Anthropic outage history

We are investigating an outage affecting features such as document creation in claude.ai, Cowork Remote and Claude Code Remote

We are currently investigating this issue.

A fix has been implemented and we are monitoring the results.

This incident has been resolved.

We are currently investigating this issue.

This incident has been resolved.

Elevated errors for Claude Opus 4.5 and Claude Sonnet 4.5 between 6:00am PT / 1:00pm UTC and 8:15am PT / 3:15pm UTC.

We are investigating elevated errors on requests to Claude Opus 4.8. We will provide an update as soon as possible.

This issue has been resolved

We are currently investigating a performance issue affecting features such as Claude Code on the Web (claude.ai/code), Claude Code Review, Cowork Remote, Claude Tag, and document creation in claude.ai. Our team is working on mitigating this issue.

A fix has been implemented and we are monitoring the results.

This issue has been resolved.

We are currently investigating this issue.

We have identified an issue causing elevated errors on requests to some models, and our team is working to resolve this issue as quickly as possible. We will provide an additional update shortly.

At this time, success rates have recovered across impacted models and we are monitoring closely to ensure no further issues occur.

We are continuing to work to fully resolve errors impacting some requests, and will provide an additional update as soon as possible.

This issue has been resolved. Users saw elevated errors on requests to some models between 10:45am PT / 17:45 UTC and 12:40pm PT / 19:40 UTC.

Users are unable to send authorized requests to MCP servers.

We are currently investigating this issue.

This incident has been resolved.

We are investigating elevated errors on requests to some models. We will provide an update as soon as possible.

We have seen success rates return to normal, but we are continuing to work to fully resolve this issue and ensure no further recurrences.

We are continuing to work to resolve an issue resulting in elevated errors on requests to some models, primarily Claude Fable 5. We will provide an additional update as soon as possible.

We are continuing to monitor issues affecting requests to some models, and have once again seen success rates return to normal. We are working to ensure there are no further issues, and will provide an additional update shortly.

This issue has been resolved.

We are currently investigating this issue.

This incident has been resolved.

We are currently investigating elevated error rates on calls made Claude Tag. Our team is actively working to identify the root cause. You may experience errors such as GitHub operations denied.

Our team has made some changes to update the load to GitHub, that we think will reduce this error rate.

Our team is observing a lower error rate after these changes. We will continue investigating in-case we observe any spikes.

We are investigating elevated errors on Claude.ai, and will provide an update as soon as possible.

We have identified and are working to resolve an issue impacting Claude.ai. An additional impact of the ongoing issue is the inability to log-in via Claude.ai OAuth for Claude Code. We will provide an additional update as soon as possible.

We have applied a fix, and at this time are seeing recovery of Claude.ai and related services such as OAuth log-in for Claude Code.

This issue has been resolved.

We are currently investigating this issue.

Fable 5 has now also started returning errors.

This incident has been resolved.

We are currently investigating this issue.

A fix has been implemented and we are monitoring the results.

This incident has been resolved.

We are currently investigating this issue.

The issue has been identified and a fix is being implemented.

A fix has been implemented and we are monitoring the results.

This incident has been resolved.

We are currently investigating this issue.

The issue has been identified and a fix is being implemented.

This incident has been resolved.

We are currently investigating elevated error rates on Opus 4.8. Our team is actively working to identify the root cause.

A fix has been implemented and we are monitoring the results.

This incident has been resolved.

We are currently investigating this issue.

The issue has been identified and a fix is being implemented.

A fix has been implemented and we are monitoring the results.

This incident has been resolved.

Elevated errors on Opus-48. It has been mitigated. We are actively monitoring the system.