✨AI-powered document extraction API

Extract structured data from documents using AI.

Zendix helps developers extract structured JSON data from invoices, receipts, purchase orders, PDFs, images, forms, and other business documents using AI extraction jobs.

1

Create a schema

Define your JSON schema that matches Zendix schema structure, or create a schema in the Zendix dashboard and then copy the generated JSON into your API request.

2

Send files or text

Upload files, send text content, or combine both in a single extraction request.

3

Receive structured JSON

Zendix processes the job synchronously and returns the structured extraction results immediately.

How Zendix works

Zendix uses synchronous extraction jobs. When you create a job, Zendix immediately starts to process it and sends the results back to the client in a JSON response.

Create Request

→

Upload Files

→

AI Processing

→

Structured Result

Job Status	Description
`successful`	The extraction completed successfully and results are available.
`failed`	The extraction failed and an error message is available.

Your first request

The example below uploads an invoice PDF and creates a new extraction job using a JSON schema.

POST/api/v1/jobs/s/create/

Python

import requests
import json

url = "https://api.zendix.app/v1/jobs/s/create/"

headers = {
    "Authorization": "Bearer YOUR_API_KEY"
}

files = [
    ("files", open("invoice.pdf", "rb"))
]

payload = {
    "body": "",
    "schema": json.dumps({
        "invoice_number": "string",
        "invoice_date": "string",
        "total": "float"
    }),
    "document_type": "invoice"
}

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

JavaScript

const formData = new FormData();

formData.append("body", "");
formData.append("schema", JSON.stringify({
        "invoice_number": "string",
        "invoice_date": "string",
        "total": "float"
    })
);
formData.append("document_type", "invoice");
formData.append("files", fileInput.files[0]);

const response = await fetch("https://api.zendix.app/v1/jobs/s/create/", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_API_KEY"
  },
  body: formData
});

const data = await response.json();
console.log(data);

cURL

curl -X POST https://api.zendix.app/v1/jobs/s/create/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "body=" \
  -F 'schema={"invoice_number": "string", "invoice_date": "string", "total": "float"}' \
  -F "document_type=invoice" \
  -F "files=@invoice.pdf"

JSON Response

{
    "success": true,
    "data": {
        "status": "successful",
        "result": {
            "invoice_number": "INV-2026-001",
            "invoice_date": "May 12, 2026",
            "total": 1381.38,
            "fail reason": ""
        },
        "error": null,
        "details": {
            "body": "",
            "document_type": "invoice",
            "schema": {
                "invoice_number": "string",
                "invoice_date": "string",
                "total": "float"
            },
            "file_count": 1,
            "created_at": "2026-08-15T14:59:53.663789Z"
        }
    },
    "meta": {
        "job_id": 90
    }
}

Authentication

All Zendix API requests must include your API key in the Authorization header.

Keep your API keys secure

Your API keys should be kept secret and secure. Never expose them in frontend applications, public repositories, or client-side code.

1

Create an API key

Purchase an API key (also called an access code) from the Zendix dashboard.

2

Include it in requests

Send the API key in the Authorization header using the Bearer format.

Python

response = requests.get(url, headers = {
    "Authorization": "Bearer YOUR_API_KEY"
})

JavaScript

const response = await fetch(url, {
  headers: {
    Authorization: "Bearer YOUR_API_KEY"
  }
});

cURL

curl url \
  -H "Authorization: Bearer YOUR_API_KEY"

Authentication errors

Zendix returns standardized error responses when authentication fails.

Invalid API Key

{
    "success": false,
    "error": {
        "code": "authentication_failed",
        "message": "Invalid API key."
    },
    "meta": null
}

Create job

Create an extraction job by sending files, text content, or both. Zendix processes the job synchronously and returns a JSON response immediately.

Custom Extraction Jobs

Create an extraction job that extracts specific fields from your documents as defined by your schema.

POST/api/v1/jobs/s/create/

Request fields

Field	Type	Required	Description
`schema`	JSON	yes	JSON schema used for extraction. Must match Zendix schema structure.
`document_type`	string	yes	The type of document being processed (e.g invoice, receipt, form).
`files`	File[]	optional	Uploaded documents. Max 10 files. Supported formats: pdf, png, jpg, jpeg, webp, txt.
`body`	string	optional	Raw text content to extract data from.

Important rule

You must provide either files, body, or both.

