Batch Extract
curl --request POST \
--url https://api.example.com/api/v1/extract/batch \
--header 'Content-Type: multipart/form-data' \
--form 'schema=<string>' \
--form 'urls=<string>' \
--form model=auto \
--form use_vision=false \
--form follow_links=false \
--form 'webhook_url=<string>'import requests
url = "https://api.example.com/api/v1/extract/batch"
payload = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"urls\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_vision\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"follow_links\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\n<string>\r\n-----011000010111000001101001--"
headers = {"Content-Type": "multipart/form-data"}
response = requests.post(url, data=payload, headers=headers)
print(response.text)const form = new FormData();
form.append('schema', '<string>');
form.append('urls', '<string>');
form.append('model', 'auto');
form.append('use_vision', 'false');
form.append('follow_links', 'false');
form.append('webhook_url', '<string>');
const options = {method: 'POST'};
options.body = form;
fetch('https://api.example.com/api/v1/extract/batch', 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.example.com/api/v1/extract/batch",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"urls\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_vision\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"follow_links\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\n<string>\r\n-----011000010111000001101001--",
CURLOPT_HTTPHEADER => [
"Content-Type: multipart/form-data"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.example.com/api/v1/extract/batch"
payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"urls\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_vision\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"follow_links\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\n<string>\r\n-----011000010111000001101001--")
req, _ := http.NewRequest("POST", url, payload)
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.example.com/api/v1/extract/batch")
.body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"urls\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_vision\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"follow_links\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\n<string>\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.example.com/api/v1/extract/batch")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"urls\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_vision\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"follow_links\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\n<string>\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}Extraction
Batch Extract
Submit multiple files or URLs for extraction with a single schema. Each item is processed concurrently. Returns a batch_id to poll.
Poll: GET /api/v1/jobs/batch/{batch_id}
Limits: Maximum 20 items per batch.
POST
/
api
/
v1
/
extract
/
batch
Batch Extract
curl --request POST \
--url https://api.example.com/api/v1/extract/batch \
--header 'Content-Type: multipart/form-data' \
--form 'schema=<string>' \
--form 'urls=<string>' \
--form model=auto \
--form use_vision=false \
--form follow_links=false \
--form 'webhook_url=<string>'import requests
url = "https://api.example.com/api/v1/extract/batch"
payload = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"urls\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_vision\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"follow_links\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\n<string>\r\n-----011000010111000001101001--"
headers = {"Content-Type": "multipart/form-data"}
response = requests.post(url, data=payload, headers=headers)
print(response.text)const form = new FormData();
form.append('schema', '<string>');
form.append('urls', '<string>');
form.append('model', 'auto');
form.append('use_vision', 'false');
form.append('follow_links', 'false');
form.append('webhook_url', '<string>');
const options = {method: 'POST'};
options.body = form;
fetch('https://api.example.com/api/v1/extract/batch', 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.example.com/api/v1/extract/batch",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"urls\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_vision\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"follow_links\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\n<string>\r\n-----011000010111000001101001--",
CURLOPT_HTTPHEADER => [
"Content-Type: multipart/form-data"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.example.com/api/v1/extract/batch"
payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"urls\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_vision\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"follow_links\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\n<string>\r\n-----011000010111000001101001--")
req, _ := http.NewRequest("POST", url, payload)
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.example.com/api/v1/extract/batch")
.body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"urls\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_vision\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"follow_links\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\n<string>\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.example.com/api/v1/extract/batch")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"urls\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_vision\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"follow_links\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\n<string>\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}Headers
Body
multipart/form-data
JSON schema — applied to every item
Files to extract data from
JSON array of URLs to extract from
Model: 'fast', 'accurate', or 'auto'
Use vision mode
Follow internal links (URLs only)
URL to POST results when the entire batch completes
Response
Successful Response
⌘I