Skip to main content
Original: Simon Willison · 16/04/2026

​
Summary

The release of llm-anthropic 0.25 introduces new features including the claude-opus-4.7 model and enhanced output options for improved user experience.

​
Key Insights

“New model: claude-opus-4.7, which supports thinking_effort: xhigh.” — Introduction of the new model in the release announcement.
“Increased default max_tokens to the maximum allowed for each model.” — Details about the enhancements made in the release.
“thinking_display summarized output is currently only available in JSON output or JSON logs.” — Information on the new output options available.

​
Topics

​
Full Article

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.

Release: llm-anthropic 0.25.1

Simon Willison · reference · 81% similar

Release: llm 0.32a2

Simon Willison · reference · 68% similar

Claude Opus 4.8: “a modest but tangible improvement”

Simon Willison · explanation · 65% similar
Originally published at https://simonwillison.net/2026/Apr/16/llm-anthropic/#atom-everything.