Supported combinations

Files	Body	Valid
✔	✖	Yes
✖	✔	Yes
✔	✔	Yes
✖	✖	No

Limits

Maximum files: 10
Maximum total upload size: 5MB
Supported file formats: pdf, png, jpg, jpeg, webp, txt

Python

import requests
import json

url = "https://api.zendix.app/v1/jobs/s/create/"

headers = {
    "Authorization": "Bearer YOUR_API_KEY"
}

files = [
    ("files", open("invoice.pdf", "rb"))
]

payload = {
    "body": "",
    "schema": json.dumps({
        "invoice_number": "string",
        "invoice_date": "string",
        "total": "float"
    }),
    "document_type": "invoice"
}

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

JavaScript

const formData = new FormData();

formData.append("body", "");
formData.append("schema", JSON.stringify({
        "invoice_number": "string",
        "invoice_date": "string",
        "total": "float"
    })
);
formData.append("document_type", "invoice");
formData.append("files", fileInput.files[0]);

const response = await fetch("https://api.zendix.app/v1/jobs/s/create/", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_API_KEY"
  },
  body: formData
});

const data = await response.json();
console.log(data);

cURL

curl -X POST https://api.zendix.app/v1/jobs/s/create/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "body=" \
  -F 'schema={"invoice_number": "string", "invoice_date": "string", "total": "float"}' \
  -F "document_type=invoice" \
  -F "files=@invoice.pdf"

JSON Response

{
    "success": true,
    "data": {
        "status": "successful",
        "result": {
            "invoice_number": "INV-2026-001",
            "invoice_date": "May 12, 2026",
            "total": 1381.38,
            "fail reason": ""
        },
        "error": null,
        "details": {
            "body": "",
            "document_type": "invoice",
            "schema": {
                "invoice_number": "string",
                "invoice_date": "string",
                "total": "float"
            },
            "file_count": 1,
            "created_at": "2026-08-15T14:59:53.663789Z"
        }
    },
    "meta": {
        "job_id": 90
    }
}

Automatic Extraction Jobs

Create an extraction job that automatically identifies and extracts the data from your documents without needing a schema.

POST/api/v1/jobs/s/a/create/

Request fields

Field	Type	Required	Description
`files`	File[]	optional	Uploaded documents. Max 10 files. Supported formats: pdf, png, jpg, jpeg, webp, txt.
`body`	string	optional	Raw text content to extract data from.

Important rule

You must provide either files, body, or both.

Supported combinations

Files	Body	Valid
✔	✖	Yes
✖	✔	Yes
✔	✔	Yes
✖	✖	No

Limits

Maximum files: 10
Maximum total upload size: 5MB
Supported file formats: pdf, png, jpg, jpeg, webp, txt

Python

import requests
import json

url = "https://api.zendix.app/v1/jobs/s/a/create/"

headers = {
    "Authorization": "Bearer YOUR_API_KEY"
}

files = [
    ("files", open("invoice.pdf", "rb"))
]

payload = {
    "body": ""
}

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

JavaScript

const formData = new FormData();

formData.append("body", "");
formData.append("files", fileInput.files[0]);

const response = await fetch("https://api.zendix.app/v1/jobs/s/a/create/", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_API_KEY"
  },
  body: formData
});

const data = await response.json();
console.log(data);

cURL

curl -X POST https://api.zendix.app/v1/jobs/s/a/create/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "body=" \
  -F "files=@invoice.pdf"

JSON Response

{
    "success": true,
    "data": {
        "status": "successful",
        "result": {
            "invoice_number": "INV-2026-001",
            "invoice_date": "May 12, 2026",
            "total": 1381.38,
            "fail reason": ""
        },
        "error": null,
        "details": {
            "body": "",
            "document_type": null,
            "schema": null,
            "file_count": 1,
            "created_at": "2026-08-15T14:59:53.663789Z"
        }
    },
    "meta": {
        "job_id": 90
    }
}

Rate limiting

Zendix enforces rate limits to ensure fair usage and system stability.

Note

Rate limits are applied per API key.

Type	Rate Limit	Window
API key	100 requests	per minute

All API keys can each make a maximum of 100 requests per minute.

File limits

Zendix enforces strict file upload limits to ensure performance and reliability.

Limit	Value
Maximum files	10 files
Total upload size	5MB
Supported formats	pdf, png, jpg, jpeg, webp, txt

Error codes

All errors follow a standardized structure to make debugging simple and predictable.

Error response format

{
  "success": false,
  "error": {
    "code": "error_code",
    "message": "Human readable message"
  },
  "meta": null
}

Common error codes

Code	Meaning
`validation_error`	Invalid request data
`method_not_allowed`	Request method not allowed
`rate_limit_exceeded`	Too many requests
`authentication_failed`	Invalid API key
`parse_error`	Invalid form data
`file_storage_limit_exceeded`	Insufficient file storage
`file_not_stored`	A file in request files failed to upload