Elevated error rates on Claude Opus 4.7

What to do

• Check whether you use Anthropic claude.ai, Claude Console (platform.claude.com), Claude API (api.anthropic.com), Claude Code and 2 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 59m it lasted.

  Anything that failed between 2026-04-25 01:35 UTC and 2026-04-25 02:34 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 3

1. investigatingApr 25, 2026, 1:35 AM UTC

   We are investigating elevated errors for requests to Claude Opus 4.7. We will provide an update as soon as possible.

   provider

2. monitoringApr 25, 2026, 2:15 AM UTC

   A fix has been deployed for Claude Opus 4.7 and we are seeing success rates at normal levels. We are continuing to monitor, and ensure no further recurrence.

   provider

3. resolvedApr 25, 2026, 2:34 AM UTC

   The issue affecting requests to Claude Opus 4.7 has been resolved. Impact occurred from 01:24–01:59 UTC.

   provider

Corrections

None so far.

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