Elevated error rate across multiple models

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 2h 25m it lasted.

  Anything that failed between 2026-06-23 14:19 UTC and 2026-06-23 16:44 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 6

1. investigatingJun 23, 2026, 2:19 PM UTC

   We are currently investigating this issue.

   provider

2. identifiedJun 23, 2026, 2:25 PM UTC

   The issue has been identified and a fix is being implemented.

   provider

3. monitoringJun 23, 2026, 2:53 PM UTC

   A fix has been implemented and we are monitoring the results.

   provider

4. monitoringJun 23, 2026, 3:28 PM UTC

   We are continuing to monitor for any further issues.

   provider

5. monitoringJun 23, 2026, 4:05 PM UTC

   We have seen error rates broadly return to normal success levels across all models. We saw elevated error rates on requests to multiple models from 7:08am PT / 14:08 UTC through 8:33am PT / 15:33 UTC.

   provider

6. resolvedJun 23, 2026, 4:44 PM 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.