精选产品82

Google 发布 Gemini Decisions API 与 Gemini Decision 1 模型

原标题:Today we’re launching the Gemini Decisions API, powered by our new Gemini Decision 1 model in @GoogleAIStudio.

Sundar Pichai@sundarpichai发布时间 (北京时间)

Google 发布 Gemini Decisions API,由新模型 Gemini Decision 1 驱动,已在 GoogleAIStudio 上线。该接口不做逐 token 文本生成,而是面向封闭集合选择打分,单次可处理最多 1,000 个问题,覆盖文本、图像、音频、视频和 PDF。

推荐理由原文给出定价、决策类型与基准表现,便于判断这类封闭选项打分接口适合哪些场景。

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)