Google
The latest voice foundation model from Google DeepMind, integrating extended chain-of-thought reasoning directly into live spoken dialogues.
262.144K ctx$0.0035 / min (Live Extended Thinking)
Introducing Gemini 2.5 Computer UseGoogleReleased October 7, 2025
Gemini 2.5 Computer Use
Specialized desktop and browser agent model that interprets screen pixels, executes mouse clicks, keyboard strokes, and multi-app tasks.
multimodal-realtimeProprietary API$1.00 / 1M tok (OS Agent)Context: 524.288K (524,288 tokens)
Technical Specifications
Architecture Type
Agentic Vision-Action Transformer
Total Parameters
Undisclosed
Context Window
524.288K (524,288 tokens)
Max Output Tokens
8.192K (8,192 tokens)
Knowledge Cutoff
June 2025
Supported Modalities
vision, text, screen-actions
License & Access
Google Cloud API Terms of Service
Benchmark Evaluations
Os World
44.8
Web Arena
52.3
Screen Click Accuracy
94.6
Deep Architectural Overview
Gemini 2.5 Computer Use provides native operating system automation. It perceives graphical user interfaces (GUIs), accurately locates interactive UI elements by pixel coordinates, and orchestrates workflows across desktop software.
Strengths & Considerations
Core Strengths
- Sub-pixel mouse click coordinate accuracy
- High OSWorld benchmark score (44.8%)
- Handles complex multi-step browser workflows
Known Limitations
- Requires sandboxed virtual machine environment for safe execution
Token & API Pricing
Input Tokens (1M)$1.00
Output Tokens (1M)$4.00
Cached Input (1M)$0.2500
Pricing is verified directly against Google's developer documentation and API rate sheets.
Similar & Alternative Models
Explore other frontier models from Google and comparable reasoning engines.
Google
The latest evolution in the Gemini 3 family, delivering state-of-the-art software engineering (73.7% DeepSWE) and agentic enterprise knowledge workflows.
1.049M ctx$0.75 / 1M tok ($1.50 reg)
Google
Universal omnimodal generation model that accepts any combination of text, audio, image, and video to generate any combination of outputs.
1.049M ctx$0.60 / 1M tok (Universal Omni)
Google
Universal multilingual speech engine supporting live simultaneous translation and speaker diarization across 100+ languages.
262.144K ctx$0.0025 / min audio (Translate & Live)