Gemini 2.5 Computer Use model
[!NOTE] Note: The Gemini 3 Pro and Flash models support built-in computer use, without the need for a separate model.
An agentic capability model designed for direct interface interaction, allowing Gemini to perceive and navigate digital environments. Gemini 2.5 Computer Use is best for browser automation, multi-step software tasks, and UI testing that requires visual reasoning and precise cursor control.
Documentation
Visit the Computer use page for full coverage of features and capabilities.
gemini-2.5-computer-use-preview-10-2025
| Property | Description |
|---|---|
| Model code | Gemini API gemini-2.5-computer-use-preview-10-2025 |
| Supported data types | Input Image, text Output Text |
| Token limits[1](https://ai.google.dev/gemini-api/docs/tokens)^ | Input token limit 128,000 Output token limit 64,000 |
| Versions | Read the model version patterns for more details. - Preview: gemini-2.5-computer-use-preview-10-2025 |
| Latest update | October 2025 |
[*] ↩︎