LLM 0.32rc2: New default model GPT-5.6 Luna and openai endpoint command

LLM 0.32rc2, released July 30, 2026, fixes a dependency issue and adds two features. The default model for users without a custom default is now GPT-5.6 Luna, replacing GPT-4o mini. Luna costs $0.20 per million input tokens and $1.20 per million output tokens, compared to $0.15/$0.60 for GPT-4o mini. Users can switch back to GPT-4o mini or choose GPT-5 nano ($0.05/$0.40) via commands. The new `llm openai endpoint` command enables running prompts, chats, and model listings against any OpenAI-compatible endpoint without prior model configuration, and these calls are not logged. The feature was added due to the lack of a CLI tool for testing prompts against arbitrary OpenAI Chat Completions imitation endpoints. It can be used via a uvx one-liner, e.g., with LM Studio local model.