Dev.to Machine Learning7h ago|Products & ServicesTutorials & How-To

llm-anthropic 0.25 Adds Opus 4.7 with xhigh Thinking Effort

The llm-anthropic CLI tool has been updated to version 0.25, adding support for the new Claude Opus 4.7 model with an 'xhigh' thinking effort setting for complex coding tasks.

đź’ˇ

Why it matters

This update gives developers direct access to Claude's most powerful reasoning abilities through a simple CLI tool, enabling them to tackle their most challenging coding tasks.

Key Points

  • 1New Claude Opus 4.7 model with 'xhigh' thinking effort setting
  • 2Added 'thinking_display' and 'thinking_adaptive' flags for better control
  • 3Increased default 'max_tokens' to the maximum allowed for each model
  • 4Removed obsolete 'structured-outputs-2025-11-13' beta header

Details

The llm-anthropic tool, which allows developers to run Anthropic's Claude language models locally, has been updated to version 0.25. The key change is the addition of the new Claude Opus 4.7 model, which introduces a new 'xhigh' thinking effort setting. This setting enables Claude's deepest reasoning capabilities, allowing it to tackle the most complex coding problems such as refactoring, debugging, and system design. The update also includes new flags like 'thinking_display' and 'thinking_adaptive' to provide more control over the model's behavior. Additionally, the default 'max_tokens' value has been increased to the maximum allowed for each model, and an obsolete beta header has been removed.

Like
Save
Read original
Cached
Comments
?

No comments yet

Be the first to comment

AI Curator - Daily AI News Curation

AI Curator

Your AI news assistant

Ask me anything about AI

I can help you understand AI news, trends, and technologies