llm 0.32rc2

Release: https://github.com/simonw/llm/releases/tag/0.32rc2">llm 0.32rc2

Hot on the heels of https://simonwillison.net/2026/Jul/30/llm-rc1/">RC1, this fixes a dependency issue and also adds two neat new features:

• The default model for users who have not set their own default is now https://developers.openai.com/api/docs/models/gpt-5.6-luna">GPT-5.6 Luna.

  It was previously https://developers.openai.com/api/docs/models/gpt-4o-mini">GPT-4o mini.

  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.

  You can switch back to 4o mini using llm models default gpt-4o-mini, or switch to https://developers.openai.com/api/docs/models/gpt-5-nano">GPT-5 nano, an even cheaper default model ($0.05/$0.40), using llm models default gpt-5-nano. https://github.com/simonw/llm/issues/1576">#1576



• New https://llm.datasette.io/en/latest/other-models.html#openai-endpoint">llm openai endpoint command for running prompts, chats and model listings against arbitrary OpenAI-compatible endpoints without first configuring a model.

  These calls are not logged. https://github.com/simonw/llm/issues/1565">#1565

The llm openai endpoint command is really cool.

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.

You don't even have to install LLM to use this.

Here's a uvx one-liner for running a prompt - with tools - against an https://lmstudio.ai">LM Studio local model:

uvx --pre llm openai endpoint http://127.0.0.1:1234/v1 \
  T llm_version -T llm_time --td \
  -m google/gemma-4-31b 'what is the current LLM version?
And the time?'

https://github.com/simonw/llm/pull/1568#issuecomment-5136163707">Output here.

Tags: https://simonwillison.net/tags/llm">llm, https://simonwillison.net/tags/uv">uv, https://simonwillison.net/tags/lm-studio">lm-studio