---
id: "b925"
language: "en"
library: "tools"
official_url: "https://github.com/opendatalab/MinerU"
profile_updated_on: "2026-10-23"
---

# MinerU

Parse complex documents with OCR and vision-language models, retaining page/block locators.

- Company / organization: MinerU Team
- Category: Model development
- Official website: [https://github.com/opendatalab/MinerU](https://github.com/opendatalab/MinerU)
- Profile updated: 2026-10-23


## Overview

MinerU 4 offers a CLI, Python SDK and local services for document parsing and agent reading. PDFs and images support four tiers combining native parsing, OCR and vision-language models. Office formats use local Flash parsing, not necessarily a VLM. Page/block locators support continued reading and citations. It is a document processor, not a ready-made RAG platform; remote parsing requires explicit configuration.

## Usage guide & costs

### Before you start

The Apache-2.0-based license adds conditions: combined affiliate MAU over 100 million or monthly revenue over US$20 million requires a commercial license. Third-party online services must prominently credit MinerU. Check model/dependency licenses separately.

[Official details](https://github.com/opendatalab/MinerU/blob/master/LICENSE.md)
[Official details](https://github.com/opendatalab/MinerU/blob/master/README.md)


## Official sources and references

- [Official website](https://github.com/opendatalab/MinerU)
- [Documentation](https://opendatalab.github.io/MinerU/)
- [Documentation](https://opendatalab.github.io/MinerU/usage/tiers/)
- [Documentation](https://github.com/opendatalab/MinerU/blob/master/README.md)

## Reading & subscriptions

- [Interactive profile](../../../products/mineru--b925.html)
- [Read](../../../read/en/products/mineru--b925.html)
- [JSON](../../../read/en/products/mineru--b925.json)

Descriptions summarize public information; consult official websites for features, pricing and regional availability.