Skip to main content
POST
/
v1
/
batches
Create a batch
curl --request POST \
  --url https://api.hanji.dev/v1/batches \
  --header 'Content-Type: application/json' \
  --header 'X-API-KEY: <api-key>' \
  --data '
{
  "source": {
    "file_ids": [
      "<string>"
    ],
    "type": "files"
  },
  "engine": "<string>",
  "extract_text": true,
  "extract_images": true,
  "ocr": "auto",
  "table_output_format": "markdown",
  "metadata": {}
}
'
import requests

url = "https://api.hanji.dev/v1/batches"

payload = {
"source": {
"file_ids": ["<string>"],
"type": "files"
},
"engine": "<string>",
"extract_text": True,
"extract_images": True,
"ocr": "auto",
"table_output_format": "markdown",
"metadata": {}
}
headers = {
"X-API-KEY": "<api-key>",
"Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)
const options = {
method: 'POST',
headers: {'X-API-KEY': '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
source: {file_ids: ['<string>'], type: 'files'},
engine: '<string>',
extract_text: true,
extract_images: true,
ocr: 'auto',
table_output_format: 'markdown',
metadata: {}
})
};

fetch('https://api.hanji.dev/v1/batches', 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.hanji.dev/v1/batches",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'source' => [
'file_ids' => [
'<string>'
],
'type' => 'files'
],
'engine' => '<string>',
'extract_text' => true,
'extract_images' => true,
'ocr' => 'auto',
'table_output_format' => 'markdown',
'metadata' => [

]
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"X-API-KEY: <api-key>"
],
]);

$response = curl_exec($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.hanji.dev/v1/batches"

payload := strings.NewReader("{\n \"source\": {\n \"file_ids\": [\n \"<string>\"\n ],\n \"type\": \"files\"\n },\n \"engine\": \"<string>\",\n \"extract_text\": true,\n \"extract_images\": true,\n \"ocr\": \"auto\",\n \"table_output_format\": \"markdown\",\n \"metadata\": {}\n}")

req, _ := http.NewRequest("POST", url, payload)

req.Header.Add("X-API-KEY", "<api-key>")
req.Header.Add("Content-Type", "application/json")

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.hanji.dev/v1/batches")
.header("X-API-KEY", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"source\": {\n \"file_ids\": [\n \"<string>\"\n ],\n \"type\": \"files\"\n },\n \"engine\": \"<string>\",\n \"extract_text\": true,\n \"extract_images\": true,\n \"ocr\": \"auto\",\n \"table_output_format\": \"markdown\",\n \"metadata\": {}\n}")
.asString();
require 'uri'
require 'net/http'

url = URI("https://api.hanji.dev/v1/batches")

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

request = Net::HTTP::Post.new(url)
request["X-API-KEY"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"source\": {\n \"file_ids\": [\n \"<string>\"\n ],\n \"type\": \"files\"\n },\n \"engine\": \"<string>\",\n \"extract_text\": true,\n \"extract_images\": true,\n \"ocr\": \"auto\",\n \"table_output_format\": \"markdown\",\n \"metadata\": {}\n}"

response = http.request(request)
puts response.read_body
{
  "id": "<string>",
  "status": "<string>",
  "counts": {
    "pending": 0,
    "running": 0,
    "succeeded": 0,
    "failed": 0,
    "cancelled": 0
  },
  "total_items": 123,
  "engine": "<string>",
  "options": {},
  "created_at": "<string>",
  "expires_at": "<string>",
  "object": "batch",
  "metadata": {},
  "started_at": "<string>",
  "completed_at": "<string>"
}
{
"error": "file_not_found",
"file_ids": [
"file_abc123"
]
}
{
"error": "file_not_uploaded",
"file_ids": [
"file_abc123"
]
}
{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}

Authorizations

X-API-KEY
string
header
required

Headers

Idempotency-Key
string | null

Body

application/json
source
FilesSource · object
required
engine
string | null
Maximum string length: 64
extract_text
boolean
default:true
extract_images
boolean
default:true
ocr
enum<string>
default:auto

Deprecated. Accepted for backward compatibility but currently has no effect.

Available options:
auto,
never,
force
table_output_format
enum<string>
default:markdown

How table chunks are structured in each item's result. 'markdown' (default) keeps the existing markdown-derived cells; 'cell_grid' returns true per-cell bounding boxes on table chunks.

Available options:
markdown,
cell_grid
metadata
Metadata · object | null

Response

Successful Response

id
string
required
status
string
required
counts
BatchCounts · object
required
total_items
integer
required
engine
string | null
required
options
Options · object
required
created_at
string
required
expires_at
string
required
object
string
default:batch
metadata
Metadata · object | null
started_at
string | null
completed_at
string | null