Skip to main content
POST
/
v1
/
tools
/
perform-web-task
Perform Web Task
curl --request POST \
  --url https://api.anchorbrowser.io/v1/tools/perform-web-task \
  --header 'Content-Type: application/json' \
  --header 'anchor-api-key: <api-key>' \
  --data '{
  "prompt": "<string>"
}'
{
  "data": {
    "result": "<string>"
  }
}

Authorizations

​
anchor-api-key
string
header
required

API key passed in the header

Query Parameters

​
sessionId
string

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

Body

application/json
​
prompt
string
required

The task to be autonomously completed.

​
url
string

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

​
agent
enum<string>

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

Available options:
browser-use,
openai-cua
​
provider
enum<string>

The AI provider to use for task completion.

Available options:
openai,
gemini,
groq,
azure,
xai
​
model
string

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

​
detect_elements
boolean

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

​
human_intervention
boolean

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

​
max_steps
integer

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

​
secret_values
object

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

​
highlight_elements
boolean

Whether to highlight elements during task execution for better visibility.

​
output_schema
object

JSON Schema defining the expected structure of the output data.

Response

The result of the autonomous task.

​
data
object