DataLearner logoDataLearnerAI
Latest AI Insights
Model Leaderboards
Benchmarks
Model Directory
Model Comparison
Resource Center
Tools
LanguageEnglish
DataLearner logoDataLearner AI

A knowledge platform focused on LLM benchmarking, datasets, and practical instruction with continuously updated capability maps.

Products

  • Leaderboards
  • Model comparison
  • Datasets

Resources

  • Tutorials
  • Editorial
  • Tool directory

Company

  • About
  • Privacy policy
  • Data methodology
  • Contact

© 2026 DataLearner AI. DataLearner curates industry data and case studies so researchers, enterprises, and developers can rely on trustworthy intelligence.

Privacy policyTerms of service
Page navigation
目录
Model catalogGemini 2.5 Computer Use (Preview)
GE

Gemini 2.5 Computer Use (Preview)

多模态大模型

Gemini 2.5 Computer Use Preview (10-2025)

Release date: 2025-10-07更新于: 2025-10-08 10:57:56423
Live demoGitHubHugging FaceCompare
Parameters
Not disclosed
Context length
128K
Chinese support
Not supported
Reasoning ability

Gemini 2.5 Computer Use Preview (10-2025) is an AI model published by Google Deep Mind, released on 2025-10-07, for 多模态大模型, with 0.0B parameters, and 128K tokens context length, under the 不开源 license.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Gemini 2.5 Computer Use (Preview)

Model basics

Reasoning traces
Supported
Thinking modes
Thinking modes not supported
Context length
128K tokens
Max output length
64000 tokens
Model type
多模态大模型
Release date
2025-10-07
Model file size
No data
MoE architecture
No
Total params / Active params
No data / N/A
Knowledge cutoff
No data
Gemini 2.5 Computer Use (Preview)

Open source & experience

Code license
不开源
Weights license
不开源- 不开源
GitHub repo
GitHub link unavailable
Hugging Face
Hugging Face link unavailable
Live demo
https://gemini.browserbase.com/
Gemini 2.5 Computer Use (Preview)

Official resources

Paper
Introducing the Gemini 2.5 Computer Use model
DataLearnerAI blog
No blog post yet
Gemini 2.5 Computer Use (Preview)

API details

API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard pricingStandard
ModalityInputOutput
Text$1.25$10.00
Image$1.25--
Extended context pricingExtended
ModalityInputOutput
Text$2.50$15.00
Image$2.50--
Gemini 2.5 Computer Use (Preview)

Benchmark Results

No benchmark data to show.
Gemini 2.5 Computer Use (Preview)

Publisher

Google Deep Mind
Google Deep Mind
View publisher details
Gemini 2.5 Computer Use Preview (10-2025)

Model Overview

概述

Gemini 2.5 Computer Use 是基于 Gemini 2.5 Pro 视觉理解与推理能力而构建的专用模型,面向通过浏览器等图形界面执行业务操作的智能体(agent)场景。该模型以 Preview 形式通过 Gemini API 在 Google AI Studio 与 Vertex AI 向开发者开放。

工作机理与能力

模型通过新的 computer_use 工具以循环(agent loop)方式运行:输入包含用户目标、当前界面截图与近期动作历史;模型输出为规范化的 UI 动作(如点击、输入、拖拽等)的函数调用,同时可能附带对高风险动作的确认请求。客户端负责执行动作并回传新截图与 URL,直至任务完成或中止。

当前模型主要针对浏览器环境进行了优化,并在移动端 UI 控制基准上显示出良好潜力;尚未针对桌面 OS 级控制进行优化。

技术规格(公开信息)

  • 模型版本(API id):gemini-2.5-computer-use-preview-10-2025
  • 输入模态:文本、图像(截图);输出模态:文本
  • 上下文窗口:输入 128K tokens;最大输出 64K tokens

性能与评测

Google 公布的自测与第三方环境(如 Browserbase harness)显示,该模型在 Online-Mind2Web、WebVoyager 与 AndroidWorld 等多项网页/移动控制基准上达到领先准确率与较低时延。具体分数及方法学细节见官方博文与随附的评估说明。

访问与定价

模型以 API 方式提供(AI Studio/Vertex AI)。Vertex AI 定价页提供了 Gemini 2.5 Pro — Computer Use (Preview) 的令牌计费:当输入上下文 ≤200K tokens 与 >200K tokens 时,输入/输出分别采用不同单价;若无在该模型项下明确列出的“缓存计费(Cached Input)”,则不应填入缓存单价。

应用与限制

适合:跨站信息采集、表单自动化、网页流程/用例测试、在登录态下操作 UI 等。限制:Preview 阶段可能产生错误与安全风险;需在受控环境运行,并对高风险动作实施二次确认与审计。

DataLearner 官方微信

欢迎关注 DataLearner 官方微信,获得最新 AI 技术推送

DataLearner 官方微信二维码