25 signals
HOlO V1 IS LIVEone ranked AI digest a day, scored in publicREAD HOW IT WORKS →HOlO V2 STARTSyour X account, your signals, every day

Model registry / Google / Gemini Pro / Gemini 2.5 Computer Use Preview 10-2025

Gemini 2.5 Computer Use Preview 10-2025

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

Line

Gemini Pro

Weights

API only

Released

2025-10-07

Context

128K

Input

$1.25 / 1M

Output

$10.00 / 1M

Max output

64K

Coverage

not covered yet

Overview

Gemini 2.5 Computer Use Preview 10-2025 is a specialized Gemini 2.5 model for browser-control agents that automate UI tasks. It sits in the gemini-pro line, released on 2025-10-07, following Gemini 2.5 Pro. It has a 128000-token context window and a 64000-token maximum output. It accepts image and text inputs and returns text. It supports reasoning and tool calling. Weights are not open. Price starts at $1.25 per million input tokens and $10.00 per million output tokens.

Specs

Released2025-10-07
LineGoogle · Gemini Pro
WeightsAPI only
Context128K tokens
Max output64K tokens
Inputimage, text
Outputtext
ReasoningYes
Tool callingYes
Knowledge cutoff2025-01
API idgemini-2.5-computer-use-preview-10-2025

Pricing

Input$1.25 / 1M tokens
Cached inputnot stated
Output$10.00 / 1M tokens

Against Gemini 2.5 Pro: window 1.05M to 128K, input $0.87 to $1.25, output $7.00 to $10.00.

Strengths

  • Specialized for browser-control agents
  • Automates UI tasks
  • Supports reasoning and tool calling
  • Accepts image and text inputs
  • 128k context window

Best for

  • Reach for it for automating browser UI tasks
  • Reach for it for building browser-control agents
  • Reach for it for tasks needing image and text understanding
  • Reach for it for long-context UI automation

How to access

ProviderModel id
Googlegemini-2.5-computer-use-preview-10-2025
Merge Gatewaygemini-2.5-computer-use-preview-10-2025

2 hosts serve this model at the price above · the maker's documentation

Gemini Pro: every version

VersionReleasedContextInput
Gemini 3.1 Pro PreviewCurrent2026-02-191.05M$1.00
Gemini 2.5 Pro2025-06-171.05M$0.87

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

FAQ

What is the context window size?
The context window is 128000 tokens, with a maximum output of 64000 tokens.
Does it support tool calling?
Yes, it supports tool calling and reasoning mode. It accepts image and text inputs and returns text.
What is the pricing?
Price starts at $1.25 per million input tokens and $10.00 per million output tokens.
ProprietaryReasoning128K context