OCRRouter

Reducto Parse vs MinerU

Pick Reducto Parse for dense financial tables and regulated healthcare or finance documents, where you need a hosted API, SOC 2 Type II and HIPAA support, and zero data retention. Pick MinerU for Chinese and English academic papers or mixed Office and PDF corpora that you want to convert on your own hardware at no licence fee. The main split is a paid, proprietary API with compliance cover against a free, self-hosted toolkit with a custom licence and known table and repetition bugs.

Reducto Parsereducto/parseMinerUopendatalab/mineru
TypeOCR APIOpen source
Price20 credits / page2 credits / page
Per 1,000 pages$20.00$2.00
Typical speed4.0 s / page2.0 s / page
Best forHigh-stakes complex documentsAcademic PDFs
InputsPDF, images, DOCXPDF, images
Languages50+ languages80+ languages
Max pages per request1,000500
Tables✓ Yes✓ Yes
HandwritingNoNo
MathNo✓ Yes
Bounding boxes✓ Yes✓ Yes
Confidence✓ YesNo
Forms✓ YesNo
MultilingualNo✓ 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 Reducto Parse if

  • It reports 90.2% average table accuracy on RD-TableBench, versus 82.7% for Azure and 80.9% for Textract, though it built and ran that benchmark itself.
  • It offers SOC 2 Type II, HIPAA with BAAs and zero data retention, which suits regulated healthcare and finance documents.
  • It runs hosted, in a VPC, on-prem or air-gapped, so you get an API without running models yourself.

Choose MinerU if

  • It costs nothing to license and runs locally, so you only pay for compute.
  • It reads PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML and writes Markdown, HTML, LaTeX, DOCX, EPUB or JSON.
  • Its basic tier runs on CPU with about 2 GB RAM, so you can start batch conversion without a GPU.

Key differences

Reducto ParseMinerU
LicenceProprietaryMinerU Open Source License (Apache-2.0 based with extra conditions); the MinerU2.5 VLM weights are tagged AGPL-3.0
How you run itHosted, VPC, on-prem or air-gappedSelf-host only, as a CLI, API or WebUI
Price15,000 free credits, then $0.015 per credit; standard parse is 1 credit per page; batch queue 20% off parsingFree; you pay for compute
Output formatsMarkdown, JSON, HTML, bounding boxesMarkdown, HTML, LaTeX, DOCX, EPUB, JSON
HardwareNot publishedBasic ONNX tier: CPU with 2 GB RAM. VLM tiers: 16 GB RAM and a GPU with 8 GB+ VRAM
Benchmark90.2% on RD-TableBench (self-built, self-run)75.2 on olmOCR-Bench overall and 45.9 ParseBench mean (independent)
Known failureChaining Parse and Extract bills credits per endpoint per pageVLM tiers drop merged header rows in tables such as bank statement account lines (issue #5554), and the VLM pipeline can repeat content into 300 KB figure blocks (issue #5728)

Sources

What each one is

Reducto Parse

High-accuracy parsing for complex financial and legal documents, with citations.

Reducto Parse 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": "reducto/parse","fallbacks": ["opendatalab/mineru"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Reducto Parse alternativesMinerU alternativesBest OCR models in 2026