谷歌发布 Gemini Decision 1 单次调用并行千项判定Simon Willison 博客T2·基座大模型

谷歌发布 Gemini Decision 1 决策模型支持多模态

原标题：Gemini Decisions API

62AI 研判分

谷歌推出 Gemini Decision 1，正式进入决策模型赛道，与 Jev、OpenAI 形成三足鼎立。该模型 API 支持是/否、多选与评分三类问题，且是三者中唯一覆盖文本、图像、音频、视频与 PDF 的全模态方案。定价为每百万输入 token 10 美分、输出免费，与 GPT-6 Luna 持平，但仍高于 Jev 的 4.2 美分。

关联知识实体

模型Gemini Decision 1 模型Jev 模型GPT-6 Luna 术语决策模型公司谷歌

报道正文

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:

YAML

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:

JSON

{
  "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

Tags: ai, generative-ai, gemini, llm-release, jev, decision-models