v33

latestOpenAPI 3.1.0raw.githubusercontent.com2026-04-2972102177.5 KB

AI Tools

Perform Web Task

Start from a URL and perform the given task.

post/v1/tools/perform-web-task

Query parameters

sessionIdstring

An optional browser session identifier to reference an existing running browser sessions. When passed, the tool will be executed on the provided browser session.

Request body

urlstring

The URL of the webpage. If not provided, the tool will use the current page in the session.

promptstring required

The task to be autonomously completed.

agent'browser-use' | 'openai-cua' | 'yutori'

The AI agent to use for task completion. Defaults to browser-use.

provider'openai' | 'gemini' | 'groq' | 'azure' | 'xai'

The AI provider to use for task completion.

modelstring

The specific model to use for task completion. see our models page for more information.

detect_elementsboolean

Enable element detection for better interaction accuracy. Improves the agent's ability to identify and interact with UI elements.

human_interventionboolean

Allow human intervention during task execution. When enabled, the agent can request human input for ambiguous situations.

max_stepsinteger

Maximum number of steps the agent can take to complete the task. Defaults to 200.

secret_valuesobject

Secret values to pass to the agent for secure credential handling. Keys and values are passed as environment variables to the agent.

highlight_elementsboolean

Whether to highlight elements during task execution for better visibility.

output_schemaobject

JSON Schema defining the expected structure of the output data.

Response

The result of the autonomous task.