Google DeepMind (Gemini) / gemini-2.5-computer-use-preview-10-2025
Gemini 2.5 Computer Use Preview stands out for Gemini specialized for controlled UI operation and 128K context with supervised browser action loops. It is best suited to browser task automation and human-supervised UI agents.
Context
128K
token
Input
$1.125
/ 1M tokens
Output
$9.00
/ 1M tokens
Quality
—
No score
Overview
Gemini 2.5 Computer Use Preview stands out for Gemini specialized for controlled UI operation and 128K context with supervised browser action loops. It is best suited to browser task automation and human-supervised UI agents.
Tool calling
Can call tools or functions, so product flows can connect model output to backend actions.
Reasoning
Better suited for multi-step analysis, planning, and tasks that need deliberate reasoning.
Model maker
Google DeepMind (Gemini)
Called through SeaLink's unified account, balance, and OpenAI-compatible API.
Protocol
OpenAI-compatible Chat Completions
Base URL: https://api.sealink.io/v1
Pricing
The final charge follows generated usage and the applicable selector, such as resolution, duration, input type, or provider unit.
API
model
gemini-2.5-computer-use-preview-10-2025base_url
https://api.sealink.io/v1Auth
Bearer $SEALINK_API_KEYcurl https://api.sealink.io/v1/chat/completions \-H "Authorization: Bearer $SEALINK_API_KEY" \-H "Content-Type: application/json" \-d '{"model": "gemini-2.5-computer-use-preview-10-2025","messages": [{"role": "user", "content": "Reply OK only. Do not use the computer."}],"tools": [{"type": "computer_use", "environment": "browser", "display_width": 1024, "display_height": 768}],"tool_choice": "auto","max_tokens": 64}'
from openai import OpenAIclient = OpenAI(base_url="https://api.sealink.io/v1", api_key="<your-sealink-key>")resp = client.chat.completions.create(model="gemini-2.5-computer-use-preview-10-2025",messages=[{"role": "user", "content": "Reply OK only. Do not use the computer."}],tools=[{"type": "computer_use", "environment": "browser", "display_width": 1024, "display_height": 768}],tool_choice="auto",max_tokens=64,)print(resp)
import OpenAI from "openai";const client = new OpenAI({baseURL: "https://api.sealink.io/v1",apiKey: process.env.SEALINK_API_KEY,});const resp = await client.chat.completions.create({model: "gemini-2.5-computer-use-preview-10-2025",messages: [{ role: "user", content: "Reply OK only. Do not use the computer." }],tools: [{ type: "computer_use", environment: "browser", display_width: 1024, display_height: 768 }],tool_choice: "auto",max_tokens: 64,});console.log(resp);