Google 推出 Gemini 2.5 Computer Use 模型：基於 Gemini 2.5 Pro，支援 API 預覽
Original: Introducing the Gemini 2.5 Computer Use model
Google DeepMind has officially launched the new dedicated "Gemini 2.5 Computer Use" model, which is now available in preview via API. This…
Google DeepMind 發表全新的 Gemini 2.5 Computer Use 專用模型，目前已透過 API 提供預覽。該模型基於 Gemini 2.5 Pro 的強大能力進行微調，旨在賦能 AI 代理（Agents）直接與作業系統及應用程式的用戶介面（UI）進行互動。這項技術將加速自動化工作流程的開發，讓 AI 能夠像人類一樣執行點擊、輸入和導覽等電腦操作。
Google DeepMind has officially launched the new dedicated "Gemini 2.5 Computer Use" model, which is now available in preview via API. This model is built on the powerful architecture and capabilities of Google's latest generation Gemini 2.5 Pro, and is specifically designed to drive AI agents capable of deeply interacting with computer user interfaces (UIs).
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Google DeepMind Blog →Summaries are AI-generated; the original article is authoritative.