Updated daily at 05:00 UTC
Vision-language
Gemini Computer Use
A Gemini model specialised to read screenshots and emit UI actions for browser automation.
By Google DeepMind.
Versions
1 version
| Model | Maker | Kind | Released | Context | Input $/1M | Output $/1M |
|---|---|---|---|---|---|---|
| Gemini 2.5 Computer UseGemini Computer Use | Google DeepMind | Vision-language | 7 Oct 2025 | 128K | $1.25 | $10.00 |
