Marker vs MinerU
Pick Marker for self-hosted PDF to Markdown on books and papers with equations, or when you want RAG chunks, as long as the weight licence fits your company. Pick MinerU for mixed PDF and Office corpora, Chinese and English papers, or CPU-only batch jobs. Marker has the higher olmOCR-bench score (83.7, reported by its authors) against 75.2 for MinerU 2.5.4 (independent).
Markerdatalab/marker | MinerUopendatalab/mineru | |
|---|---|---|
| Type | OCR API | Open source |
| Price | 14 credits / page | 2 credits / page |
| Per 1,000 pages | $14.00 | $2.00 |
| Typical speed | 2.5 s / page | 2.0 s / page |
| Best for | Books and research papers | Academic PDFs |
| Inputs | PDF, images, DOCX | PDF, images |
| Languages | 90+ 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 Marker if
- Its vllm mode scores 83.7 on olmOCR-bench, though that number comes from Datalab itself.
- You can use a hosted API from Datalab with about 5,000 free pages per month instead of running your own servers.
- It outputs RAG chunks and JSON block trees, and it suits books and papers with equations.
Choose MinerU if
- It accepts PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML in one tool, which suits mixed corpora.
- Its basic ONNX tier runs on CPU with about 2 GB RAM, so you can start without a GPU.
- It can render to Markdown, HTML, LaTeX, DOCX and EPUB, and it targets Chinese and English academic papers.
Key differences
| Marker | MinerU | |
|---|---|---|
| Licence | Code Apache-2.0; weights under a modified AI Pubs Open Rail-M licence, free for research, personal use and startups under $5M | MinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights tagged AGPL-3.0 |
| How you run it | Local on GPU, CPU or Apple Silicon, or Datalab's hosted API | Self-host only, as CLI, API or WebUI |
| Price | Free self-hosted within the weight licence; hosted API has about 5,000 free pages per month, then paid plans | Free, self-hosted; you pay for compute |
| Hardware | vllm mode needs an NVIDIA GPU; fast mode runs on CPU with about 18 MB of ONNX weights | Basic tier runs on CPU with 2 GB RAM; VLM tiers need 16 GB RAM and a GPU with 8 GB+ VRAM |
| Input formats | Not published | PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML |
| olmOCR-bench overall | 83.7 in vllm mode (authors' own number); 66.6 in CPU fast mode | 75.2 for MinerU 2.5.4 (independent) |
| Known failure | Not published | VLM tiers drop merged header rows in tables such as bank statement account lines; the VLM pipeline can repeat content and produce 300 KB figure blocks |
Sources
- Marker GitHub README
- Datalab pricing
- MinerU GitHub README
- olmOCR-Bench table
- Issue #5554 table header rows
- Issue #5728 repetition
What each one is
Marker
Hosted version of the open-source Marker and Surya models. Strong on books and papers.
Marker 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": "datalab/marker","fallbacks": ["opendatalab/mineru"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Marker alternativesMinerU alternativesBest OCR models in 2026