Simon Willison Unveils llm-anthropic 0.25 with Powerful New Claude Opus 4.7 Integration

product #llm 📝 Blog|Analyzed: Apr 16, 2026 22:55•

Published: Apr 16, 2026 20:37

•

1 min read

•Simon Willison

Analysis

Simon Willison's latest release of the llm-anthropic plugin is a massive win for developers working with Anthropic's models. The introduction of the cutting-edge claude-opus-4.7 model brings incredible new capabilities, including an extended 'xhigh' reasoning effort setting. Combined with new adaptive thinking features and maximized token limits, this update empowers creators to build far more sophisticated Large Language Model (LLM) applications than ever before.

Key Takeaways

•The update introduces the advanced claude-opus-4.7 model with a massive new 'xhigh' reasoning capability.
•New boolean options for thinking_display and thinking_adaptive allow for dynamic and interactive Chain of Thought experiences.
•Default max tokens have been increased to the absolute maximum allowed for each model, vastly expanding the Context Window.

Reference / Citation

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

S

Simon WillisonApr 16, 2026 20:37

* Cited for critical analysis under Article 32.

Revolutionizing Data Clustering: A New Joint Manifold Learning Framework

Local Large Language Model (LLM) Triumphs: Qwen 3.6 Outperforms Claude Opus 4.7 in Creative SVG Benchmark

Related Analysis

Zero Human Coding: OpenAI's Frontier Team Builds Million-Line System Entirely with Agents!

Apr 17, 2026 08:14

Intel Launches Core Series 3: Bringing Powerful AI PCs to Budget-Friendly Prices

Apr 17, 2026 08:53

Revolutionizing Automation: How AI Agents Masterfully Control Our Computers

Apr 17, 2026 09:00

Source: Simon Willison