Google: Gemini 2.5 Computer Use Preview

Specialized Gemini 2.5 model for browser-control agents that automate UI tasks

Model lab: Google
Model family: gemini-pro

Modalitiestext, image → text

Context window128,000

Maximum output64,000

Input · Base context tier (boundary 200000 tokens)USD 1 / 1M tokens

Output · Base context tier (boundary 200000 tokens)USD 8 / 1M tokens

Try now

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to google/gemini-2.5-computer-use-preview-10-2025.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "google/gemini-2.5-computer-use-preview-10-2025"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Gemini 2.5 Computer Use Preview API Pricing

Type	Price information
Input · Base context tier (boundary 200000 tokens)	USD 1 / 1M tokens
Output · Base context tier (boundary 200000 tokens)	USD 8 / 1M tokens

Performance

Performance trends

Throughput88.2 tok/sCurrent

Time to first token1.4 sCurrent

End-to-end latency7.4 sCurrent

Throughput

Current88.2 tok/s

Window average89.9 tok/s

Time to first token

Current1.4 s

Window average1.4 s

End-to-end latency

Current7.4 s

Window average7.5 s

Tail latency (P99)

Current17.0 s

Window average17.1 s

Prompt cache hit rate

Current26.3%

Window average24.6%

Error rate

Current0.0%

Window average0.1%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

Gemini 2.5 Computer Use Preview Compare models

Model	Input price	Output price	Context window	Capabilities
Gemini 2.5 Computer Use PreviewThis page	USD 1 / 1M tokens · Base context tier (boundary 200000 tokens)	USD 8 / 1M tokens · Base context tier (boundary 200000 tokens)	128,000	Text output · Reasoning · Tool calling
Gemini 3.1 Pro Preview	USD 0.8 / 1M tokens	USD 4.8 / 1M tokens	1,048,576	Text output · Reasoning · Tool calling
Gemini 3.1 Pro Preview Custom Tools	USD 1.6 / 1M tokens · Base context tier (boundary 200000 tokens)	USD 9.6 / 1M tokens · Base context tier (boundary 200000 tokens)	1,048,576	Text output · Reasoning · Tool calling
Gemini 3 Pro Preview	USD 1.6 / 1M tokens · Base context tier (boundary 200000 tokens)	USD 9.6 / 1M tokens · Base context tier (boundary 200000 tokens)	1,048,576	Text output · Reasoning · Tool calling
Gemini 2.5 Pro	USD 1 / 1M tokens · Base context tier (boundary 200000 tokens)	USD 8 / 1M tokens · Base context tier (boundary 200000 tokens)	1,048,576	Text output · Reasoning · Tool calling

Model specifications

Input: text, image
Output: text
Context window: 128,000
Maximum output: 64,000
Release date: 2025-10-07
Attachments: Yes
Reasoning: Yes
Tool calling: Yes
Temperature setting: Yes
Open weights: No

Frequently asked questions

What is Gemini 2.5 Computer Use Preview for?

Specialized Gemini 2.5 model for browser-control agents that automate UI tasks

What inputs and outputs does Gemini 2.5 Computer Use Preview support?

Recorded inputs: text, images; outputs: text.

How is Gemini 2.5 Computer Use Preview priced?

The pricing table shows the current recorded Moduck price. For example: Input · Base context tier (boundary 200000 tokens) USD 1 / 1M tokens; Output · Base context tier (boundary 200000 tokens) USD 8 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Gemini 2.5 Computer Use Preview?

Current model records list Context window 128,000 tokens; Maximum output 64,000 tokens.

What model parameter does the Quickstart use?

The example uses google/gemini-2.5-computer-use-preview-10-2025. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.