# Auto-splitting document API, for multi-page file processing

Seamless batch segmentation for streamlined workflows and high‑precision data capture

Enhance processing speed through intelligent boundary detection that isolates multi-page files into discrete records

## Auto-split

Generalist LLMs struggle with structural speed, requiring heavy resource overhead to deliver accurate splitting results

Prone to missing boundaries in long files

You pay for thousands of tokens just to find a "page break"

Difficult to admit when it's "unsure" of a type

Trained on the open web; lacks deep "document-type" nuance

## With

Auto-split

+95%

Document-level split accuracy

Handles 1-page receipts and 50-page contracts.

Scans and slices a 100-page batch in milliseconds

Built-in metrics to trigger human review only when needed

Trained on millions of real-world business documents

## Implement “Split” into your document workflow, in seconds

Available for every plan

From Mindee’s platform, create a new pre‑processing model by clicking on “Split” utility

You will find it at the bottom of the user interface. If you are more familiar with this type of pre-processing model, you can directly use it by checking the [Documentation for more details](https://docs.mindee.com/).

Custom to your needs

## Enter the document categories that correspond to your needs

Before final pre-processing, you need to define appropriate categories. Be sure to manually add an “Undefined” category. If a file doesn’t match to your document main categories, it will be available in the “Undefined” one.

### PDF, HEIC, PNG, JPEG... Multiple formats

Accelerate ingestion with native support for PDFs and all image formats. From high-res scans to mobile captures, Mindee API handles any input, ensuring your data is always ready for extraction.

## Find all your files categorized in standard JSON format, ready for extraction based on categories

Pre-processing via auto-split can then be combined with other Mindee’s API features to further improve the granularity or directly extract data based on each category classification.

## Use auto-split and more to optimize your document workflow

1. Capture
2. Pre-processing
3. Data extraction
4. Enrichment
5. Validation

Smart capture image from poor quality phone pictures, handwritten notes to native PDFs

Bridge the gap between noisy inputs and structured data. Mindee API cleans low-quality phone captures, analyze handwriting, and isolate multi-documents on a single page/picture.

AI-powered classification that identifies document "DNA" (Invoices vs. Contracts) and automates batch splitting

Manual document sorting is a bottleneck of the past. Our routing engine acts as a digital architect, instantly classifying documents and directing them to the correct business logic.

## Extract data from any layout with outstanding accuracy:

Move beyond simple character recognition. Our extraction layer leverages Neural Networks to understand your data contextually, turning static unstructured files into dynamic, structured assets in standard JSON format.

Real-time synchronization with ERP/CRM master data and automated third-party API validation (VAT, Compliance)

Data in a vacuum has limited utility. The "Enrich" phase bridges the gap between a document and your entire enterprise ecosystem (ERP, CRM, PLM) thanks to integrations.

Automated business rule validation and high-efficiency Human-in-the-Loop workflows for edge-case validation.

Go beyond simple extraction. Build resilient document pipelines that automatically verify data against your custom business rules. Our API manages the friction between automated confidence scores and human edge-case validation, ensuring your production data is always clean, compliant, and actionable.

## Integrate Mindee into your workflow in minutes with SDKs & no-code tools

Go live in minutes using our verified Zapier & Make.com app with zero coding, or integrate seamlessly via our well-documented REST API built for developers. SDKs available for Python, Node.JS, Java, Ruby, PHP.

## Enterprise-grade security

Our API has a SOC 2 Type II certified infrastructure and is GDPR Compliant to ensure your file information remains protected at all times.

Developers and technical profiles already used it!

Mindee is an integrated document processing platform backed by reliable AI technology. The service has an intuitive and user-friendly interface and provides highly accurate results extracting data from various document types, especially financial receipts and invoices. The platform provides seamless integration with data processing workflows through customizable APIs, allowing for efficient data extraction and automation.

## FAQ to know more about Mindee's API

### What is automated document splitting?

Automated document splitting is a **pre-processing technology** that analyzes multi-page file uploads (like a 50-page PDF) and automatically breaks them down into separate, logical documents.

### What are examples of automated document splitting?

In the real-world operational landscape, auto-splitting is a game-changer for **accounts payable** departments that frequently receive bulk PDF attachments.

It ensures each document is correctly identified without any manual sorting.