Multiple Opus-family models down simultaneously; root cause found & fix underway in 20 mins. Production services shifting to retry mode.
Elevated errors across multiple Claude models — cause identified
Original: Elevated errors for multiple models
Importance: 複数の主要モデルに対する本番APIの障害であり、稼働中のサービスに直接的な影響が生じている
Summary
Anthropic reported elevated error rates affecting multiple Claude models including Claude Mythos 5, Fable 5, Opus 5, and Opus 4.8. Investigation began at 05:06 UTC on August 24, with the root cause identified by 05:27 UTC. The company is working on a fix and promises further updates soon.
Key Points
- Simultaneous errors across Mythos 5, Fable 5, Opus 5, and other models
- Root cause identified, fix in progress
- Monitor status.claude.com for detailed updates
- ~20 minutes from initial report to root cause identification
View developer notes (APIs, breaking changes, migration)
Error rate elevation affecting Claude Mythos 5, Fable 5, Opus 5, and Opus 4.8 endpoints. Root cause identified as of 05:27 UTC August 24; fix in progress. Impact likely spans Messages API, Batch API, Vision endpoints. Developers should monitor status.claude.com for resolution updates.
Source: https://status.claude.com/incidents/vgz5psbjmt1h
Outlet: Anthropic Status
This article is an AI-generated summary (OpenAI GPT-4o-mini) of publicly available information from Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, Sakana, and other vendors. The original source URL is always provided in accordance with fair-use citation requirements. Summaries are AI-generated and may contain mistranslations or misinterpretations. Always verify details with the original source.