OCRRouter

GPT vs MinerU

Pick GPT when you need handwriting, custom JSON extraction or document question answering through a hosted API. Pick MinerU when you want to self-host, convert Chinese and English papers or mixed Office and PDF files, or run batch jobs on CPU. The main split is a paid, closed API versus a free, local toolkit with licence strings attached.

GPTopenai/gptMinerUopendatalab/mineru
TypeVision modelOpen source
Price11 credits / page2 credits / page
Per 1,000 pages$11.00$2.00
Typical speed2.4 s / page2.0 s / page
Best forMessy scans, custom instructionsAcademic PDFs
InputsPDF, imagesPDF, images
Languages50+ languages80+ languages
Max pages per request100500
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
Math✓ Yes✓ Yes
Bounding boxesNo✓ 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 GPT if

  • It was reported at about 5% errors on messy cursive, against about 30% for Mistral OCR, so it suits handwritten notes.
  • You can prompt it to extract straight into custom JSON, or to answer questions about a document.
  • It is a hosted API that takes files up to 50 MB per request, so there is nothing to deploy.

Choose MinerU if

  • It is free to self-host and the basic tier runs on CPU with about 2 GB RAM, so you pay only for compute.
  • It reads PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML and renders to Markdown, HTML, LaTeX, DOCX, EPUB or JSON.
  • The VLM tier reaches 2.12 pages per second on one A100 with vLLM, and it targets Chinese and English academic papers.

Key differences

GPTMinerU
How you run itHosted OpenAI APISelf-host as CLI, API or WebUI
LicenceProprietaryMinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights tagged AGPL-3.0
PriceToken-based; page images add input tokens, so cost per page is not fixedFree software; you pay for compute
Output formatsMarkdown, JSON, plain textMarkdown, HTML, LaTeX, DOCX, EPUB, JSON
BenchmarkOmniDocBench v1.5 overall 85.50 (GPT-5.2); v1.6 overall 86.59olmOCR-Bench overall 75.2 (MinerU 2.5.4); ParseBench mean 45.9 (MinerU2.5). Different benchmarks, so not directly comparable
CoordinatesNo bounding boxes or confidence scores in the standard responseNot published
Known failureCost varies with page images; scored below Gemini 3 Pro (90.33) on OmniDocBench v1.5VLM tiers drop merged header rows in tables such as bank statements; repeated content can produce 300 KB figure blocks; full-width Chinese punctuation becomes half-width with no switch

Sources

What each one is

GPT

General vision model. Good at messy scans and following extraction instructions.

GPT 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": "openai/gpt","fallbacks": ["opendatalab/mineru"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

GPT alternativesMinerU alternativesBest OCR models in 2026