# Key Features
Mindee headline features center on custom models, RAG, confidence scores, and rich outputs.
## Custom Extraction Models
Build fully customizable extraction models with interactive data schemas and an AI assistant for fast iteration and control over fields and guidelines.\
Learn more at [data-schema](https://docs.mindee.com/extraction-models/data-schema "mention").
Live Test UI for side-by-side visual validation, JSON inspection, and RAG simulation before production.\
Learn more at [live-test](https://docs.mindee.com/models/live-test "mention").
## Extraction Model Catalog
Choose from our catalog models with predefined fields for data extraction.\
You can modify them as needed, just like our custom models.
Some popular use cases include:
* **Billing**: Financial Document, Invoice, Receipt, ...
* **Identification**: Passport, ID Card, Driver License, ...
* **Employment**: Resume or CV, Payslip, ...
* **Banking**: Check, Bank Statement, ...
* **Logistics**: Bill of Lading, Vehicle Registration, ...
Learn more at [extraction-models](https://docs.mindee.com/use-cases/extraction-models "mention")
## Utility Models
In addition to extraction models, Mindee also provides utility models that can be used either separately or in conjunction with Extraction Models.
These utilities allow for more complex workflows and greater flexibility.
* **Split**: Detect separate documents in a multi-page source file, matching each document to a category.
* **Crop**: Detect document boundaries on each page, matching each document to a category.
* **Classification**: Automatically assign images and scanned documents to the right category.
* **OCR**: Extract raw text and word boundaries from any document with high precision.
{% hint style="info" %}
Utilities are currently in beta: they are usable, with full integration support coming soon.
{% endhint %}
## Advanced Features
Retrieval-Augmented Generation (RAG) to continuously improve accuracy using your own documents and corrections.\
Learn more at [improving-accuracy](https://docs.mindee.com/extraction-models/optional-features/improving-accuracy "mention").
Confidence scores per field to boost precision and drive downstream decisions. Allows automating your workflows.\
Learn more at [automation-confidence-score](https://docs.mindee.com/extraction-models/optional-features/automation-confidence-score "mention").
Polygon coordinates for every extracted field to map values to document regions.\
Learn more at [polygons-bounding-boxes](https://docs.mindee.com/extraction-models/optional-features/polygons-bounding-boxes "mention").
Full text content output for complete OCR alongside structured fields.\
Learn more at [raw-text-full-ocr](https://docs.mindee.com/extraction-models/optional-features/raw-text-full-ocr "mention").
Data residency controls (EU/US) for privacy and compliance (GDPR, SOC 2 Type II).\
Learn more at [data-processing-policies](https://docs.mindee.com/models/data-processing-policies "mention").
## Integrations
Asynchronous processing with polling and webhooks; official SDKs for Python, Node.js, Ruby, PHP, Java, and .NET.\
Learn more at [client-libraries-sdk](https://docs.mindee.com/integrations/client-libraries-sdk "mention").
No‑code and low‑code integrations, including an official Make.com app and generic HTTP workflows.\
Learn more at [no-code-integrations](https://docs.mindee.com/integrations/no-code-integrations "mention").
## Flexible Plans
Mindee pricing is plan-based with included pages, overages, and feature tiers.
Pay annually to save money, or monthly.
Compare all plans and their features at [plans](https://docs.mindee.com/account-management/plans "mention").
Sign Up to Mindee
## Need Something Else?
Our product team is always interested in adding new features to help our users.\
[Make a feature request!](https://feedback.mindee.com/?b=682f69c9e2404756e7e68d1c)
---
# Agent Instructions: 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:
```
GET https://docs.mindee.com/getting-started/key-features.md?ask=
```
The question should be specific, self-contained, and written in natural language.
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.