Get the status and result of an async extract job

curl --request GET \
  --url https://api.lighton.ai/api/v3/extract/{job_id} \
  --header 'Authorization: Bearer <token>'

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://api.lighton.ai/api/v3/extract/{job_id}', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.lighton.ai/api/v3/extract/{job_id}",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.lighton.ai/api/v3/extract/{job_id}"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("Authorization", "Bearer <token>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://api.lighton.ai/api/v3/extract/{job_id}")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'

response = http.request(request)
puts response.read_body

{
  "id": "ext_0196e4b2a3c14d5e8f7a9b2c1d0e3f4a",
  "status": "completed",
  "created_at": "2026-03-31T10:00:00+00:00",
  "completed_at": "2026-03-31T10:00:04+00:00",
  "processing_time_ms": 3200,
  "document": {
    "filename": "invoice.pdf",
    "page_count": 3,
    "file_size_bytes": 245120,
    "mime_type": "application/pdf"
  },
  "result": {
    "data": [
      {
        "invoice_number": "INV-2026-001",
        "total": null
      },
      {
        "invoice_number": null,
        "total": 1250
      },
      {
        "invoice_number": null,
        "total": null
      }
    ],
    "pagination": {
      "page": 1,
      "page_size": 15,
      "total_items": 3,
      "total_pages": 1,
      "has_next": false,
      "has_prev": false
    }
  },
  "usage": {
    "pages_processed": 3
  },
  "progress": {
    "percentage": 100,
    "pages_processed": 3
  }
}

Extract

Get the status and result of an async extract job

Poll for the status and result of an async extract job submitted via POST /api/v3/extract with options.async=true. Returns the same envelope shape as the synchronous extract endpoint once status is completed.

curl https://api.lighton.ai/api/v3/extract/ext_0196e4b2a3c14d5e \
  -H 'Authorization: Bearer $TOKEN'

Pagination: when completed, result.data is paginated with a fixed page size of 15. Use the page query param (1-based) to navigate; result.pagination reports total_items, total_pages, has_next, has_prev.

Recommended polling cadence: 1s for the first 10s, then 5s, capped at 30s. Stop polling once status is in {completed, failed}.

GET

api

extract

{job_id}

Get the status and result of an async extract job

curl --request GET \
  --url https://api.lighton.ai/api/v3/extract/{job_id} \
  --header 'Authorization: Bearer <token>'

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://api.lighton.ai/api/v3/extract/{job_id}', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.lighton.ai/api/v3/extract/{job_id}",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.lighton.ai/api/v3/extract/{job_id}"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("Authorization", "Bearer <token>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://api.lighton.ai/api/v3/extract/{job_id}")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'

response = http.request(request)
puts response.read_body

{
  "id": "ext_0196e4b2a3c14d5e8f7a9b2c1d0e3f4a",
  "status": "completed",
  "created_at": "2026-03-31T10:00:00+00:00",
  "completed_at": "2026-03-31T10:00:04+00:00",
  "processing_time_ms": 3200,
  "document": {
    "filename": "invoice.pdf",
    "page_count": 3,
    "file_size_bytes": 245120,
    "mime_type": "application/pdf"
  },
  "result": {
    "data": [
      {
        "invoice_number": "INV-2026-001",
        "total": null
      },
      {
        "invoice_number": null,
        "total": 1250
      },
      {
        "invoice_number": null,
        "total": null
      }
    ],
    "pagination": {
      "page": 1,
      "page_size": 15,
      "total_items": 3,
      "total_pages": 1,
      "has_next": false,
      "has_prev": false
    }
  },
  "usage": {
    "pages_processed": 3
  },
  "progress": {
    "percentage": 100,
    "pages_processed": 3
  }
}

Authorizations

Authorization

string

header

required

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

Path Parameters

job_id

string

required

Query Parameters

page

integer

default:1

1-based page index for navigating result.data. Fixed page size of 15 items. An out-of-range page is rejected.

Response

Extract job status (pending, processing, completed, or failed).

string

required

status

string

required

created_at

string<date-time> | null

completed_at

string<date-time> | null

processing_time_ms

integer | null

document

ExtractDocument · object | null

Show child attributes

result

ExtractResult · object | null

Show child attributes

usage

ExtractUsage · object | null

Show child attributes

progress

JobProgress · object | null

Live progress of a long-running async job while it is in flight.

Shared by the parse (GET /api/v3/parse/<id>) and extract (GET /api/v3/extract/<id>) polling envelopes: pages_processed is the count of pages done so far and percentage is the completion percentage [0, 100] derived from it.

Show child attributes

⌘I

Overview

Intelligence

Document Processing

Administration

Get the status and result of an async extract job

Authorizations

Path Parameters

Query Parameters

Response