Elevated errors on requests to Claude models

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 21m it lasted.

  Anything that failed between 2026-04-10 16:30 UTC and 2026-04-10 16:51 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 10, 2026, 4:30 PM UTC

   We are investigating reports of elevated errors on requests to Claude across all products. We will provide an update as soon as possible.

   provider

2. identifiedApr 10, 2026, 4:42 PM UTC

   We have identified the current issue as affecting requests to models other than Claude Opus 4.6, and are working to fully resolve this issue. We will provide additional updates shortly.

   provider

3. resolvedApr 10, 2026, 4:51 PM UTC

   The issue affecting requests to non-Opus models has been resolved.

   provider

Corrections

None so far.

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