llm-anthropic 0.25

Simon Willison's Weblog

Simon Willison's Weblog2026年4月16日

llm-anthropic 0.25

5.5内容质量

TL;DR · AI 摘要

llm-anthropic 0.25 发布，新增 Claude Opus 4.7 模型支持及 thinking_effort 等新参数配置。

核心要点

新增 claude-opus-4.7 模型，支持 thinking_effort: xhigh
引入 thinking_display 和 thinking_adaptive 布尔选项
默认 max_tokens 提升至各模型允许的最大值

#LLM#Anthropic#Claude#API

打开原文

Release: llm-anthropic 0.25

[Simon Willison’s Weblog](http://simonwillison.net/)

Subscribe

Sponsored by: Honeycomb — AI agents behave unpredictably. Get the context you need to debug what actually happened. Read the blog

16th April 2026

Releasellm-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.

Posted 16th April 2026 at 8:37 pm

Recent articles

Qwen3.6-35B-A3B on my laptop drew me a better pelican than Claude Opus 4.7 - 16th April 2026
Meta's new model is Muse Spark, and meta.ai chat has some interesting tools - 8th April 2026
Anthropic's Project Glasswing - restricting Claude Mythos to security researchers - sounds necessary to me - 7th April 2026

This is a beat by Simon Willison, posted on 16th April 2026.

llm 585 anthropic 270 claude 267

Monthly briefing

Sponsor me for $10/month and get a curated email digest of the month's most important LLM developments.

Pay me to send you less!

Sponsor & subscribe