Mistral OCR vs MinerU
Pick Mistral OCR if you want a hosted API for high-volume PDF to Markdown, with no servers to run. Pick MinerU if you need to self-host, parse Office files as well as PDFs, or run on a CPU-only machine. The main split is deployment: Mistral OCR is a paid proprietary API, MinerU is a free toolkit you run yourself.
Mistral OCRmistral/mistral-ocr | MinerUopendatalab/mineru | |
|---|---|---|
| Type | OCR API | Open source |
| Price | 25 credits / page | 2 credits / page |
| Per 1,000 pages | $25.00 | $2.00 |
| Typical speed | 0.9 s / page | 2.0 s / page |
| Best for | High-volume PDF to Markdown | Academic PDFs |
| Inputs | PDF, images | PDF, images |
| Languages | 100+ 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 Mistral OCR if
- You want a hosted API at $2 per 1,000 pages, or $1 per 1,000 pages through the Batch API, with no GPU or servers to manage.
- You process scanned business documents in batch and feed the Markdown into RAG.
- You need tables returned as HTML with rowspan and colspan, which OCR 3 reconstructs.
Choose MinerU if
- You must self-host and pay only for compute, with the option of a CPU-only tier that runs on about 2 GB RAM.
- Your corpus mixes PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML, and you want one tool for all of them.
- You work with Chinese and English academic papers, or need LaTeX, DOCX or EPUB output.
Key differences
| Mistral OCR | MinerU | |
|---|---|---|
| How you run it | Hosted API from Mistral AI (mistral-ocr-2512, OCR 3) | Self-hosted CLI, API or WebUI from OpenDataLab |
| Licence | Proprietary | MinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights tagged AGPL-3.0 |
| Price | $2 per 1,000 pages; $3 with structured annotations; $1 via Batch API | Free; you pay for compute |
| Hardware | None on your side | Basic ONNX tier: CPU, 2 GB RAM. VLM tiers: 16 GB RAM and a GPU with 8 GB+ VRAM |
| Output formats | Markdown, HTML, JSON, images | Markdown, HTML, LaTeX, DOCX, EPUB, JSON |
| Benchmark | OmniDocBench v1.6 overall: 85.66 (v1.5 for the first version, OCR 2503: 78.83) | olmOCR-Bench overall: 75.2 (MinerU 2.5.4); ParseBench mean: 45.9 (MinerU2.5). Different benchmarks, so scores are not directly comparable |
| Known failures | Hallucinated text on unreadable handwriting; changed checkbox states and misread characters on a dense financial table; colored-background pages returned as images without text (2025 release) | Merged header rows dropped in tables such as bank statements; repeated content producing 300 KB figure blocks; full-width Chinese punctuation converted to half-width with no switch |
Sources
- Mistral OCR 3 announcement
- OmniDocBench v1.6 leaderboard
- Reducto test of Mistral OCR
- MinerU GitHub README
- olmOCR-Bench table
- Issue #5554 table header rows
What each one is
Mistral OCR
Fast document OCR that returns clean Markdown with tables and embedded images.
Mistral 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.
PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?
Use one, fall back to the other
{"model": "mistral/mistral-ocr","fallbacks": ["opendatalab/mineru"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Mistral OCR vs DoclingMistral OCR vs Unlimited OCRGemini Flash vs MinerUMinerU vs ERNIE 4.5 VLMinerU vs DoclingMinerU vs OCR.spaceMistral OCR vs Adobe Acrobat OCRMistral OCR vs docTR
Mistral OCR alternativesMinerU alternativesBest OCR models in 2026