---
title: "LLM 0.32rc2 发布：默认模型升级为 GPT-5.6 Luna，新增 OpenAI 兼容端点命令"
source: "Simon Willison 博客（Atom）"
source_tier: "t2"
url: "https://simonwillison.net/2026/Jul/30/llm-rc2/#atom-everything"
permalink: "https://feed.astralor.com/items/itm_d650f98337e042a320b071d9"
published: "2026-07-30T22:52:06.000Z"
score: 78
channel: "ai"
tags: ["CLI工具","GPT-5.6 Luna","LLM","LM Studio","OpenAI","uv"]
---

# LLM 0.32rc2 发布：默认模型升级为 GPT-5.6 Luna，新增 OpenAI 兼容端点命令

## AI 点评

> 本次更新最亮眼的是 `llm openai endpoint` 命令，它让开发者无需安装完整工具即可快速测试任意兼容端点，对经常调试本地模型或第三方服务的 AI 工程师来说非常实用。默认模型的升级也值得关注，Luna 性价比不错。

## 速览

Simon Willison 发布 llm 0.32rc2，修复依赖问题并带来两项新特性：未设置默认模型的用户将自动使用 GPT-5.6 Luna（价格稍高但性能更强），同时新增 `llm openai endpoint` 命令，允许直接对任意兼容 OpenAI 的端点运行提示、聊天和模型列表查询，无需预先配置模型。该命令无需安装 llm，可通过 uvx 一键执行，极大方便了开发者调试本地或第三方模型。

## 关键点

- 默认模型从 GPT-4o mini 切换为 GPT-5.6 Luna，价格分别为 $0.20/M 输入、$1.20/M 输出。
- 新增 `llm openai endpoint` 命令，可直接调用任意兼容 OpenAI 的 API 端点。
- 该命令无需安装 LLM，可通过 `uvx --pre llm openai endpoint` 一键运行。
- 修复了 rc1 的依赖问题，提升了稳定性。

## 全文

Release: llm 0.32rc2 Hot on the heels of 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 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, or switch to GPT-5 nano, an even cheaper default model ($0.05/$0.40), using llm models default gpt-5-nano. #1576 New 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 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 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?' Output here. Tags: llm, uv, lm-studio

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_d650f98337e042a320b071d9