Anthropic: Elevated errors on Claude Sonnet 4.6 and Opus 4.8

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 3m it lasted.
Anything that failed between 2026-06-17 00:47 UTC and 2026-06-17 02:50 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.

investigatingJun 17, 2026, 12:47 AM UTC
We are currently investigating this issue.
provider
identifiedJun 17, 2026, 1:52 AM UTC
At this time, success rates for Claude Sonnet 4.6 have recovered and we are working to resolve an issue resulting in elevated errors on Opus 4.8. We will provide additional updates as soon as possible.
provider
resolvedJun 17, 2026, 2:50 AM UTC
This incident has been resolved.
provider

Reports count in aggregate; nothing about you is shown.

None so far.

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

Is Anthropic still down?

No, this incident was resolved 2026-06-17 02:50 UTC. For Anthropic's live state, see https://down.guide/anthropic.

How long did it last?

2h 3m, from 2026-06-17 00:47 UTC to 2026-06-17 02:50 UTC, by the times Anthropic posted.

What was affected?

Anthropic named claude.ai, Claude Console (platform.claude.com), Claude API (api.anthropic.com), Claude Code and 1 more.

What caused it?

Anthropic hasn't published a root cause. If it does, it shows here.

Where does this come from?

Anthropic's official status page, https://status.claude.com, quoted verbatim. down.guide's own probes, reports and social counts are labeled as ours.