Skip to content
TopicTracker
From HackerNewsView original
TranslationTranslation

Claude: Elevated Error Rates for Opus 4.8, Opus 4.7, Opus 4.6, and Sonnet 4.6

Anthropic reported elevated error rates affecting Claude models including Opus 4.8, Opus 4.7, Opus 4.6, and Sonnet 4.6. The issue has been identified and a fix is being implemented to restore normal service.

Background

- Claude is Anthropic's family of large language models (AI assistants). The "status.claude.com" page is Anthropic's official service status page, similar to what AWS or GitHub maintain. It tells users whether Claude's API and web interfaces are healthy or having problems. - This incident entry describes a current outage or degradation: certain model versions (Opus 4.8, 4.7, 4.6 and Sonnet 4.6) are experiencing "elevated error rates" — meaning users trying to use these specific models get errors (likely 5xx HTTP errors or timeouts) at a higher rate than normal. - "Opus" and "Sonnet" are model tiers: Opus is Anthropic's most capable (and expensive) model; Sonnet is the mid-tier workhorse model. The numbers (4.6, 4.7, etc.) denote specific version releases. - This matters because developers and companies rely on these models via API to power their applications; elevated error rates can mean broken chatbots, writing tools, code assistants, or automated workflows. The status page is the canonical source for whether Anthropic acknowledges a problem and is working on a fix.