Google 发布 Gemini Decisions API 与 Gemini Decision 1 模型
Today we’re launching the Gemini Decisions API, powered by our new Gemini Decision 1 model in @GoogleAIStudio.
Google 发布 Gemini Decisions API，由新模型 Gemini Decision 1 驱动，已在 GoogleAIStudio 上线。该模型不做逐 token 文本生成，而是对最多 1,000 道题做封闭集选择打分，单次可处理文本、图像、音频、视频和 PDF。支持是/否、最多 255 个选项的多选题和评分量表三种决策类型，输入定价 $0.10/1M tokens、输出 token 不计费，约为 Flash-Lite 的 5 倍便宜，并在多项基准评测中领先且校准误差最低。
推荐理由
精选AI 评分 71
新模型把生成式输出改为封闭集打分，配合定价与基准表现，可判断这类决策接口的适用边界。
主题
正文
Today we’re launching the Gemini Decisions API, powered by our new Gemini Decision 1 model in @GoogleAIStudio.
Instead of generating text token by token, it’s built for closed-set choices scoring up to 1,000 questions across text, images, audio, video + PDFs in a single pass. A few details:
- 3 decision types: yes/no, multiple choice (up to 255 options) + rubric scoring - $0.10 / 1M input tokens with $0 billed for output tokens (~5x cheaper than Flash-Lite) - leads on several benchmark evals with lowest calibration error
Google teams are already building with it, below is a look at Stitch Rapid designing a full product flow in seconds (1x speed)