Anthropic Claude Opus and Sonnet 4.x Models Hit Elevated Error Rates
June 21, 2026
Anthropic reported elevated error rates across Claude Opus 4.8, 4.7, 4.6, and Sonnet 4.6 on June 22, 2026, affecting claude.ai, the Claude API, Claude Code, and Claude Cowork simultaneously. No resolution or root cause was published at time of report.
HOW THIS AFFECTS YOU
●
builderIf you depend on any of these Claude model versions in production, expect degraded reliability and plan for fallback routing or retry logic until Anthropic posts a resolution.