OCRRouter

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-ocrMinerUopendatalab/mineru
TypeOCR APIOpen source
Price25 credits / page2 credits / page
Per 1,000 pages$25.00$2.00
Typical speed0.9 s / page2.0 s / page
Best forHigh-volume PDF to MarkdownAcademic PDFs
InputsPDF, imagesPDF, images
Languages100+ languages80+ languages
Max pages per request1,000500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxes✓ Yes✓ Yes
ConfidenceNoNo
FormsNoNo
Multilingual✓ Yes✓ Yes
On OCRRouterAvailableAvailable

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 OCRMinerU
How you run itHosted API from Mistral AI (mistral-ocr-2512, OCR 3)Self-hosted CLI, API or WebUI from OpenDataLab
LicenceProprietaryMinerU 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 APIFree; you pay for compute
HardwareNone on your sideBasic ONNX tier: CPU, 2 GB RAM. VLM tiers: 16 GB RAM and a GPU with 8 GB+ VRAM
Output formatsMarkdown, HTML, JSON, imagesMarkdown, HTML, LaTeX, DOCX, EPUB, JSON
BenchmarkOmniDocBench 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 failuresHallucinated 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

What each one is

Mistral OCR

Fast document OCR that returns clean Markdown with tables and embedded images.

Mistral OCR details

MinerU

Open-source PDF to Markdown pipeline popular for academic and Chinese documents.

MinerU details

Try 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 alternativesMinerU alternativesBest OCR models in 2026