新闻
Gemini Decisions API: Fast, calibrated multimodal decisions
Google AI · {"$":{"xmlns:author":"http://www.w3.org/2005/Atom"},"name":["Min Choi"],"title":["Product Manager"],"department":["Google DeepMind"],"company":[""]} · 发布于 · 阅读约3分钟 · Hacker News 385 分
30秒读懂
- 发生了什么
- Google released Gemini Decisions API with a new Decision 1 model for fast yes/no, multiple-choice, and rubric-scoring decisions across multimodal inputs.
- 为何重要
- Relevant for engineers building systems requiring low-latency classification, routing, or grading across text, images, audio, video, and PDFs in production.
- 注意
- API pricing charges input tokens once per request regardless of question count; output tokens are free. Latency remains 150-250ms end-to-end, which may not suit sub-100ms requirements.
- gemini
这条新闻背后的模式
每个模式都讲清楚技术如何运作、何时值得投入，以及在哪里会失效。
The Agent Architect
每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。
每周一封邮件,一键退订。您的地址仅用于发送简报。