Claude Outage History

Claude's Opus 4.6 model experienced elevated error rates for 1.3 hours, affecting the console, API, and main Claude website. The incident impacted users' ability to interact with the Opus model across all Anthropic platforms. The issue was successfully resolved after investigation and remediation efforts.

Claude experienced a 56-minute service incident where users encountered errors when uploading documents to Google Drive from Claude.ai, including the desktop app and Cowork. The issue affected multiple components including console.anthropic.com, api.anthropic.com, and claude.ai, and has been resolved.

Claude's Opus 4.6 model experienced an elevated rate of errors for 52 minutes, affecting the console, API, and main Claude website. The issue was identified and resolved with a fix implementation.

Claude experienced a major service outage lasting 2.9 hours that affected Claude.ai, the API, and Claude Code, causing widespread login failures, internal server errors (500 errors), and connection issues across all platforms. Users reported being unable to access Claude.ai with "check your connection" messages, API requests failing with internal server errors, and inability to log into Claude Code and desktop applications. The incident was resolved after engineers identified the root cause and implemented a fix, with the API recovering first followed by the web platform and login services.

Claude experienced degraded performance on usage and analytics admin API endpoints for 5.9 hours, causing intermittent 503 errors that affected claude.ai, api.anthropic.com, and console.anthropic.com. The root cause was identified and fixes were deployed through the standard pipeline. The incident was resolved after implementing the fix and monitoring confirmed normal service operation.

Claude.ai experienced a major outage affecting login functionality across claude.ai, api.anthropic.com, and console.anthropic.com for 56 minutes. Users were unable to log in to the web application, were logged out of existing sessions, and could not load their cloud sessions when the interface was accessible. The login issue was identified and resolved, with service fully restored after approximately 48 minutes of impact.

Claude experienced elevated errors affecting requests to all models except Claude Opus 4.6 across claude.ai, the API, and console for 21 minutes. Users were unable to send requests, impacting development work and other activities. The issue was identified as specifically affecting non-Opus models and was fully resolved.

Claude's connectors experienced elevated error rates for 40 minutes, affecting both claude.ai and api.anthropic.com services. Users reported service disruptions, including complete outages in some locations like Seattle. The issue was investigated and resolved within 40 minutes of initial detection.

Claude's Sonnet 4.6 model experienced an elevated rate of errors for 48 minutes, affecting claude.ai, the API, and console services. Users reported Claude not responding to prompts, hanging without output, and longer than usual response times. The issue was identified and resolved with a fix implementation.

Claude experienced authentication failures across all platforms from 17:25-17:44 UTC, preventing users from logging into Claude.ai (web, mobile, desktop), platform.claude.com, and Claude Code. Users encountered 500 Internal Server Error messages when attempting to access the services. The authentication issue was resolved after 19 minutes, restoring normal login functionality across all affected platforms.