Developers automating websites without APIs can use it on current Gemini models at normal token rates; the original 2.5 model is shut down.
Kenning's take
What it does
Computer Use is a tool in the Gemini API that lets a model look at screenshots and return clicks, typing and other UI actions, so developers can build agents that fill in forms and use apps. It first shipped in October 2025 as the Gemini 2.5 Computer Use model; that preview model was shut down in July 2026 and the tool now runs on Gemini 3.x models such as 3.8 Flash.
- Browser, mobile and desktop control
- Actions returned with an intent explaining each step
- Runs in a developer-built execution loop
- Supported on Gemini 3.x models
Who it suits. Developers building agents that must use websites or apps without an API.
Key facts
- Category
- Developer tools
- Part of
- Google Gemini
- Made by
- Based in
- United States
- Released
- 7 October 2025
- How to get it
- Gemini API (computer_use tool) and Gemini Enterprise Agent Platform
- Works on
- API
- In the UK
- Yes
- Free plan
- Not available on the free tier
- API price
- Charged as regular tokens at the chosen model's rate
FAQ
What is Gemini Computer Use?
A Gemini API tool that lets a model see screenshots and return UI actions so agents can operate software.
Is the Gemini 2.5 Computer Use model still available?
No. The preview model was shut down on 28 July 2026; Google recommends Gemini 3.8 Flash with the computer use tool.
Facts from the maker's own pages and the sources listed. Checked 2026-10-11.
Similar tools
Gemini Deep Research Max
Google's slower, more thorough research agent for developers, built on Gemini 3.1 Pro
Gemini CLI
Google's open-source AI agent that runs Gemini in the terminal for coding and other tasks
Gemini Deep Research Agent
Gemini API agent that plans and runs multi-step web research and returns cited reports
Gemini Enterprise Agent Platform
Google Cloud's platform for building and running AI agents, which replaced Vertex AI