Simon Willison first-party · 5d ago · 2/5
llm-anthropic 0.25 ↗
Simon Willison released llm-anthropic version 0.25, introducing Claude Opus 4.7 with support for xhigh thinking_effort levels. The update adds thinking_display and thinking_adaptive boolean options, with summarized thinking output available in JSON formats, and increases default max_tokens to model maximums. The release also removes deprecated structured-outputs beta headers for older models.
claude-opus-4.7, which supports thinking_effort: xhigh