# Elevated errors for some models

- Provider: [Anthropic](https://down.guide/providers/anthropic)
- Confidence: Confirmed
- Impact: Partial outage
- lasted 3h 44m
- started 2026-07-07 20:02 UTC
- claude.ai, Claude API (api.anthropic.com), Claude Code +1
- id: DWN-3ab81bd06c
- Official page: https://stspg.io/sv3shhq5lpd3

## Updates from Anthropic
### 2026-07-07 20:02 UTC: investigating
We are investigating elevated errors on requests to some models. We will provide an update as soon as possible.

### 2026-07-07 20:28 UTC: identified
We have seen success rates return to normal, but we are continuing to work to fully resolve this issue and ensure no further recurrences.

### 2026-07-07 21:47 UTC: identified
We are continuing to work to resolve an issue resulting in elevated errors on requests to some models, primarily Claude Fable 5. We will provide an additional update as soon as possible.

### 2026-07-07 23:19 UTC: monitoring
We are continuing to monitor issues affecting requests to some models, and have once again seen success rates return to normal. We are working to ensure there are no further issues, and will provide an additional update shortly.

### 2026-07-07 23:46 UTC: resolved
This issue has been resolved.

From the builder: does your app depend on Anthropic? [Sazabi](https://www.sazabi.com/?utm_source=down-guide&utm_medium=markdown&utm_content=anthropic) detects problems in your own logs without hand-written monitors, and you can ask it in plain language which errors mention Anthropic.

---
down.guide reads providers' official status pages every minute and adds its own evidence, always labeled. Free, no account. Agents: MCP at https://down.guide/mcp, REST at https://down.guide/api/v1, feeds at https://down.guide/feed. Built by [Sazabi](https://www.sazabi.com/?utm_source=down-guide&utm_medium=markdown&utm_content=DWN-3ab81bd06c), AI-native observability and security: automatic issue detection, plain-language log search and live dashboards.