The BrowserAI API enables developers to programmatically create, manage, and retrieve results from browser-based automation tasks powered by AI. This API is designed to help you automate web interactions, extract data, scrape, and run scripts in our cloud-based browser environment with customizable geographic targeting. Whether you’re building a data extraction pipeline, automating web testing, or integrating browser automation into your product, this API provides a secure and scalable interface to manage your automation workflows.

​
Getting Started

  1. Obtain your API key from the Projects Dashboard.
  2. Create a task by sending a request to /tasks with your prompt and geo settings.
  3. Track the task using the session ID returned.
  4. Fetch results once the task is completed!

​
Authentication

All endpoints are secured using an API key. You must include your API key in the Authorization header using the following format: 
Authorization: apikey <API-KEY>

​
Available Endpoints

MethodEndpointDescription
POST/tasksCreate a new task.
POST/tasks/{session_id}/commandForce stop a task.
GET/tasks/{session_id}Get metadata, progress and status of a task.
GET/results/{session_id}Retrieve the results of a task.
POST/saved_tasksCreate a saved task.
GET/saved_tasksGet list of saved tasks.
GET/saved_tasks/name/{task_name}Get a saved task by name.