llm 0.32rc2
- ID
- 9290
- Status
- summarized
- Published
- 31 Jul 2026, 6:52 AM
- Fetched
- 31 Jul 2026, 8:44 AM
- Provider
- Simon Willison
- Category
- developer-ai
- Original URL
- https://simonwillison.net/2026/Jul/30/llm-rc2/
- Source URL
- https://simonwillison.net/atom/everything/
Summary
- Score
- 7.0
- Created
- 31 Jul 2026, 4:28 PM
- Tags
- Audience
- developersvibe_codersai_ml_learnersai_agent_users
What happened
Simon Willison's `llm` CLI tool hits 0.32rc2, changing the default model from GPT-4o mini to GPT-5.6 Luna ($0.20/$1.20 per million input/output tokens vs $0.15/$0.60 for 4o mini). It also adds `llm openai endpoint`, a command for running prompts, chats, and model listings against any OpenAI-compatible endpoint without prior configuration, runnable via `uvx` without installing llm.
Why it matters
If you use `llm` as your daily CLI, your default model just changed and your token costs went up slightly—run `llm models default gpt-4o-mini` or `gpt-5-nano` ($0.05/$0.40) if you want cheaper defaults. The new `llm openai endpoint` command is immediately useful for testing prompts against local models (e.g., LM Studio at 127.0.0.1:1234) or any OpenAI-compatible API without setup, which is handy for Malaysian developers experimenting with self-hosted or regional LLM endpoints.
Discussion angle
Try the `uvx --pre llm openai endpoint` one-liner live against a local LM Studio model to show how quickly you can test prompts and tools against self-hosted models without any configuration overhead.