We've launched Claude Opus 4.8 (claude-opus-4-8), our most capable generally available model. Claude Opus 4.8 supports a 1M token context window by default, 128k max output tokens, and the same set of
We've launched Claude Opus 4.8 (claude-opus-4-8), our most capable generally available model. Claude Opus 4.8 supports a 1M token context window by default, 128k max output tokens, and the same set of tools and platform features as Claude Opus 4.7. See What's new in Claude Opus 4.8 for capability improvements, new features, and migration guidance.
출처: Claude Platform 릴리스 노트 (원문 보기)
With adaptive thinking enabled, Claude Opus 4.8 triggers reasoning only when a turn needs it, reducing wasted thinking tokens compared to Claude Opus 4.7 at the same effort level.
The stop_details field on refusal responses is now publicly documented; it returns a category (cyber, bio, or null) and a human-readable explanation, so your application can route different classes of
On the Claude API, you are no longer billed for a request when it returns stop_reason: "refusal" without Claude having generated any output. See Streaming refusals for detecting and handling refusals.
The advisor tool now supports a max_tokens parameter to cap the advisor model's output per call, reducing latency and output token cost for workloads that don't need full-length advisor responses. Set
Join the community to share tips with other users, or explore more guides.