重點導讀
Google 宣佈在 Google AI Studio 推出 Gemini Decisions API,由新模型 Gemini Decision 1 驅動,可針對多種輸入進行單次決策。
- 輸入與判斷:支援文字、圖片、音訊、影片與 PDF,最多可比對 1,000 個問題。
- 處理與計費:模型不逐 token 生成文字回覆,而是在單次處理中做出決策;輸出 token 不計費。
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
Google@Google
·11 天前
We're introducing the Gemini Decisions API in @GoogleAIStudio, powered by our new Gemini Decision 1 model.
Instead of generating a text response token by token, Gemini Decision 1 evaluates your input (across text, images, audio, video, and PDFs) against up to 1,000 questions to make fast, confident decisions in a single pass, with zero output tokens billed.
Here's a look at how it works 🧵
推文來源 · X (Twitter)在 X 參與討論