Elevated errors on many Claude models

What to do

• Check whether your product depends on Anthropic. 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 3h 9m it lasted.

  Anything that failed between 2026-06-05 15:19 UTC and 2026-06-05 18:28 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 5, 2026, 3:19 PM UTC

   We are currently investigating this issue.

   provider

2. identifiedJun 5, 2026, 3:43 PM UTC

   We have identified the issue and we are working to mitigate the issue. Current ongoing issues with frontier models are with Opus 4.7 and Opus 4.8 and other models have recovered.

   provider

3. identifiedJun 5, 2026, 4:46 PM UTC

   We are continuing to work to resolve issues affecting success rates on Opus 4.7 and 4.8, and will provide additional updates as soon as possible.

   provider

4. monitoringJun 5, 2026, 5:13 PM UTC

   Success rates across all models have returned to expected levels. We are continuing to monitor closely to ensure no further issues will recur.

   provider

5. monitoringJun 5, 2026, 6:27 PM UTC

   The incident started at 8:08 PT / 15:08 UTC. Recovery times per model were: Opus 4.6 - 8:25 PT / 15:25 UTC Sonnet 4.6 — 9:23 PT / 16:23 UTC Opus 4.8 — 9:59 PT / 16:59 UTC Opus 4.7 — 10:12 PT / 17:12 UTC Opus 4.5 — 10:29 PT / 17:29 UTC All models have now fully recovered.

   provider

6. resolvedJun 5, 2026, 6:28 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.