Unlimited OCR vs MinerU
Pick Unlimited OCR for long reports and books that you want parsed in one request, with an MIT licence and bounding boxes in the output. Pick MinerU for mixed PDF and Office corpora, for many output formats, or when you have no GPU. The main split is scope: Unlimited OCR is a long-document parser that needs a CUDA GPU, while MinerU is a wider toolkit with a CPU tier.
Unlimited OCRbaidu/unlimited-ocr | MinerUopendatalab/mineru | |
|---|---|---|
| Type | Open source | Open source |
| Price | 2 credits / page | 2 credits / page |
| Per 1,000 pages | $2.00 | $2.00 |
| Typical speed | 1.2 s / page | 2.0 s / page |
| Best for | Books and very long documents | Academic PDFs |
| Inputs | PDF, images | PDF, images |
| Languages | 30+ languages | 80+ languages |
| Max pages per request | 1,000 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | ✓ Yes |
| On OCRRouter | Available | Available |
Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.
Which to choose
Choose Unlimited OCR if
- It parses 40+ pages in a single forward pass with roughly constant memory, so long reports and books go in as one request.
- The MIT licence allows commercial use with no copyleft.
- It returns block types and bounding boxes alongside text, which suits layout-aware extraction.
Choose MinerU if
- It accepts PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML in one tool, which fits mixed Office and PDF corpora.
- The basic ONNX tier runs on CPU with about 2 GB RAM, so you can start without a GPU.
- It renders to Markdown, HTML, LaTeX, DOCX, EPUB and JSON, and it is aimed at Chinese and English academic papers.
Key differences
| Unlimited OCR | MinerU | |
|---|---|---|
| Licence | MIT | MinerU Open Source License (Apache-2.0 based with extra conditions); the MinerU2.5 VLM weights are tagged AGPL-3.0 |
| How you run it | Self-host with vLLM, SGLang or transformers; also hosted in Baidu Cloud's OCR product | Self-host only, as a CLI, API or WebUI |
| Hardware | NVIDIA GPU with CUDA 12.9 or 13.0; Unlimited OCR 2 under SGLang runs out of memory on 12 GB GPUs | Basic tier runs on CPU with 2 GB RAM; VLM tiers need 16 GB RAM and a GPU with 8 GB+ VRAM |
| Input and output | Multi-page documents in one pass, context capped at 32,768 tokens; outputs Markdown, plain text and bounding boxes | PDF, images and Office files in; Markdown, HTML, LaTeX, DOCX, EPUB and JSON out |
| Independent benchmark | ParseBench mean 46.17 | ParseBench mean 45.9; olmOCR-Bench overall 75.2 (MinerU 2.5.4) |
| Formatting and tables | ParseBench text formatting score is 0.97, so bold and italic styling is mostly lost | VLM tiers drop merged header rows in tables such as bank statement account lines (issue #5554) |
| Known failure | Text repetition and looping (issue #55), hallucinated text (issue #58), bbox coordinate loops on GB10 GPUs under SGLang (issue #114) | Repeated content producing 300 KB figure blocks (issue #5728); full-width Chinese punctuation converted to half-width with no switch (issue #5765) |
Sources
- Hugging Face model card (Unlimited OCR)
- Unlimited OCR GitHub repo
- MinerU GitHub README
- MinerU2.5 model card
- olmOCR-Bench table
- Issue #5554 table header rows
What each one is
Unlimited OCR
Open-source model from Baidu that reads hundreds of pages in one pass with flat memory use.
Unlimited OCR detailsMinerU
Open-source PDF to Markdown pipeline popular for academic and Chinese documents.
MinerU detailsTry both on your own file
Run the file once with each model and compare the output.
Use one, fall back to the other
{"model": "baidu/unlimited-ocr","fallbacks": ["opendatalab/mineru"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Unlimited OCR alternativesMinerU alternativesBest OCR models in 2026