Claude Outage History

Claude Opus 4.6 experienced elevated error rates starting at 1:33 PT, affecting both claude.ai and api.anthropic.com services. Error rates returned to baseline levels at 2:19 PT, and the incident was fully resolved after 53 minutes of impact.

Claude Desktop version 1.1.9310 had a major issue where Dispatch sessions stopped responding - messages were received and processed but replies did not appear in conversations, while standard Cowork sessions remained unaffected. The incident lasted 3.9 hours and was resolved by fixing the underlying issue that prevented agents from sending responses and releasing an updated desktop app version 1.1.9493.

Claude's Opus 4.6 model experienced elevated error rates for 9.8 hours, affecting claude.ai, console.anthropic.com, and api.anthropic.com. During the incident, Sonnet 4.6 also temporarily showed elevated errors but was restored to normal operation after about 7 hours. The main issue was mitigated and error rates returned to baseline levels.

Claude experienced elevated errors for MCP (Model Context Protocol) calls, affecting the claude.ai service for 16 minutes. Users reported that voice functionality was unavailable during this period. The incident was investigated and resolved within the same timeframe.

Claude experienced elevated errors affecting Opus 4.6 and Sonnet 4.6 models for 2.9 hours, impacting claude.ai, the developer console, and API endpoints. Users reported issues including unavailable voice options during the incident. The issue was identified as causing a low rate of errors and was fully resolved.

Claude Opus 4.6 experienced elevated errors for 9.2 hours, affecting claude.ai, console.anthropic.com, and api.anthropic.com. The service experienced multiple waves of issues throughout the incident period, with errors recurring after initial mitigation attempts. The incident was fully resolved after implementing a fix and monitoring period.

Claude experienced elevated errors for 2 hours affecting claude.ai, preventing users from accessing the service across web, mobile, and desktop applications. Users consistently received "This isn't working right now. You can try again later" error messages, with additional issues including login failures, 500 errors, slow chat responses, and problems with project chats and file uploads. The issue was identified and resolved with a fix implementation after monitoring for recovery.

Claude Opus 4.6 experienced elevated errors for 3.6 hours, affecting claude.ai, console.anthropic.com, and api.anthropic.com. Users reported continuous server downtime during the incident. The issue was resolved after implementing a fix and monitoring the results.

Between 9:10 PT and 9:26 PT, users experienced an elevated rate of errors when using Claude.ai, while the Claude API remained unaffected. The incident lasted approximately 16 minutes and has been resolved.

Claude experienced a major service incident that prevented users from logging into both claude.ai and the Claude Console (platform.claude.com). The authentication issue affected user access to these platforms for approximately 8 minutes before a mitigation was applied and logins returned to normal. The incident was fully resolved with authentication services restored across all affected components.