llm-openai-decisions 0.1a0 插件发布：调用 OpenAI Decisions API
llm-openai-decisions 0.1a0
Simon Willison 用 GPT-6 Astra 写了个插件，把 OpenAI 新的 Decisions API 接进 llm 命令行，还能对图片做 yes/no 判断，比 Jev 贵但支持图像。
OpenAI 在 DevDay 上公布的 Jev 风格 Decisions API 正式上线。作者 Simon Willison 让 GPT-6 Astra 阅读该 API 文档，参考自己的 llm-typesafe 插件构建了 llm-openai-decisions 插件。该 API 支持 yes/no、choices、scores 三种提问类型，gpt-6-luna 模型在文本之外还支持图像输入。计费方面，OpenAI 输入为每百万 token 10 美分，Jev 为 4.2 美分，两者均只对输入收费。
llm-openai-decisions 0.1a0
Release: llm-openai-decisions 0.1a0 OpenAI released their new Jev-style Decisions API , as previously announced at last week's DevDay. Since I already have an llm-typesafe plugin for talking to Jev, I had GPT-6 Astra read the new OpenAI API documentation and build an llm-openai-decisions plugin inspired by llm-typesafe . Unlike Jev, the new gpt-6-luna decision model supports image input in addition to text. Both models charge for input it and not for output: OpenAI's is 10 cents per million input tokens, Jev's is 4.2 cents per million. Otherwise the API shape is very similar to Jev, at least conceptually. Jev supports three question types for yes/no, choices, or scores. OpenAI Decisions supports the same three types. Install the plugin like this: llm install llm-openai-decisions Here's an example query against an image attachment: llm -m openai-decisions/gpt-6-luna \ -a https://static.simonwillison.net/static/2025/two-pelicans.jpg \ -s ' Does this image contain any mammals? ' And example output: { "type" : " predicate " , "name" : " evaluation " , "probability" : 0.0 } Consult the README for full details of how to run the other types of questions. Tags: openai , llm , coding-agents , jev
