> 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/models/models-overview.md).

# Models Overview

## What is a Model?

A **Model** in the Mindee platform is a configurable and reusable engine designed to process documents. In technical terms, a model is a set of parameters and complex prediction algorithms that perform an inference on files uploaded to Mindee.

Various types of models are available, from simple text recognition to data extraction and classification. Models use Optical Character Recognition (OCR) combined with sophisticated data processing techniques.

Models allow you to automate the process of turning unstructured document images into actionable, structured data. They can be tailored to different document types and business needs, ensuring that only the most relevant information is captured for your workflows.

On the Models page, you can view, search, and manage all your document extraction models. Each model is represented as a card showing its name, a preview (if available), and a summary of the main fields it extracts. This makes it easy to organize, access, and deploy models for your document processing tasks.

Each Model contains a dedicated set of tools:

* Configuration: a model is defined by its configuration, that sets the way it should extract data from documents or analyze files. Configuration depends on the model type.
* Settings: overall settings of the model such as processing zone, storage policy, ownership transfer, etc.

## Extraction Models

An **Extraction Model** in the Mindee platform is designed to extract structured data from documents using Optical Character Recognition (OCR) combined with data extraction techniques.

More information is available in the section: [Extraction Models](/extraction-models/extraction-models-overview.md)

## Utility Models

A **Utility Model** in the Mindee platform is designed to perform document analysis, or to preprocess documents in a data extraction workflow.

More information is available for each model type:

* [Split Model Overview](/split-models/split.md) ⇒ find documents in a multi-page file
* [Crop Model Overview](/crop-models/crop.md) ⇒ find documents on a single page
* [Classification Model Overview](/classification-models/classification.md) ⇒ identify file contents
* [Raw Text Model Overview](/raw-text-ocr-models/ocr.md)⇒ structured text extraction

## Live Test

Once a model is created you can process documents directly on the platform. Use your own files or choose from our samples selection.

You can also view your document history.

This allows easily testing a model before integrating the API and going live to production.

For more information, consult:  [Live Test](/models/live-test.md).

## Changing Settings

Settings control the high-level options of the model, such as storage duration and processing zone.

For more information on available options, consult:  [Model Settings](/models/model-settings.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/models/models-overview.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.