COMPUTER USE / PROFILE

Gemini Computer Use: capabilities, evidence & fit

Screenshot-driven UI actions for browser, mobile, and desktop agent integrations.

Computer-use modelpreview

A model/tool capability, with client-side action execution. Your loop sends screenshots, receives UI function calls, handles safety decisions, executes approved actions, and returns the resulting screen.

Last verified: Sep 27, 2026
Primary sources: 3
Evidence state: Fresh
Benchmark records: No linked results

Where it fits

CONSIDER IT FOR

A single model interface across multiple UI environments
Applications that handle safety decisions in their own loop

LOOK ELSEWHERE WHEN

Critical decisions cannot tolerate preview errors
A supervised execution environment is unavailable

Fit recommendations are editorial interpretations of the documented architecture.

Documented capabilities

CAPABILITY	DOCUMENTED STATE	SOURCE
Environment coverage	Browser, mobile and desktop control agents	EVIDENCE RECORD Follow the source. Source verification confirms what the publisher states. It is not our independent performance test. official docs Environment coverage: Browser, mobile and desktop control agents Verified Sep 27, 2026 · verified ai.google.dev
Visual input	Screenshots provide the model's current UI state	EVIDENCE RECORD Follow the source. Source verification confirms what the publisher states. It is not our independent performance test. official docs Visual input: Screenshots provide the model's current UI state Verified Sep 27, 2026 · verified ai.google.dev
UI action output	Function calls describe clicks, scrolling and keystrokes	EVIDENCE RECORD Follow the source. Source verification confirms what the publisher states. It is not our independent performance test. official docs UI action output: Function calls describe clicks, scrolling and keystrokes Verified Sep 27, 2026 · verified ai.google.dev
Safety response	Actions may require confirmation or be blocked	EVIDENCE RECORD Follow the source. Source verification confirms what the publisher states. It is not our independent performance test. official docs Safety response: Actions may require confirmation or be blocked Verified Sep 27, 2026 · verified ai.google.dev
Execution ownership	Client code executes approved actions and returns screenshots	EVIDENCE RECORD Follow the source. Source verification confirms what the publisher states. It is not our independent performance test. official docs Execution ownership: Client code executes approved actions and returns screenshots Verified Sep 27, 2026 · verified ai.google.dev
Reference implementation	Public example includes browser execution code	EVIDENCE RECORD Follow the source. Source verification confirms what the publisher states. It is not our independent performance test. official repo Reference implementation: Public example includes browser execution code Verified Sep 27, 2026 · verified github.com

Environment, deployment & control

Environment

browser: Full
desktop: Full
mobile: Full

Deployment

cloud: Full
local: Unknown
self Hosted: Unknown

Extensibility

api: Full
sdk: Full
mcp: Unknown
bring Your Own Model: Unknown

Control method

screenshots: Full
mouse Keyboard: Full
dom Or Accessibility: Unknown
code Execution: Unknown

Unknown = insufficient public evidence; No evidence = an explicit negative record; N/A = does not apply to this layer.

Trust, oversight & limitations

Documented oversight

human Approval: Partial
audit Logs: Unknown
sandboxing: Unknown
prompt Injection Defense: Partial
credential Controls: Unknown

Know the boundary

Google labels Computer Use a preview capability and recommends close supervision for important tasks.
Environment and action availability depend on the chosen Gemini model; the legacy 2.5 preview is browser-focused.

Design human approval →

Pricing snapshot

Price needs verification

Current pricing is not sufficiently verified, or its 14-day review window has expired. Check the official provider before budgeting.

Compare the tradeoffs

OpenAI Computer Use vs Gemini Computer Use

Compare execution contracts and required environments first. Public capability scope does not establish that either integration completes your workflow more reliably.

Claude Computer Use vs Gemini Computer Use

Both require an execution environment and application controls. Their documented tool surfaces and safety configuration differ, so choose around the required environment and an explicit approval model.

Relevant use cases

Computer use for legacy software

Evaluate native interface control only after checking supported import, scripting, and integration paths.

RESEARCH NOTES

Sources & verification

Reviewed Sep 27, 2026. Architecture recommendations are editorial analysis; linked vendor documentation supports the underlying capability and safety facts.

How we verify evidence →