Elevated error rates on requests to some models

What to do

• Check whether you use Anthropic Claude API (api.anthropic.com), Claude Code. 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 28m it lasted.

  Anything that failed between 2026-05-15 00:18 UTC and 2026-05-15 01:46 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 5

1. investigatingMay 15, 2026, 12:18 AM UTC

   We are currently investigating this issue.

   provider

2. investigatingMay 15, 2026, 12:19 AM UTC

   We are continuing to investigate this issue.

   provider

3. identifiedMay 15, 2026, 1:06 AM UTC

   We are currently working to resolve issues affecting requests to Claude Opus and Sonnet 4.6, though success rates for Opus 4.7 have returned to normal.

   provider

4. identifiedMay 15, 2026, 1:26 AM UTC

   We are working to resolve errors impacting Claude Opus 4.6, and have seen both Sonnet 4.6 and Opus 4.7 return to normal success rates.

   provider

5. resolvedMay 15, 2026, 1:46 AM UTC

   This incident 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.