# Degraded performance for multiple models

- Provider: [Anthropic](https://down.guide/providers/anthropic)
- Confidence: Confirmed
- Impact: Degraded
- lasted 2h 41m
- started 2026-08-18 16:20 UTC
- claude.ai, Claude API (api.anthropic.com), Claude Code +1
- Anthropic states the impact was 2026-08-18 16:11 to 18:23 UTC (2h 12m)
- id: DWN-9492a0febd
- Official page: https://stspg.io/tcsfmtc03xgm

## Updates from Anthropic
### 2026-08-18 16:20 UTC: investigating
We are investigating reports of degraded performance affecting multiple models. We will provide an update as soon as possible.

### 2026-08-18 16:20 UTC: investigating
We are investigating elevated errors on requests to Claude Mythos 5, Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Haiku 4.5, and other Claude models. We will provide an update as soon as possible.

### 2026-08-18 17:12 UTC: investigating
We are investigating elevated errors on requests to Claude Opus 5. We will provide an update as soon as possible.

### 2026-08-18 18:26 UTC: monitoring
A fix has been implemented and we are monitoring the results.

### 2026-08-18 19:01 UTC: resolved
The issue affecting Claude Opus 5 has been resolved. Impact occurred from 16:11 to 18:23 UTC.

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-9492a0febd), AI-native observability and security: automatic issue detection, plain-language log search and live dashboards.