- Home
- PDF Converter Software
- MinerU
MinerU
What it is
MinerU 4.0 combines document parsing, a local document library, and tools for conversion, application integration, and agent reading. It accepts PDFs, images, office documents, ebooks, web formats, spreadsheets, and other listed inputs. Outputs include Markdown, HTML, LaTeX, DOCX, EPUB, PDF, structured content, and Content List V1/V2. Flash, Basic, Standard, and Advanced parsing tiers address different quality and compute needs. The document library discovers files, caches parse results, searches content, resumes work by page or block, and preserves citation locators. Developers can use the Python SDK, V1 HTTP API, command-line tools, or Gradio WebUI. MinerU supports MCP and agent frameworks, with export to Dify and Notion. Documents are not automatically uploaded to the official service; remote parsing requires explicit configuration. Local WebUI and API server deployment is documented for Linux, macOS, and Windows, and self-hosted API connections are supported. The open-source project is free under its license, which sets commercial-use limits above 100 million monthly active users or USD 20 million monthly revenue and requires attribution for third-party online services based on MinerU.
For and against
For
- Broad document input support
- Multiple parsing quality tiers
- Searchable local document library
- Python SDK, API, CLI, and WebUI
- Local and self-hosted deployment options
Against
- Higher-throughput local use recommends 16 GB memory
- Commercial-use limits apply under the project license
- Remote parsing requires explicit configuration
The verdict
MinerU combines parsing, conversion, library search, and integration tools in one open-source project. Its local-processing approach and deployment choices suit privacy-conscious workflows, while hardware and license conditions deserve review.
Who it suits
MinerU suits teams processing mixed document formats locally or through APIs, including application and agent workflows. It is also relevant to users needing searchable libraries, OCR conversion, batch conversion, or self-hosting.
Plans and prices
Free
5 free pages every day · files up to 10 MB · images up to 5 MB · PDFs up to 5 pages
Read 15 Oct 2026 · mineru.io
Pro · Monthly
1,000 pages every month · files up to 200 MB · images up to 50 MB · PDFs up to 500 pages
Read 15 Oct 2026 · mineru.io
Pro · Annual
1,000 pages every month · files up to 200 MB · images up to 50 MB · PDFs up to 500 pages
Read 15 Oct 2026 · mineru.io
MinerU open-source software
Commercial license required above 100 million monthly active users or USD 20 million monthly revenue · online services must attribute MinerU
Read 5 Oct 2026 · github.com
On-premise
models and data run inside your network · dedicated support
Read 15 Oct 2026 · mineru.io
On the record
- Agent integrations
- The official site says MinerU supports the MCP protocol and agent frameworks, and offers export to Dify and Notion.mineru.net · read 5 Oct 2026
- API network limitation
- The hosted create-task API documentation warns that URLs hosted on GitHub, AWS and other overseas services may time out.mineru.net · read 15 Oct 2026
- API rate limits
- The hosted service documents 300 submit requests per minute, 1,000 result queries per minute and up to 10,000 files per day, subject to dynamic adjustment.mineru.net · read 15 Oct 2026
- Changelog license change
- Release 3.1.0 dated April 18, 2026 changed the project from AGPLv3 to the custom Apache-2.0-based MinerU Open Source License.opendatalab.github.io · read 15 Oct 2026
- Cloud lightweight API
- The Agent Lightweight API requires no login but is IP-rate-limited, handles one file up to 10 MB and 20 pages, and returns Markdown only.mineru.net · read 15 Oct 2026
- Cloud precision API
- The Precision Extract API requires a token, accepts files up to 200 MB and 600 pages, batches up to 200 files, and returns ZIP results with Markdown and JSON plus optional DOCX, HTML or LaTeX.mineru.net · read 15 Oct 2026
- Company headquarters and size
- Crunchbase lists OpenDataLab as a private for-profit organization headquartered in Shanghai with 51–100 employees.crunchbase.com · read 15 Oct 2026
- Company identity
- OpenDataLab's official site identifies it as the Data Platform Center of Shanghai Artificial Intelligence Laboratory and the maker of MinerU.opendatalab.github.io · read 15 Oct 2026
- Developer tooling
- Official tooling includes a Python SDK, V1 HTTP API, stateless batch conversion, multi-service Router and Gradio WebUI.opendatalab.github.io · read 15 Oct 2026
- Docker support
- The documented Docker workflow targets Linux NVIDIA GPUs and Windows WSL2; macOS Docker has no MPS acceleration and non-NVIDIA deployment is pending.opendatalab.github.io · read 15 Oct 2026
- Document library
- Its library discovers and caches files, supports content search and continuation by page or block, and preserves stable citation locators.opendatalab.github.io · read 15 Oct 2026
- Export formats
- The document model supports Markdown, HTML, LaTeX, DOCX, EPUB, PDF, Structured Content and Content List V1/V2 outputs.opendatalab.github.io · read 15 Oct 2026
- Hardware requirements
- The docs recommend at least 16 GB system memory for higher-throughput local deployments and at least 16 GB unified memory for Apple Silicon.opendatalab.github.io · read 5 Oct 2026
- Hosted service
- The official site links to online use and describes an official cloud service, but the opened pages did not state its pricing.mineru.net · read 5 Oct 2026
- Input formats
- Supported inputs include PDF, images, DOC/DOCX, PPT/PPTX, XLS/XLSX, RTF, OpenDocument, EPUB, OFD, HTML/MHTML and CSV/TSV.opendatalab.github.io · read 15 Oct 2026
- Installation
- The base package is installed with mineru>=4.0,<5 and includes the WebUI, ONNX runtime and llama.cpp VLM.opendatalab.github.io · read 15 Oct 2026
- Institution founding
- LinkedIn lists Shanghai Artificial Intelligence Laboratory as founded in 2020, headquartered in Shanghai, with 201–500 employees.linkedin.com · read 15 Oct 2026
- Integration
- MinerU provides a Python SDK, V1 HTTP API, command-line tools, and a Gradio-based WebUI.opendatalab.github.io · read 5 Oct 2026
