> For the complete documentation index, see [llms.txt](https://docs.mindee.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.mindee.com/split-models/split.md).

# Split Model Overview

Automatically breaking a multi-page source file into separate documents and associate a class to each one.

## Use Cases

Process a bundle of different documents sent in the same file. The result has both the page range and the class for each document identified, allowing for complex workflows.

Some common examples, where a single PDF contains:

* Several different invoices
* A mix of invoices, receipts, and bank statements
* The person's driver license, vehicle registration, insurance
* Front and back of an ID card, each on a separate page
* The same type of document, but from different regions or languages

A file sent to the Split Model may have any number of pages, [within limits](/integrations/technical-limitations.md#file-limits).

By default, a Split model only returns the page ranges and classes of each document. Use [Extraction model chaining](/split-models/extraction-model-chaining.md) if you also need to extract data from each document.

Split Models also work on single-page files. When a file has a single page, the range will always be exactly one page. This means you can mix various file types in the same workflow, i.e. PDFs and images.

If you need multiple extraction results for each page, take a look at [Crop Models](/crop-models/crop.md) instead.

## Create a Split Model

Split models are always custom, there are no templates available in the Catalog.\
This keeps Split models flexible for different documents and workflows.

Each Split model gets its own unique model ID when you create it.

1. To create a Split model, you need to click on **Models**, and then on **Create your document AI model**.
2. Scroll to the **Document Utilities** section, click on **Split.**
3. A pop-up will appear, allowing you to enter the classes you want. Each class corresponds to a document type possibly present in the documents you want to process.\
   \
   For example, if the files you are processing contain invoices, receipts, and driving licenses, set the classes as: `INVOICE`, `RECEIPT`, `DRIVER_LICENSE`.

{% hint style="info" icon="lightbulb" %}
Add the class `OTHER` if you need the model to identify documents that are not one of the explicitly defined classes.
{% endhint %}

<figure><img src="https://4029869281-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fu5bStlX8nv4b9z4GXB2S%2Fuploads%2FrrYJxgnJ7grVx0OXoX7y%2Fimage.png?alt=media&amp;token=b55ded5c-0af8-43d1-957b-3d9c6116e3f1" alt="" width="375"><figcaption></figcaption></figure>

4. Once ready, click on **Create Utility** to create your custom Split Model.\
   This step will also generate the model's unique ID.
5. You can now use the **Live Test** tab to process documents, and the **Utility Configuration** to update your classes.<br>

Your utility is now available in your **Models** tab:

<figure><img src="https://4029869281-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fu5bStlX8nv4b9z4GXB2S%2Fuploads%2F9efndiptFDTz3yHHeEud%2Fimage.png?alt=media&amp;token=5f692e79-893e-4716-9064-3eb3ff8ff46f" alt=""><figcaption></figcaption></figure>

Here is a step-by-step tutorial that shows you how to properly create a Split Utility :<br>

{% @supademo/embed url="<https://app.supademo.com/demo/cmls4fbup1r1611891nvrrlyw>" demoId="cmls4fbup1r1611891nvrrlyw" %}

## Technical Considerations

Models requires at least two classes defined.

Class names may be in most languages and writing systems, but cannot exceed 128 characters.

Having more than a few dozen classes will yield unexpected results, and is not recommended. If you need classes based on vendor/customer names, product codes, phone numbers, etc, you should use a text field in an [Extraction model](/extraction-models/extraction-models-overview.md) instead.

{% hint style="info" %}
Class names will be returned **exactly** as defined on the platform in the return, spaces and capitalization included.

If the class names are changed on the platform, the change in the API return will be **immediate** for all new files sent.
{% endhint %}

## Integration

Once your Split model is created and tested, integration documentation is provided in the "Documentation" page, or here: [Split Quick Start](/split-models/sdk-integration/split-quick-start.md).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.mindee.com/split-models/split.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.