llm-openai-decisions 插件发布:接入 OpenAI Decisions API
Simon Willison 发布了 LLM 插件 llm-openai-decisions 0.1a0,用于调用 OpenAI 上周 DevDay 宣布的 Jev 式 Decisions API;他让 GPT-6 Astra 阅读新 API 文档,仿照已有的 llm-typesafe(对应 Jev)完成开发。新决策模型 gpt-6-luna 除文本外还支持图像输入。据文中描述,两个模型都只按输入计费、不计输出,OpenAI 为每百万输入 token 10 美分,Jev 为 4.2 美分;API 均支持是/否、选项和打分三类问题。
为什么重要:这类“只按输入计费”的决策接口,让开发者能以较低成本从模型获得结构化的判断结果,而不是生成长文本。
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.
前因后果
- OpenAI强化训练监控:可即时叫停模型联网异常Simon Willison's Weblog · OpenAI
- llm-mistral 0.16 支持推理模型Simon Willison's Weblog · LLM
- 辛顿提议为AI设立FDA式审批IT之家 AI · OpenAI
- 《Artificial》讽刺OpenAI与人工智能竞赛WIRED AI · OpenAI
- Altman:AI监管应容忍部分坏事TechSpot · OpenAI
- Personal AI争夺下一代个人入口虎嗅 AI · OpenAI