Skip to main content
POST
/
api
/
v2
/
extract
/
start
Turn a single URL to data without a workflow, ad-hoc
curl --request POST \
  --url https://api.jsonify.com/api/v2/extract/start \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "schema": {
    "name": "<the site name>"
  }
}
'
{
  "message": "started",
  "result": {
    "id": "e4ab8b5b-45bd-4e0f-8abb-5ce8a4db255e"
  },
  "success": true
}

Documentation Index

Fetch the complete documentation index at: https://docs.jsonify.com/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Query Parameters

​
url
string
required

The URL to extract from

​
additional_instructions
string

Additional hints to the AI about what you want to extract

​
model
enum<string>

The model to use. Large is slower but may be more accurate. Small is faster but may be less accurate.

Available options:
auto,
large,
small
​
extended
boolean

Attempt to extract extended metadata, like URLs and images

​
cap_screenshots
integer
default:5

Increasing this will cause the AI to scroll further down the page

Body

application/json

A JSON schema to extract against

Example:
{ "schema": { "name": "<the site name>" } }

Response

200 - application/json

An in-progress result, which you can retrieve later with /result/{result_id}

​
message
string
Example:

"started"

​
result
object
​
success
boolean
Example:

true