llm-openai-decisions 0.1a0：让 GPT-6 Astra 读 OpenAI Decisions API 文档生成 LLM 插件——gpt-6-luna 决策模型支持图像输入、只按输入计费 $0.10/M，对比 Jev 的 $0.042/M
llm-openai-decisions 0.1a0
评分 55
导读
OpenAI 发布 DevDay 预告过的 Jev 式 Decisions API。作者仿自己的 llm-typesafe（对接 Jev）让 GPT-6 Astra 读新 API 文档构建出 llm-openai-decisions 插件：与 Jev 同样支持 yes/no、choices、scores 三种题型；不同点是 gpt-6-luna 决策模型除文本外还支持图像输入。两家都只对输入计费——OpenAI 每百万输入 token 十美分，Jev 四点二美分。示例对一张鹈鹕照片问“图里有哺乳动物吗”，得 probability 0.0。
主体与标签
#教程/实操#定价/成本#API/工具
正文
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-decisionsHere'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?'{"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