MinerU vs Chunkr
Pick MinerU for mixed corpora of PDFs and Office files, especially Chinese and English academic papers, and for CPU-only batch runs. Pick Chunkr when you want layout parsing with bounding boxes and semantic chunking for RAG, with a hosted API or a self-hosted Docker setup. MinerU is a local toolkit with a published olmOCR-Bench score of 75.2, while Chunkr offers a cloud option and publishes no benchmark.
MinerUopendatalab/mineru | Chunkrchunkr/chunkr | |
|---|---|---|
| Type | Open source | OCR API |
| Price | 2 credits / page | 14 credits / page |
| Per 1,000 pages | $2.00 | $14.00 |
| Typical speed | 2.0 s / page | 3.0 s / page |
| Best for | Academic PDFs | Layout-aware chunks for RAG |
| Inputs | PDF, images | PDF, images, DOCX |
| Languages | 80+ languages | Multilingual |
| Max pages per request | 500 | 1,000 |
| 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 MinerU if
- You have a mixed corpus: it reads PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML in one tool.
- You have no GPU: the basic ONNX tier runs on CPU with about 2 GB RAM.
- You need many output formats: Markdown, HTML, LaTeX, DOCX, EPUB and JSON.
Choose Chunkr if
- You want a hosted API as well as a self-host option, so you can start in the cloud and move later.
- You need OCR with bounding boxes plus semantic chunking of PDFs and slides for RAG.
- You already run an OpenAI-compatible LLM endpoint that the self-hosted version can use.
Key differences
| MinerU | Chunkr | |
|---|---|---|
| How you run it | Self-host only: CLI, API or WebUI. | Cloud API or self-host via Docker (GPU, CPU-only and Mac ARM options). |
| Licence | MinerU Open Source License (Apache-2.0 based with extra conditions). The MinerU2.5 VLM weights are tagged AGPL-3.0. | AGPL-3.0 or a commercial licence. Closed-source use needs the commercial licence. |
| Price | Free. You pay for compute. | Hosted credit-based plans, official prices not published. Open-source version is free, but you pay for compute and an LLM endpoint. |
| Input formats | PDF, images, DOCX, PPTX, XLSX, EPUB, OFD, HTML. | PDF, PPT, Word and images. Excel is not supported in the open-source version. |
| Output formats | Markdown, HTML, LaTeX, DOCX, EPUB, JSON. | HTML, Markdown, JSON and bounding boxes. |
| Hardware | CPU with 2 GB RAM for the basic tier. VLM tiers need 16 GB RAM and a GPU with 8 GB+ VRAM. | Not published. Self-host also needs an external LLM endpoint. |
| Benchmark and known failures | olmOCR-Bench overall 75.2 (MinerU 2.5.4). VLM tiers drop merged header rows in tables such as bank statements, and can repeat content in 300 KB figure blocks. | Not published. The open-source version uses community models that are less accurate than the cloud's in-house models. |
Sources
- MinerU GitHub README
- olmOCR-Bench table
- Issue #5554 table header rows
- Issue #5728 repetition
- Chunkr GitHub README
- Chunkr site
What each one is
MinerU
Open-source PDF to Markdown pipeline popular for academic and Chinese documents.
MinerU detailsChunkr
Document parsing API that segments and chunks pages for RAG. Self-hostable version available.
Chunkr 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": "opendatalab/mineru","fallbacks": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
MinerU alternativesChunkr alternativesBest OCR models in 2026