Invoice OCR API: extract invoices to JSON

pip install openai requests
export MUNITO_API_KEY="munitoai_..."

# pip install openai requests
import base64
import json
import os
import sys
import time

import requests
from openai import OpenAI

HOST = "https://api.munito.ai"
BASE_URL = f"{HOST}/inference/v1"
HEADERS = {"Authorization": f"Bearer {os.environ['MUNITO_API_KEY']}"}

INVOICE_SCHEMA = {
    "type": "object",
    "properties": {
        "invoice_number": {"type": "string"},
        "invoice_date": {"type": "string", "description": "ISO 8601 date, YYYY-MM-DD"},
        "seller": {"type": "string"},
        "buyer": {"type": "string"},
        "currency": {"type": "string", "description": "ISO 4217 code, such as EUR"},
        "total": {"type": "number"},
        "lines": {
            "type": "array",
            "items": {
                "type": "object",
                "properties": {
                    "description": {"type": "string"},
                    "quantity": {"type": "number"},
                    "unit_price": {"type": "number"},
                    "amount": {"type": "number"},
                },
                "required": ["description", "quantity", "unit_price", "amount"],
                "additionalProperties": False,
            },
        },
    },
    "required": ["invoice_number", "invoice_date", "seller", "buyer", "currency", "total", "lines"],
    "additionalProperties": False,
}


def ocr_markdown(path: str) -> str:
    """Read the PDF with Munito OCR and return the Markdown of all pages."""
    with open(path, "rb") as f:
        data = base64.b64encode(f.read()).decode()
    response = requests.post(
        f"{BASE_URL}/ocr",
        headers=HEADERS,
        json={
            "model": "munito/ocr-auto",
            "document": {"type": "base64", "data": data, "filename": os.path.basename(path)},
        },
        timeout=300,
    )
    response.raise_for_status()
    body = response.json()
    # A long document answers 202. Poll its location until the status is final.
    while response.status_code == 202 or body.get("status") == "running":
        time.sleep(2)
        response = requests.get(HOST + body["location"], headers=HEADERS, timeout=60)
        response.raise_for_status()
        body = {**response.json(), "location": body["location"]}
    if body.get("status", "completed") != "completed":
        sys.exit(f"OCR ended with status {body['status']}")
    return "\n\n".join(page["markdown"] for page in body["pages"])


def extract_fields(markdown: str) -> dict:
    """Ask a chat model for the invoice fields, as JSON that matches the schema."""
    client = OpenAI(base_url=BASE_URL, api_key=os.environ["MUNITO_API_KEY"])
    completion = client.chat.completions.create(
        model="qwen/qwen3.8-27b",
        messages=[
            {"role": "system", "content": "Extract the invoice fields. Use only values that the invoice shows."},
            {"role": "user", "content": markdown},
        ],
        response_format={
            "type": "json_schema",
            "json_schema": {"name": "invoice", "schema": INVOICE_SCHEMA, "strict": True},
        },
        reasoning_effort="low",
        max_tokens=4096,
    )
    return json.loads(completion.choices[0].message.content)


if __name__ == "__main__":
    path = sys.argv[1] if len(sys.argv) > 1 else "invoice.pdf"
    fields = extract_fields(ocr_markdown(path))
    print(json.dumps(fields, indent=2))

python extract_invoice.py invoice.pdf

{
  "invoice_number": "INV-2026-0417",
  "invoice_date": "2026-10-15",
  "seller": "Nordlicht Software GmbH",
  "buyer": "Atelier Vert SARL",
  "currency": "EUR",
  "total": 1499.4,
  "lines": [
    {
      "description": "Support plan, October",
      "quantity": 1,
      "unit_price": 900,
      "amount": 900
    },
    {
      "description": "Onboarding workshop (hours)",
      "quantity": 3,
      "unit_price": 120,
      "amount": 360
    }
  ]
}