Live

Elevated errors for Claude Sonnet 5.5 and Claude Fable 5.2

Anthropic reports elevated errors for Claude Sonnet 5.5 and Claude Fable 5.2. The errors affected claude.ai, the Claude API, Claude Code, and Claude Cowork. The issue is resolved and lasted about 73 minutes.

State

Resolved

Started

Lasted

1 h 15 min

Worst impact

Partial outage

Timeline

3 updates
07:4908:0808:2708:4509:04
Partial outageUpdate postedTimes in UTC

Investigating

13 min 18%

Monitoring

1 h 1 min 82%

Updates

Times in UTC

As posted by Anthropic

Resolved

The issue affecting claude.ai, the Claude API, Claude Code, and Claude Cowork has been resolved. Impact occurred from 23:32 PT on November 15 / 07:32 UTC on November 16 to 00:45 PT / 08:45 UTC on November 16.

Monitoring

A fix has been deployed for Claude Sonnet 5.5 and other Claude models and we are monitoring for recovery.

Investigating

We are currently investigating this issue.

Affected components

4
claude.aiClaude API (api.anthropic.com)Claude CodeClaude Cowork

Anthropic in the last 90 days

Full history
90 days agoToday

Incidents in 90 days

48

Days with an incident

41

Median duration

1 h 13 min

This incident

About the median

How long each incident lasted, on the day it started. The outlined bar is this incident.

6 days
median 1 h 13 min
90 days agoToday

Other Anthropic incidents

All incidents

Anthropic·Claude unable to join meetings

Anthropic reports that Claude cannot join new calls in Claude Meetings (beta) on claude.ai. Claude was unable to join many calls. Anthropic identified the issue and put mitigations in place. Claude Meetings is re-enabled for Enterprise customers. Adding Claude to new calls and Auto-join stay paused for Team customers.

Partial outage

Anthropic·Some users unable to sign up with Apple on the Claude iOS app

Sign in with Apple does not work on the Claude iOS app. The problem mainly affects new accounts on claude.ai. Anthropic reports that the issue is resolved. The outage lasted from 00:29 UTC on November 14 to 18:31 UTC on November 16.

Resolved

Anthropic·Elevated purchasing errors on claude.ai

Anthropic reports errors on purchases, plan upgrades and cancellations on claude.ai. The issue is resolved. It lasted about 89 minutes. Delayed plan changes and payments are applied. Anthropic says customers do not need to pay again.

Resolved

Anthropic·Elevated errors on claude.ai, the Claude API, and Claude Code

On 13 November 2026, Anthropic reported elevated errors on claude.ai, the Claude API, Claude Code and Claude Cowork. Anthropic later reported normal error levels on claude.ai and the Claude API, and is monitoring. The incident lasted 2 hours and 30 minutes and is resolved.

Resolved

Anthropic·Elevated errors on claude.ai, Claude Code, and platform.claude.com

Anthropic reported elevated errors on claude.ai, Claude Code, platform.claude.com, and Claude Cowork. Anthropic later confirmed the issue is resolved. The outage lasted about 120 minutes.

Resolved · 1 affected

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.

Prompt
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.live/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.

RSS
https://outages.live/feed.xml?providers=anthropic
Slack
/feed subscribe https://outages.live/feed.xml?providers=anthropic

FAQ

Go from tracking outages to fixing production issues with Polylane.

Try Polylane