OCRRouter

MinerU vs Typhoon OCR

Pick MinerU for mixed Office and PDF corpora, Chinese and English academic papers, or CPU-only batch conversion. Pick Typhoon OCR for Thai and Thai-English documents such as government forms and financial reports. The main split is language focus: MinerU is a broad document toolkit, Typhoon OCR is a 2B model tuned for Thai.

MinerUopendatalab/mineruTyphoon OCRtyphoon/typhoon-ocr
TypeOpen sourceOpen source
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed2.0 s / page1.8 s / page
Best forAcademic PDFsThai documents
InputsPDF, imagesPDF, images
Languages80+ languagesThai, English
Max pages per request500500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ YesNo
Bounding boxes✓ YesNo
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 MinerU if

  • It accepts PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML in one tool, so mixed corpora need no separate converters.
  • Its basic tier runs on CPU with about 2 GB RAM, so you can start batch conversion without a GPU.
  • It renders to Markdown, HTML, LaTeX, DOCX, EPUB and JSON, which suits RAG pipelines and downstream editing.

Choose Typhoon OCR if

  • V1.5 beat GPT-5 and Gemini 2.5 Pro on Thai government forms (BLEU 0.870), and V2 2B scores 81.3 on MDPBench Thai pages versus 61.3 for its base model.
  • It outputs tables as HTML with merged cells, equations as LaTeX and marked checkboxes, and V2 2B scores 84.7 on olmOCR-bench at only 2B parameters.
  • You can self-host the weights or call the Typhoon API as typhoon-ocr-v2, and there is a 0.8B V2 variant.

Key differences

MinerUTyphoon OCR
Language focusChinese and English academic papers are a listed strengthThai and English only; no other languages were evaluated
How you run itSelf-host only, as a CLI, API or WebUISelf-host the weights or use the Typhoon API (typhoon-ocr-v2)
LicenceMinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights tagged AGPL-3.0Apache-2.0, subject to OpenTyphoon Terms and Conditions
Input and outputInputs: PDF, images, DOCX, PPTX, XLSX, EPUB, OFD, HTML. Outputs: Markdown, HTML, LaTeX, DOCX, EPUB, JSONOutputs: Markdown, HTML, LaTeX
Hardware and sizeBasic ONNX tier on CPU with 2 GB RAM; VLM tiers need 16 GB RAM and a GPU with 8 GB+ VRAM; VLM is 1.2B2B model (V2 and V1.5) with a 0.8B V2 variant; hardware needs not published
olmOCR-Bench75.2 (MinerU 2.5.4, independent)84.7 (V2 2B, reported by the authors)
Known failureVLM tiers drop merged header rows in tables such as bank statement account lines, and can repeat content into 300 KB figure blocksV2 can loop until the token limit on dense multi-column pages; key-information extraction is weakest at 21.0 on ThaiOCRBench

Sources

What each one is

MinerU

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

MinerU details

Typhoon OCR

Open vision model tuned for Thai and English documents, with Markdown output.

Typhoon OCR 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": "opendatalab/mineru","fallbacks": ["typhoon/typhoon-ocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

MinerU alternativesTyphoon OCR alternativesBest OCR models in 2026