Degraded performance for multiple models

What to do

• Check whether you use Anthropic claude.ai, Claude API (api.anthropic.com), Claude Code, Claude Cowork. 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 4h 17m it lasted.

  Anything that failed between 2026-08-12 13:50 UTC and 2026-08-12 18:07 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 4

1. investigatingAug 12, 2026, 1:50 PM UTC

   We are investigating elevated errors on requests to multiple models. We will provide an update as soon as possible.

   provider

2. identifiedAug 12, 2026, 4:10 PM UTC

   We have identified an issue which resulted in errors across multiple models. At this time, errors are primarily impacting Claude Fable 5 and we are working to fully resolve these issues.

   provider

3. identifiedAug 12, 2026, 5:28 PM UTC

   We are continuing to work to resolve an issue resulting in slightly elevated errors on requests to Claude Fable 5. We will provide an update as soon as possible.

   provider

4. resolvedAug 12, 2026, 6:07 PM UTC

   This issue 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.