Companies / Anthropic / incidents
Anthropic: Elevated errors across all models
Anthropic reported a critical incident involving elevated errors across all models, affecting claude.ai, Claude API (api.anthropic.com), Claude Code and Claude Cowork. The incident started at 2026-07-29 19:49 UTC and was resolved at 2026-07-29 22:36 UTC, lasting 2 h 46 min; Anthropic reported recovery in success rates across all models.
Machine-written from the archived incident (Sol). Check the timeline before relying on it.
Affected components: Claude CoworkClaude API (api.anthropic.com)claude.aiClaude Code
Timeline of updates
- investigating
We are currently investigating this issue.
- identified
We have identified an issue resulting in elevated errors across multiple models, and are working to resolve this. We will provide an update as soon as possible.
- identified
We are continuing to work to fully resolve issues resulting in elevated requests and latency to Claude models. At this time, we are seeing recovery across most models. We will provide an additional update as soon as possible.
- monitoring
From 12:45 PT / 19:45 UTC through to 1:26 PT / 21:26 UTC, we saw elevated rates of errors across Claude models. We have seen recovery in success rates across all models and are monitoring closely to ensure no further issues.
- resolved
This issue has been resolved.
Rewindex changes for this incident
- Critical incident: Elevated errors across all models 2026-07-29 19:49 UTC
Impact, status and times are the vendor’s own, as last archived. View on stspg.io (opens in new tab). Anthropic profile · Recent Anthropic incidents · Markdown · JSON