Anthropic favicon

Anthropic outage on 2026-11-13

claude.com
November 2026 13 Major incident

Anthropic's claude.ai, Claude Code and API had two separate error spells on 13 November 2026, totalling over four and a half hours of combined incident time. Both were faults on Anthropic's side, not anything in your own setup.

Started

09:58 UTC

Duration

Lasted 2h 2m

Source

IsDown

Next time

Anthropic is degraded. Is your product working?

An incident on their side does not always mean an outage on yours, and the only way to know is to already be watching your own endpoints. Set that up in under a minute and you will be notified the next time your own site is affected. And there will be a next time.

50 monitors for your own websites. No card.

Affected components: api.anthropic.com, claude.ai, console.anthropic.com

What happened?

Anthropic logged two distinct incidents on 13 November 2026, affecting claude.ai, console.anthropic.com and api.anthropic.com between them. The first started at 09:58 UTC as an authentication problem for users signing into claude.ai and Claude Code. Anthropic deployed a fix by 11:05 UTC and marked the issue resolved at 11:58 UTC, a total of 2 hours 2 minutes. The second began at 13:09 UTC as degraded performance across claude.ai, the Claude API and Claude Code, and widened as the morning went on. By 14:03 UTC Anthropic's updates listed connectors including Claude Docs and Claude Sheets, Claude Security and Claude Managed Agents as also affected. Partial recovery was reported at 14:36 UTC, though Anthropic warned errors could return while work continued. By 15:33 UTC claude.ai, mobile apps, the API and Claude Code were back to normal levels, but Anthropic flagged lingering problems: new connectors could not be added, scheduled tasks and routines were running over two hours late with some runs skipped, and Claude Security scans and project setup remained delayed. The second incident closed at 15:38 UTC, 2 hours 31 minutes after it started. No user reports were filed during either window on this record. Anthropic has not published any further explanation of the cause for either incident. Over the prior 90 days Anthropic logged 46 incidents with a median duration of 1 hour 4 minutes, so both of these ran longer than typical.

Learning

UptimeRobot's own 30 day figures for Anthropic show 16 incidents with a median duration of 45 minutes, a different count and a different rhythm from Anthropic's own status history, because the two are watching different things. An external check against Anthropic's endpoints can come back green while authentication or a specific surface like connectors is broken for signed in users, since a simple reachability probe does not exercise login or the degraded code paths behind it. That is exactly the shape of both incidents here: the services answered, but some requests failed for real users. If your own monitoring only pings your front end, it will show green while your product throws authentication errors from Anthropic, and that is two different layers being watched, not a contradiction. The lesson is to treat your uptime checks and the provider's status page as separate signals that need reading together. Your monitoring covers your half, UptimeRobot now watches the provider's half too, so next time you know which side broke without guessing.

4.7
stars out of 5
284+ reviews on

Start monitoring in 30 seconds.

There's nothing to install. No credit card required. 50 monitors for free.