Google DeepMind 推出 Gemini Decisions API 与 Gemini…
Google joins the decision-model wave with Gemini Decision 1, scoring 1,000 questions in a single pass
Google DeepMind 推出面向封闭式决策的 Gemini Decisions API,其底层模型 Gemini Decision 1 可在单次处理中同时处理最多 1000 个独立问题,覆盖文本、图像、音频、视频和 PDF,直接给选项打分并返回带置信度的概率,耗时 150 到 250 毫秒。该 API 定价为每百万输入 token 0.10 美元且不收取输出 token 费用,Google 称约为 Gemini 3.5 Flash-Lite 的五分之一,现已通过 Google AI Studio 提供,OpenRouter、LangChain、Vercel 等平台的集成正在陆续推出。Google 表示已在 Gemini Notebook 的动态模型路由、Stitch 的设计原型和 Google Search 的安全检查中内部使用该 API。
推荐理由
AI 评分 74
原文给出了单次处理 1000 个封闭式问题的能力、延迟与定价,读者可据此判断这类决策接口适合哪些场景。
主题
正文
Google Deepmind is introducing the Gemini Decisions API, an interface built for fast, closed-ended decisions like yes/no questions, multiple choice, and scale-based ratings. The underlying model, Gemini Decision 1 , processes up to 1,000 independent questions in a single pass across text, images, audio, video, and PDFs. It scores options directly and returns probabilities with confidence values in 150 to 250 milliseconds. Google says it already uses the API internally for dynamic model routing in Gemini Notebook, design prototyping in Stitch , and safety checks in Google Search.
The API costs $0.10 per million input tokens with no output-token charge, about five times cheaper than Gemini 3.5 Flash-Lite according to Google. It's available now through Google AI Studio , with integrations for OpenRouter, LangChain, Vercel, and other platforms rolling out.
Similar models have been popping up in recent weeks. After the startup Jev introduced its version, OpenAI , Cloudflare , and Microsoft quickly followed with similar offerings.