Intel / article

Release: llm 0.32rc2

Source: simonwillison.net
Author: Simon Willison
Date: Published Jul 30, 2026

Why it matters

The new ` openai endpoint` command lets you point the CLI at any OpenAI-compatible API—including local servers like LM Studio—for one-off prompts and model listings without editing config files first, making it faster to sanity-check local or third-party endpoints.

Terms in this piece · Glossary

LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.

Key quotes

“Luna is a much better and more recent model, albeit slightly more expensive - $0.20 per million input tokens and $1.20 per million output tokens, compared to $0.15/$0.60 for 4o mini.”

“New llm openai endpoint command for running prompts, chats and model listings against arbitrary OpenAI-compatible endpoints without first configuring a model.”

“I got frustrated at the lack of an obvious CLI tool for trying out prompts against arbitrary OpenAI Chat Completions imitation endpoints, so I decided to add that to LLM itself.”

Read the source simonwillison.net