Optional
options: RequestOptionsClick
Optional
options: RequestOptionsDrag
Optional
options: RequestOptionsExtract data from the UI interface using a JSON schema.
Optional
options: RequestOptionsMove to position
Optional
options: RequestOptionsPress button on the device. like power button, volume up button, volume down button, etc.
Optional
options: RequestOptionsSimulates pressing a specific key by triggering the complete keyboard key event chain (keydown, keypress, keyup). Use this to activate keyboard key event listeners such as shortcuts or form submissions.
Optional
options: RequestOptionsGet the current structured screen layout information. This endpoint returns detailed structural information about the UI elements currently displayed on the screen, which can be used for UI automation, element analysis, and accessibility purposes. The format varies by box type: Android boxes return XML format with detailed UI hierarchy information including element bounds, text content, resource IDs, and properties, while other box types may return different structured formats.
Optional
options: RequestOptionsRotate screen
Optional
options: RequestOptionsTake screenshot
Optional
options: RequestOptionsScroll
Optional
options: RequestOptionsPerforms a swipe in the specified direction
Optional
options: RequestOptionsTouch
Optional
options: RequestOptionsDirectly inputs text content without triggering physical key events (keydown, etc.), ideal for quickly filling large amounts of text when intermediate input events aren't needed.
Optional
options: RequestOptions
Use natural language instructions to perform UI operations on the box. You can describe what you want to do in plain language (e.g., 'click the login button', 'scroll down to find settings', 'input my email address'), and the AI will automatically convert your instruction into the appropriate UI action and execute it on the box.