Google 推出 Gemini Decision 1 决策模型 API

Gemini Decisions API

AI 导读

Google 推出决策模型 Gemini Decision 1 API，进入与 Jev 和 OpenAI 竞争的决策模型品类，支持是非题、多选题和标准评分。该模型全面支持文本、图像、音频、视频及 PDF 等多模态输入，输入定价为每百万 token 0.10 美元且输出免费。在实测视频的是非问答中，与 Jev 和 OpenAI 直接输出 1.0 或 0.0 不同，Gemini 会给出具体的概率数值。

推荐理由

原文对比了 Gemini 与 OpenAI 及 Jev 在全多模态支持、Token 定价以及是非题概率输出形式上的具体差异，便于评估决策模型选型。

正文 · 原文

11th November 2026 - Link Blog

Gemini Decisions API (via) 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.

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.

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.

I tested it against video by passing these questions to it along with my Yonkers stomping robot video file:

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:

{
  "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
  }
}