{"slug": "llm-0-32rc2", "title": "llm 0.32rc2", "summary": "LLM 0.32rc2 fixes a dependency issue and adds two features: the default model for users without a custom default is now GPT-5.6 Luna ($0.20/M input, $1.20/M output), and a new `llm openai endpoint` command lets users run prompts against arbitrary OpenAI-compatible endpoints without prior configuration. The release is available on GitHub.", "body_md": "**Release:** [llm 0.32rc2](https://github.com/simonw/llm/releases/tag/0.32rc2)\n\nHot on the heels of [RC1](https://simonwillison.net/2026/Jul/30/llm-rc1/), this fixes a dependency issue and also adds two neat new features:\n\n- The default model for users who have not set their own default is now\n[GPT-5.6 Luna]. It was previously[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`\n\n, or switch to[GPT-5 nano], an even cheaper default model ($0.05/$0.40), using`llm models default gpt-5-nano`\n\n.[#1576]- New\n[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.[#1565]\n\nThe `llm openai endpoint`\n\ncommand 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.\n\nYou don't even have to install LLM to use this. Here's a `uvx`\n\none-liner for running a prompt - with tools - against an [LM Studio](https://lmstudio.ai) local model:\n\n```\nuvx --pre llm openai endpoint http://127.0.0.1:1234/v1 \\\n  T llm_version -T llm_time --td \\\n  -m google/gemma-4-31b 'what is the current LLM version? And the time?'\n```\n\n", "url": "https://wpnews.pro/news/llm-0-32rc2", "canonical_source": "https://simonwillison.net/2026/Jul/30/llm-rc2/#atom-everything", "published_at": "2026-07-30 22:52:06+00:00", "updated_at": "2026-07-31 00:27:18.206340+00:00", "lang": "en", "topics": ["developer-tools", "large-language-models", "ai-tools"], "entities": ["LLM", "GPT-5.6 Luna", "GPT-4o mini", "GPT-5 nano", "OpenAI", "LM Studio", "Simon Willison"], "alternates": {"html": "https://wpnews.pro/news/llm-0-32rc2", "markdown": "https://wpnews.pro/news/llm-0-32rc2.md", "text": "https://wpnews.pro/news/llm-0-32rc2.txt", "jsonld": "https://wpnews.pro/news/llm-0-32rc2.jsonld"}}