Google发布Gemini Decision 1决策模型API
Gemini Decisions API
决策模型是近期热点，Gemini Decision 1补齐了多模态短板，定价策略明确，开发者可直接对比选型。
Gemini Decisions API
Google join Jev and OpenAI in the decision model category with "Gemini Decision 1". This new model API is almost identical to Jev: it supports the same three types of questions (yes/no, choice, and rubric-scoring) and even reuses Jev's term "Noul" for a yes/no question.
Google 加入 Jev 和 OpenAI，在决策模型类别中推出“Gemini Decision 1”。这个新的模型 API 与 Jev 几乎完全相同：它支持相同的三种问题类型（是/否、选择项和评分量表），甚至复用了 Jev 对是/否问题的术语“Noul”。
It's priced the same as the GPT-6 Luna decision model: 10 cents per million input tokens, and output is free. Jev remains the cheapest of the three, at 4.2 cents per million.
它的定价与 GPT-6 Luna 决策模型相同：每百万输入 token 10 美分，输出免费。Jev 仍然是三者中最便宜的，每百万 token 4.2 美分。
Jev is text (and JSON) only. OpenAI can handle text and images. Gemini Decision 1 is fully multi-model: it covers text, images, audio, video, and PDFs.
Jev 仅支持文本（和 JSON）。OpenAI 可以处理文本和图片。Gemini Decision 1 是完全多模态的：涵盖文本、图片、音频、视频和 PDF。
I tested it against video by passing these questions to it along with my Yonkers stomping robot video file:
我通过将以下问题连同我的 Yonkers stomping robot 视频文件一起传入，对其进行了视频测试：
dragon: Does this video have a dragon in it?
robot: Does this video have a robot in it?
france: Is this video set in France?
usa: Is this video set in the USA?Jev and OpenAI both return 1.0 or 0.0 for yes/no questions, but Gemini insists on being a little less confident than that:
Jev 和 OpenAI 对于是/否问题都会返回 1.0 或 0.0，但 Gemini 坚持表现得稍微不那么确定：
{
"dragon": {
"type": "yes_no",
"probability": 0.04976021841520312
},
"robot": {
"type": "yes_no",
"probability": 0.9234055387792485
},
"france": {
"type": "yes_no",
"probability": 0.08329171353166241
},
"usa": {
"type": "yes_no",
"probability": 0.9230459995157706
}
}Via Hacker News
来源：Hacker News
Tags: ai, generative-ai, gemini, llm-release, jev, decision-models
标签：ai, generative-ai, gemini, llm-release, jev, decision-models
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力