AI BriefingLLM CLI tool 0.32rc2 update
·2026.07.31 07:52
Key point
The default model for the LLM CLI tool has changed to GPT-5.6 Luna, and support for OpenAI-compatible endpoints has been added.
Details
Simon Willison's llm CLI tool has been updated to version 0.32rc2.
The key changes are as follows:
- Default model change: The default model for users who haven't set a specific configuration has changed from the previous GPT-4o mini to GPT-5.6 Luna. The Luna model costs $0.20 per 1 million input tokens and $1.20 per 1 million output tokens.
- OpenAI-compatible endpoint support: The
llm openai endpointcommand has been added, allowing prompt execution, chat, and model listing against any OpenAI-compatible endpoint without separate model configuration. - Local model usage: This feature enables immediate testing of models using local servers such as LM Studio without any additional installation.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Foremerge v0.5.0 Released: Rust-Based Open-Source Tool Detects Intent Conflicts Between Parallel AI Coding Agents