Key Points

The llm-anthropic 0.25 release adds the new Anthropic model `claude-opus-4.7` with an increased capability to control reasoning via `thinking_effort: xhigh`.
It introduces new boolean options, `thinking_display` and `thinking_adaptive`, with `thinking_display` currently available only when using JSON output or JSON logs.
The integration raises the default `max_tokens` setting to the maximum allowed for each Anthropic model, expanding default generation length.
It removes reliance on the obsolete `structured-outputs-2025-11-13` beta header for older models to improve compatibility and cleanup legacy behavior.

Simon Willison’s Weblog

Sponsored by: Teleport — Connect agents to your infra in seconds with Teleport Beams. Built-in identity. Zero secrets. Get early access

16th April 2026

Release llm-anthropic 0.25 — LLM access to models by Anthropic, including the Claude series

New model: claude-opus-4.7, which supports thinking_effort: xhigh. #66

New thinking_display and thinking_adaptive boolean options. thinking_display summarized output is currently only available in JSON output or JSON logs.

Increased default max_tokens to the maximum allowed for each model.

No longer uses obsolete structured-outputs-2025-11-13 beta header for older models.