COMPUTER USE / PROFILE

OpenAI Computer Use: capabilities, evidence & fit

A model capability for deciding browser and desktop actions in an environment you control.

Computer-use modellive

The decision layer. Your application supplies a browser or desktop, executes returned actions, captures the next screenshot, and enforces approval boundaries. Pair it with execution infrastructure or a local sandbox.

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

Where it fits

CONSIDER IT FOR

Custom browser and desktop agent loops
Teams already using the Responses API

LOOK ELSEWHERE WHEN

You need a ready-made hosted browser
A stable application API already covers the workflow

Fit recommendations are editorial interpretations of the documented architecture.

Documented capabilities

CAPABILITY	DOCUMENTED STATE	SOURCE
Control surfaces	Browser and desktop interfaces	EVIDENCE RECORD Follow the source. Source verification confirms what the publisher states. It is not our independent performance test. official docs Control surfaces: Browser and desktop interfaces Verified Sep 27, 2026 · verified developers.openai.com
Perception	Screenshots and tool results guide the next action	EVIDENCE RECORD Follow the source. Source verification confirms what the publisher states. It is not our independent performance test. official docs Perception: Screenshots and tool results guide the next action Verified Sep 27, 2026 · verified developers.openai.com
Action interface	Structured mouse and keyboard actions	EVIDENCE RECORD Follow the source. Source verification confirms what the publisher states. It is not our independent performance test. official docs Action interface: Structured mouse and keyboard actions Verified Sep 27, 2026 · verified developers.openai.com
Code path	Code execution can use Playwright or PyAutoGUI	EVIDENCE RECORD Follow the source. Source verification confirms what the publisher states. It is not our independent performance test. official docs Code path: Code execution can use Playwright or PyAutoGUI Verified Sep 27, 2026 · verified developers.openai.com
Execution ownership	The developer supplies and controls action execution	EVIDENCE RECORD Follow the source. Source verification confirms what the publisher states. It is not our independent performance test. official docs Execution ownership: The developer supplies and controls action execution Verified Sep 27, 2026 · verified developers.openai.com
Integration reference	Official sample application is publicly available	EVIDENCE RECORD Follow the source. Source verification confirms what the publisher states. It is not our independent performance test. official repo Integration reference: Official sample application is publicly available Verified Sep 27, 2026 · verified github.com

Environment, deployment & control

Environment

browser: Full
desktop: Full
mobile: Unknown

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: Full

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: Unknown
audit Logs: Unknown
sandboxing: Unknown
prompt Injection Defense: Unknown
credential Controls: Unknown

Know the boundary

The API does not itself supply your application's execution environment.
Untrusted screen content can contain instructions; sandboxing and consequential-action approval remain application responsibilities.

Design human approval →

Pricing snapshot

$10 / 1M input tokens · gpt-6-astra

gpt-6-astra · Standard · short context

Verified Sep 27, 2026 · USD · usage. Hosted services and software licensing can have different terms.

Cost inputs & calculator →

Compare the tradeoffs

OpenAI Computer Use vs Claude Computer Use

Both provide model-side computer-use capabilities. The decision is which provider integration and action surface fit your runtime; neither comparison entry includes the surrounding production system.

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.

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 →