Simon Willison's Weblog

Gemini Decisions API

8.5内容质量

TL;DR · AI 摘要

Google推出Gemini Decision 1决策模型，支持多模态输入，价格与GPT-6 Luna相当，但比Jev贵。

核心要点

  • Gemini Decision 1定价10美分/百万输入令牌，Jev仅需4.2美分，为最便宜决策模型
  • Gemini支持文本/图像/音频/视频/PDF多模态输入，Jev和OpenAI仅支持文本
  • 视频测试显示Gemini输出概率值（如0.923），而竞品仅返回0.0或1.0

结构提纲

按章节快速跳转。

  1. §Gemini Decision 1发布

    介绍Google新推出的决策模型及其市场定位

  2. ·功能对比

    与Jev、OpenAI决策模型在输入类型和定价方面的差异

  3. ›多模态能力

    Gemini支持视频分析等多模态输入，输出概率值而非二值判断

  4. ·定价策略

    10美分/百万输入令牌，与GPT-6 Luna持平但高于Jev

  5. ›测试案例

    使用Yonkers机器人视频验证模型对视频内容的识别能力

思维导图

用一张图看清主题之间的关系。

查看大纲文本（无障碍 / 无 JS 友好）
  • Gemini Decision 1
    • 功能特性
      • 多模态支持（文本/图像/视频等）
      • 概率输出（0.0-1.0）
    • 市场定位
      • 定价：10美分/百万输入
      • 竞品对比：比Jev贵但功能更强

金句 / Highlights

值得收藏与分享的关键句。

  • Gemini Decision 1支持文本、图像、音频、视频和PDF的多模态输入，显著优于仅支持文本的Jev和OpenAI

    — 第3段

    ⬇︎ 下载 PNG𝕏 分享到 X
  • 在视频分析测试中，Gemini输出概率值（如robot:0.923），而Jev和OpenAI仅返回0.0或1.0

    — 代码块测试结果

    ⬇︎ 下载 PNG𝕏 分享到 X
  • Jev以4.2美分/百万输入令牌的价格成为目前最经济的决策模型

    — 第2段

    ⬇︎ 下载 PNG𝕏 分享到 X
#Gemini#决策模型#AI#多模态#模型对比
打开原文

Gemini Decisions API

Simon Willison’s Weblog

Newsletter

#smallhead

Sponsored by:

doubleAI — doubleAI’s Maxwell makes software faster as it runs, no code changes needed.

Now in early access

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:

code
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:

code
{
"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
}
}

Posted

11th November 2026

at 10:03 pm

Recent articles

  • Locating the source of a mysterious beep with Claude - 9th November 2026
  • Hide your slop PR descriptions behind <details><summary> - 9th November 2026
  • Qwen 3.8 27B on my laptop can interpret model weights, too - 3rd November 2026
  • The U.S. Census Bureau and “Super Intelligence” - 2nd November 2026

#primary

This is a link post by Simon Willison, posted on 11th November 2026 .

ai

2,321

generative-ai

2,060

gemini

202

llm-release

242

jev

4

decision-models

Monthly briefing

Sponsor me for $10/month and get a curated email digest of the month's most important LLM developments.

Pay me to send you less!

Sponsor & subscribe

.metabox

#secondary

#wrapper

  • Disclosures
  • Colophon
  • ©
  • 2002
  • 2003
  • 2004
  • 2005
  • 2006
  • 2007
  • 2008
  • 2009
  • 2010
  • 2011
  • 2012
  • 2013
  • 2014
  • 2015
  • 2016
  • 2017
  • 2018
  • 2019
  • 2020
  • 2021
  • 2022
  • 2023
  • 2024
  • 2025
  • 2026