Read scanned bank statements and ID forms

The problem

Scanned statements and forms often combine small print, tables, stamps, and uneven page quality. A basic text extraction may return nothing or scramble columns, leaving the agent to guess which balance or label belongs to which line.

How NativePort helps

NativePort sends the selected pages to a document reader and returns their recognized text with table structure where detected. The agent gets a readable source to review, and your app can preserve page references when a person needs to check a value.

Technical implementation

Use Python 3 with requests installed (python -m pip install requests). Set NATIVEPORT_API_KEY in your environment to your NativePort key. Run the snippets on your server, where your key stays private.

Set DOCUMENT_URL to an HTTPS URL the document service can fetch, such as a time-limited file link. The example reads page 0 (the first page). Select only pages you need, up to 100 per request; split longer documents into batches. Send the URL, not inline file bytes.

python

import os
import requests

BASE = "https://api.nativeport.ai"
HEADERS = {"Authorization": f"Bearer {os.environ['NATIVEPORT_API_KEY']}"}

payload = {
    "document": {"type": "document_url", "document_url": os.environ["DOCUMENT_URL"]},
    "pages": [0],
}
response = requests.post(BASE + "/mistral/v1/ocr", headers=HEADERS,
                         json=payload, timeout=120)
response.raise_for_status()
result = response.json()
for page in result["pages"]:
    print(f"--- Page {page['index'] + 1} ---")
    print(page["markdown"])

This step reads the document; it does not verify identity, validate account ownership, or reconcile balances. Use a short-lived document link and keep source page numbers alongside extracted values. See the Mistral request policy for document URLs, page selection, and accepted options. OCR returns recognized content; check unclear scans against the source.

Tool costs

Tool used in the example	Price per call
Mistral — OCR	$0.00422 / call (1 page)

Prices in USD. Usage-based tools have no fixed per-call price. View pricing.

Let your agent build it

You don’t need to write this code yourself. Copy this page’s link and paste it into your agent. Ask it to follow the guide and implement the feature for you.

https://nativeport.ai/use-cases/read-bank-statements-and-forms/

The problem

How NativePort helps

Technical implementation

Tool costs

Let your agent build it

Keep exploring

Let your agent interpret images

Make images searchable by meaning

Read passport fields without retyping them

Explore all use cases