Elevated errors for multiple models

What to do

• Check whether you use Anthropic claude.ai, Claude API (api.anthropic.com), Claude Code, Claude Cowork. Check your stack

  Paste a package.json, lockfile, Terraform or a list of domains at down.guide/stack to see every provider you depend on.

• Confirm your retries, queues and scheduled jobs caught up after the 1h 38m it lasted.

  Anything that failed between 2026-09-22 00:57 UTC and 2026-09-22 02:35 UTC may need a replay.

• Subscribe to Anthropic's feed to hear about the next one first. RSS feed

  https://down.guide/feed?provider=anthropic works in Slack (/feed subscribe), Discord feed bots and any RSS reader.

Updates from Anthropic 5

1. investigatingSep 22, 2026, 12:57 AM UTC

   We are investigating elevated errors on requests to Claude Mythos 5.1, Claude Fable 5.1, and Claude Opus 5. We will provide an update as soon as possible.

   provider

2. identifiedSep 22, 2026, 1:17 AM UTC

   We have identified the cause of elevated errors on requests to Claude Mythos 5.1, Claude Fable 5.1, and Claude Opus 5 and are working on a fix. We will provide an update as soon as possible.

   provider

3. identifiedSep 22, 2026, 1:35 AM UTC

   We are continuing to work to resolve errors affecting some models. At this time, requests to Claude Fable 5 and 5.1 and Mythos 5 and 5.1 have returned to normal success rates. We are working to resolve remaining errors affecting Claude Opus 5, and will provide an additional update shortly.

   provider

4. monitoringSep 22, 2026, 2:11 AM UTC

   We have seen success rates return to normal across affected models, and are monitoring closely to ensure no further issues.

   provider

5. resolvedSep 22, 2026, 2:35 AM UTC

   This issue has been resolved. Impact occurred from 5:50pm PT / 00:50 UTC to 7:10pm PT / 02:10 UTC.

   provider

Corrections

None so far.

Something wrong on this page? Report an error or send us a note. Every fix is listed here.