Anthropic incident: Elevated errors across many models

1. resolvedJun 16, 2026, 19:32 UTC

   The incident has now been resolved. We had two phases: * between 10:23 PT / 17:23 UTC to 11:00 PT / 18:00 UTC -- all Sonnet and Opus models were affected, reaching an error rate of around 10% * after 11:00 PT / 18:00 UTC and until 12:20 PT / 19:20 UTC -- Opus 4.8 had an average error rate of 10% The incident is now resolved.

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.

• Claude: We’ve suspended access to Claude Mythos 5 and Claude Fable 5Critical · Jun 13, 2026, 00:50 UTC
• Snowflake: INC20000034Critical · Jun 15, 2026, 14:30 UTC
• Snowflake: INC0159144Major · Jun 16, 2026, 10:29 UTC
• GitHub: Disruption with some GitHub servicesMajor · Jun 16, 2026, 17:45 UTC
• Cursor: Elevated errors across many models on AnthropicMajor · Jun 16, 2026, 18:00 UTC
• Akamai: Edge Delivery - HTTP Content Delivery in EuropeMinor · Jun 5, 2026, 16:36 UTC
• Snyk: Data Freshness delay in Issues API for customers on app.snyk.ioMinor · Jun 16, 2026, 04:52 UTC
• LiveKit: Elevated rate of egress ending early in India regionMinor · Jun 16, 2026, 09:49 UTC
• Twilio: SMS Delivery Delays and Failures from a Subset of Twilio Sender IDs to Multiple Networks in IndiaMinor · Jun 16, 2026, 11:50 UTC
• Mailgun: Delayed logs in US regionMinor · Jun 16, 2026, 14:28 UTC

How often does Anthropic have incidents?

Anthropic reported 85 incidents in the last 90 days, 32 of them major or critical. A typical incident lasted 1h 7m. See Anthropic's uptime and incident history