Google发布Gemini Decisions API
Today we’re launching the Gemini Decisions API, powered by our new Gemini Decisi…
多模态决策专用API上线,定价极具竞争力,适合需要批量结构化输出的场景,建议开发者关注并测试。
Today we’re launching the Gemini Decisions API, powered by our new Gemini Decision 1 model in @GoogleAIStudio.
今天,我们在 @GoogleAIStudio 推出了 Gemini Decisions API,该 API 由我们全新的 Gemini Decision 1 模型提供支持。
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:
它不再逐 token 生成文本,而是专为封闭式选择设计,可在单次传递中对多达 1,000 个问题(涵盖文本、图像、音频、视频及 PDF)进行评分。以下是几个关键细节:
- 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
- 3 种决策类型:是/否、多项选择(最多 255 个选项)+ 量规评分 - 每百万输入 token 收费 $0.10,输出 token 免费(约比 Flash-Lite 便宜 5 倍) - 在多项基准评估中领先,且校准误差最低
Google teams are already building with it, below is a look at Stitch Rapid designing a full product flow in seconds (1x speed)
Google 团队已在基于此构建应用,以下展示了 Stitch Rapid 如何在数秒内(1x 速度)设计完整的产品流程
更进一步:量化金融体系
看懂新闻只是起点——沿量化金融路径,把它变成能交付的工程能力