Skip to main content
POST
/
v1
/
browsing
/
tasks
curl --request POST \
  --url https://api.yutori.com/v1/browsing/tasks \
  --header 'X-API-Key: YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "task": "Give me a list of all employees (names and titles) of Yutori.",
    "start_url": "https://yutori.com"
  }'

{
  "task_id": "<string>",
  "view_url": "<string>",
  "status": "queued",
  "result": "<string>",
  "paused": true,
  "structured_result": {},
  "webhook_url": "<string>"
}
curl --request POST \
  --url https://api.yutori.com/v1/browsing/tasks \
  --header 'X-API-Key: YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "task": "Give me a list of all employees (names and titles) of Yutori.",
    "start_url": "https://yutori.com"
  }'

​
Advanced Example

Configure structured output with output_schema to receive data in a specific JSON schema format, and optionally add webhook notifications.
curl --request POST \
  --url https://api.yutori.com/v1/browsing/tasks \
  --header 'X-API-Key: YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "task": "Give me a list of all employees (names and titles) of Yutori.",
    "start_url": "https://yutori.com",
    "max_steps": 75,
    "webhook_url": "https://example.com/webhook",
    "output_schema": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "name": { "type": "string" },
          "title": { "type": "string" }
        }
      }
    }
  }'

Authorizations

​
x-api-key
string
header
required

Body

application/json
​
task
string
required

String describing the browsing task in natural language.

Example:

"Give me a list of all employees (names and titles) of Yutori."

​
start_url
string
required

URL to open before running the task

Example:

"https://yutori.com"

​
max_steps
integer | null

Maximum number of steps the agent can take

Required range: 2 <= x <= 100
Example:

50

​
agent
enum<string> | null

Which agent to use for the browsing task. Defaults to navigator-n1-latest.

Available options:
navigator-n1-latest,
claude-sonnet-4-5-computer-use-2025-01-24,
navigator-n1-preview-2025-11
Example:

"navigator-n1-latest"

​
require_auth
boolean
default:false

Hint that this task is likely to involve authentication (e.g. logging in or entering passwords). When true, the system will prefer an auth-optimized browser provider when available.

​
output_schema
Output Schema · object

JSON Schema for structured output. Takes precedence over task_spec if both provided.

Example:
{
  "items": {
    "properties": {
      "name": {
        "description": "Full name of the employee",
        "type": "string"
      },
      "title": {
        "description": "Job title of the employee",
        "type": "string"
      }
    },
    "type": "object"
  },
  "type": "array"
}
​
task_spec
TaskSpec · object
deprecated

Deprecated but still supported. Use output_schema instead.

​
webhook_url
string | null

Optional webhook URL to receive the agent.run result for the calling user using webhook_format.

Example:

"https://example.com/webhook"

​
webhook_format
enum<string>
default:scout

Webhook payload format to use when webhook_url is provided. Slack incoming webhook URLs require 'slack'.

Available options:
scout,
slack,
zapier
Example:

"scout"

​
used_deprecated_task_spec
boolean
default:false

Response

Successful Response

​
task_id
string
required

Unique identifier for this browsing task

​
view_url
string
required
​
status
enum<string>
required
Available options:
queued,
running,
succeeded,
failed
​
result
string | null
​
paused
boolean | null
​
structured_result

If an output schema was provided, the result formatted as JSON matching that schema

​
webhook_url
string | null

Echoes the webhook URL configured for this agent.run request, if provided.