发布：llm-openai-decisions 0.1a0

OpenAI 推出了新的 Jev 风格 Decisions API，正如此前在上周 DevDay 上宣布的一样。

由于我已经有一个可与 Jev 通信的 llm-typesafe 插件，我让 GPT-6 Astra 阅读了新的 OpenAI API 文档，并参考 llm-typesafe 构建了一个 llm-openai-decisions 插件。

与 Jev 不同，新的 gpt-6-luna 决策模型除了文本外还支持图像输入。两个模型都只对输入收费，不对输出收费：OpenAI 的价格是每百万输入 token 10 美分，Jev 的价格是每百万输入 token 4.2 美分。

除此之外，API 的形式与 Jev 在概念上非常相似。Jev 支持三种问题类型：是/否、选项选择或评分。OpenAI Decisions 也支持相同的三种类型。

按如下方式安装该插件：

llm install llm-openai-decisions

以下是一个针对图像附件的查询示例：

llm -m openai-decisions/gpt-6-luna \
  -a https://static.simonwillison.net/static/2025/two-pelicans.jpg \
  -s 'Does this image contain any mammals?'

示例输出：

{"type": "predicate", "name": "evaluation", "probability": 0.0}

有关如何运行其他类型问题的完整说明，请参阅 README。

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.