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/mineru | Typhoon OCRtyphoon/typhoon-ocr | |
|---|---|---|
| Type | Open source | Open source |
| Price | 2 credits / page | 2 credits / page |
| Per 1,000 pages | $2.00 | $2.00 |
| Typical speed | 2.0 s / page | 1.8 s / page |
| Best for | Academic PDFs | Thai documents |
| Inputs | PDF, images | PDF, images |
| Languages | 80+ languages | Thai, English |
| Max pages per request | 500 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | No |
| Bounding boxes | ✓ Yes | No |
| 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 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
| MinerU | Typhoon OCR | |
|---|---|---|
| Language focus | Chinese and English academic papers are a listed strength | Thai and English only; no other languages were evaluated |
| How you run it | Self-host only, as a CLI, API or WebUI | Self-host the weights or use the Typhoon API (typhoon-ocr-v2) |
| Licence | MinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights tagged AGPL-3.0 | Apache-2.0, subject to OpenTyphoon Terms and Conditions |
| Input and output | Inputs: PDF, images, DOCX, PPTX, XLSX, EPUB, OFD, HTML. Outputs: Markdown, HTML, LaTeX, DOCX, EPUB, JSON | Outputs: Markdown, HTML, LaTeX |
| Hardware and size | Basic ONNX tier on CPU with 2 GB RAM; VLM tiers need 16 GB RAM and a GPU with 8 GB+ VRAM; VLM is 1.2B | 2B model (V2 and V1.5) with a 0.8B V2 variant; hardware needs not published |
| olmOCR-Bench | 75.2 (MinerU 2.5.4, independent) | 84.7 (V2 2B, reported by the authors) |
| Known failure | VLM tiers drop merged header rows in tables such as bank statement account lines, and can repeat content into 300 KB figure blocks | V2 can loop until the token limit on dense multi-column pages; key-information extraction is weakest at 21.0 on ThaiOCRBench |
Sources
- MinerU GitHub README
- olmOCR-Bench table
- Issue #5554 table header rows
- Typhoon OCR V2 2B model card
- Typhoon OCR technical report
What each one is
MinerU
Open-source PDF to Markdown pipeline popular for academic and Chinese documents.
MinerU detailsTyphoon OCR
Open vision model tuned for Thai and English documents, with Markdown output.
Typhoon OCR 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": "opendatalab/mineru","fallbacks": ["typhoon/typhoon-ocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
MinerU vs Florence-2MinerU vs GOT-OCR 2.0Docling vs Typhoon OCRUnlimited OCR vs Typhoon OCRMinerU vs DoclingTyphoon OCR vs UnstructuredTrOCR vs Typhoon OCRMinerU vs Phi-4-multimodal
MinerU alternativesTyphoon OCR alternativesBest OCR models in 2026