Skip to main content
OpenAI’s computer tool drives interfaces through the Responses API. This guide wires it to an Orgo computer.
The computer tool is the generally available integration and runs on the GPT-5.5 and GPT-5.6 families. The older computer_use_preview tool and its computer-use-preview model still work, and are covered at the end of this page. Use the GA tool for anything new.

Coordinate space

Orgo computers boot at 1280x720x24. The computer tool takes no display size. The model reads the screen dimensions from the screenshots you send, and returns x and y in that same pixel space. Send an Orgo screenshot unresized and the coordinates come back as the computer’s pixels. Pass them straight to left_click. Send "detail": "original" with each screenshot so the API keeps the resolution the model is measuring against.
Downscale a screenshot and click the raw coordinates and every click lands short of where the model aimed. Nothing errors. The agent looks like it is confidently clicking the wrong thing. If you must resize, keep the scale factor and map each coordinate back to the original resolution.
GET /computers/{id}/screens reports the current width and height if you created the computer at another resolution or resized its screen later.

Quick start

The examples pass ram and cpu, and take screenshots and scroll over HTTP, so they also run on older SDKs. SDK versions before 0.0.47 (Python) and 1.0.22 (TypeScript) default to 2 GB, which POST /computers rejects with 400. Their screenshot() and screenshot_base64() cannot read the stored-image path the API returns by default, and their scroll() takes no coordinates, so the computer scrolls at the top-left corner.
1

Install packages

2

Set up API keys

3

Run your first task

Complete example

A full agent loop. The model returns a batch of actions per turn, so run every entry in actions[] in order before you screenshot.

Usage examples

Basic tasks

Complex workflows

Reusing sessions

Key concepts

The agent loop

  1. Request Send the task to the model.
  2. Actions The model returns a computer_call holding a batch of actions.
  3. Execute Your code runs every action in the batch, in order.
  4. Screenshot Capture the result and return it as a computer_call_output.
  5. Repeat Continue until a response has no computer_call.

Action types

Safety

The model acts on whatever the screen shows, and page content is untrusted input. OpenAI’s guidance is to isolate the environment, restrict which sites the agent can reach, and keep a human in the loop for consequential steps. An Orgo computer covers the isolation half: the blast radius is that one computer, and computer.destroy() ends it.

Best practices

1. Clear instructions

2. Error handling

3. Session management

4. Timing considerations

Migrating from the preview tool

The preview integration still runs. These are the differences: The preview tool declares its own display size, so on a default Orgo computer set display_width: 1280 and display_height: 720 to match the screenshots you send.

Comparison with Claude

Next steps

OpenAI Docs

Official OpenAI computer use documentation

Orgo Quickstart

Learn more about Orgo computers