Elevated error rates on Opus 4.6

What to do

• Check whether you use Anthropic claude.ai, Claude Console (platform.claude.com), Claude API (api.anthropic.com), Claude Code and 1 more. 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 9h 47m it lasted.

  Anything that failed between 2026-03-27 06:59 UTC and 2026-03-27 16:46 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 7

1. investigatingMar 27, 2026, 6:59 AM UTC

   We are currently investigating this issue.

   provider

2. investigatingMar 27, 2026, 11:04 AM UTC

   We are continuing to investigate the ongoing incident.

   provider

3. investigatingMar 27, 2026, 11:21 AM UTC

   Sonnet 4.6 is also showing elevated errors.

   provider

4. investigatingMar 27, 2026, 12:09 PM UTC

   As of 5:00 PT / 12:00 UTC Sonnet 4.6 is now healthy. We are still working to fix Opus 4.6.

   provider

5. identifiedMar 27, 2026, 1:34 PM UTC

   We have mitigated the main issue and the error rate for Opus 4.6 is hovering around 0.4% which is still high, but much better than the performance during the previous hours. We are waiting for a more permanent fix to land in the near future.

   provider

6. monitoringMar 27, 2026, 1:46 PM UTC

   As of 6:40 PT / 13:40 UTC our error rate has returned to the baseline. We are still monitoring the current situation.

   provider

7. resolvedMar 27, 2026, 4:46 PM UTC

   This incident has been mitigated as of 9:30 PT / 16:30 UTC.

   provider

Corrections

None so far.

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