJul 29, 2026, 19:49 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.

• HashiCorp Vault: HCP Terraform Workspace Runs Failing with IAM Errors After AWS Provider UpgradeMajor · Jul 29, 2026, 12:36 UTC
• Resend: Elevated error rates on email sending, API, and dashboardMajor · Jul 29, 2026, 21:07 UTC
• RevenueCat: Newly created apps error with "The key is not valid or is not compatible with the Bundle ID of your app"Minor · Jul 27, 2026, 10:14 UTC
• DigitalOcean: Response Degradation Impacting Kimi-K3Minor · Jul 29, 2026, 17:56 UTC
• GitHub: Incident with Copilot AI Model ProvidersMinor · Jul 29, 2026, 20:07 UTC
• Grafana Cloud: IRM Performance Degradation in EU RegionMinor · Jul 29, 2026, 21:46 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