All models experiencing elevated errors — no ETA yet. API users should verify retry configs
Elevated errors across all models — Anthropic investigating
Original: Elevated errors across all models
Importance: 本番環境障害であり、API 利用者と Claude.ai ユーザーの両方に即座の影響を与える可能性が高い
Summary
Anthropic reported elevated errors across all Claude models starting July 29, 19:49 UTC. The company is actively investigating the incident. No specific error details, scope, or estimated recovery time were disclosed at the time of this status update. Both API users and Claude.ai end users may be affected.
Key Points
- Errors reported across all models, investigation underway
- Incident started July 29, 19:49 UTC
- No ETA or root cause disclosed yet
- Developers should verify retry logic
- Updates expected on status page
View developer notes (APIs, breaking changes, migration)
Incident status is at 'Investigating' phase. Specific cause, HTTP error codes, regional impact, model-specific effects (Claude 3.5 Sonnet vs Opus), and any automatic fallback behavior changes are not yet disclosed. Developers should verify exception handling in Claude API clients (REST/SDK), enable retry logic, and confirm webhook monitoring on production tokens.
Source: https://status.claude.com/incidents/q2kg8n613kr3
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.