Elevated errors for multiple models
This issue has been resolved. From 9:50pm PT / 04:50 UTC through 00:36am PT / 07:36 UTC, users saw elevated errors on requests to Claude models, including Claude Opus 5 and Fable 5.
The latest update from Anthropic.
State
Resolved
Started
69 d ago
2026-08-24 05:06 UTC
Lasted
3 h 24 min
until 2026-08-24 08:30 UTC
Worst impact
Partial outage
Timeline
5 updatesInvestigating
21 min 10%
Identified
3 h 3 min 90%
Updates
Times in UTCAs posted by Anthropic
This issue has been resolved. From 9:50pm PT / 04:50 UTC through 00:36am PT / 07:36 UTC, users saw elevated errors on requests to Claude models, including Claude Opus 5 and Fable 5.
At this time, we have seen errors stabilize on Opus 5 and Fable 5, and are working to fully resolve success rates on all affected models. We will provide an update as soon as possible.
We are continuing to work to resolve issues causing elevated requests on multiple models. We will provide an update as soon as possible.
We have identified the cause of elevated errors on requests to Claude Mythos 5, Claude Fable 5, Claude Opus 5, and other Claude models and are working on a fix. We will provide an update as soon as possible.
We are investigating elevated errors on requests to Claude Mythos 5, Claude Fable 5, Claude Opus 5, and Claude Opus 4.8. We will provide an update as soon as possible.
Affected components
4Anthropic in the last 90 days
Full historyIncidents in 90 days
50
Days with an incident
42
Median duration
1 h 8 min
This incident
3.0× the median
Other Anthropic incidents
All incidentsAnthropic·Elevated errors affecting the Google Calendar connector
The issue affecting the Google Calendar connector on claude.ai, Claude Code, and Claude Cowork has been resolved. Impact occurred from 04:07 PT / 11:07 UTC on October 26 to 11:52 PT / 18:52 UTC on October 28.
Anthropic·Elevated errors affecting the Gmail connector
The issue affecting the Gmail connector on claude.ai, Claude Code, and Claude Cowork has been resolved. Impact occurred from 16:00 PT / 23:00 UTC on October 27 to 22:29 PT on October 27 / 05:29 UTC on October 28.
Anthropic·Elevated errors for Claude Sonnet 5.5
The issue affecting claude.ai, the Claude API, Claude Code, and Claude Cowork has been resolved. Impact occurred from 07:42 PT / 14:42 UTC to 08:17 PT / 15:17 UTC.
Anthropic·Elevated errors for Claude Sonnet 5.5
The issue affecting Claude services has been resolved.
Anthropic·Elevated errors for Claude Fable 5.1
The issue affecting Claude services has been resolved. Impact occurred from 01:08 PT / 08:08 UTC to 01:29 PT / 08:29 UTC.
Follow Anthropic
Your coding agent knows when Anthropic is down, and tells you when a failure is theirs, not yours. You can also get Anthropic incidents in a feed reader or in Slack.
Install the outages.live MCP server, so that when something breaks you can tell if the cause is a provider we depend on and not my code. It reads the official status pages of cloud, AI, payment and developer providers and gives you their incidents as MCP tools.
Add it as a remote MCP server named "outages" at https://outages.cc/mcp (Streamable HTTP, no authentication), with your CLI command or your MCP config file.
Then:
1. Make sure it connects and shows the tools get_provider, list_feed and send_feedback.
2. Call get_provider with "anthropic" and tell me if Anthropic has a problem right now.
3. From now on, when a call to a third-party service fails or becomes slow, call get_provider for that service before you change my code.Paste this into any coding agent. It adds the server with its own MCP setup.
https://outages.cc/feed.xml?providers=anthropic/feed subscribe https://outages.cc/feed.xml?providers=anthropicFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane