Outage in Anthropic
Elevated errors on several models
Resolved MajorIncident Report
Summary AI Generated
Anthropic experienced elevated error rates across multiple Claude models on both claude.ai and the API for approximately one hour on July 21, 2026 (8:28–9:26am PT). The issue was identified and a fix was implemented within roughly 55 minutes of the incident starting. Service was fully restored by 9:26am PT.
We are currently investigating this issue.
Trusted by 1,000+ teams
The Status Page Aggregator with Early Outage Detection
Stop finding out about outages from your users. Monitor 6,320+ cloud services and get alerted the second something breaks.
Latest Updates ( sorted recent to last )
RESOLVED
about 14 hours ago - at 07/21/2026 06:18PM
From 8:28am PT / 15:28 UTC through 9:26am PT / 16:26 UTC users experienced elevated errors on requests to multiple Claude models. This issue has been resolved.
MONITORING
about 15 hours ago - at 07/21/2026 05:07PM
A fix has been implemented and we are monitoring the results.
IDENTIFIED
about 16 hours ago - at 07/21/2026 03:51PM
The issue has been identified and a fix is being implemented.
INVESTIGATING
about 16 hours ago - at 07/21/2026 03:35PM
We are currently investigating this issue.
Latest Anthropic outages
Service disruption on Claude services - about 14 hours ago
Elevated errors on Haiku 4.5 - about 19 hours ago
Elevated errors across Fable 5 - about 21 hours ago
Elevated errors across models - about 22 hours ago
Elevated errors on Haiku 4.5 - 1 day ago
The Status Page Aggregator with Early Outage Detection
With IsDown, you can monitor all your critical services' official status pages from one centralized dashboard and receive instant alerts the moment an outage is detected. Say goodbye to constantly checking multiple sites for updates and stay ahead of outages with IsDown.
Start free trialNo credit card required · Cancel anytime · 6320 services available
Integrations with
