Qianfan OCR vs Donut
Pick Qianfan OCR for full-page parsing of multilingual documents with tables, formulas and handwriting, where you want Markdown, JSON or HTML out of the box. Pick Donut for narrow, fixed-layout jobs such as receipts and forms, where you can fine-tune on your own labelled samples. The main split is that Qianfan OCR works without training and Donut does not.
Qianfan OCRbaidu/qianfan-ocr | Donutnaver/donut | |
|---|---|---|
| Type | OCR API | Open source |
| Price | 2 credits / page | 1 credit / page |
| Per 1,000 pages | $2.00 | $1.00 |
| Typical speed | 2.0 s / page | 1.0 s / page |
| Best for | Chinese documents | Receipt and form fields after fine-tuning |
| Inputs | PDF, images | images |
| Languages | Chinese, English and more | English, Chinese, Japanese, Korean |
| Max pages per request | 200 | 100 |
| Tables | ✓ Yes | No |
| Handwriting | ✓ Yes | No |
| Math | ✓ Yes | No |
| Bounding boxes | No | No |
| Confidence | No | No |
| Forms | No | ✓ Yes |
| Multilingual | ✓ Yes | No |
| 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 Qianfan OCR if
- You need full-page output in Markdown, JSON, HTML, LaTeX or bounding boxes, and Donut lists only JSON and plain text.
- You process many languages, handwriting or scene text, since Qianfan OCR covers 192 languages.
- You want a published benchmark: 93.12 on OmniDocBench v1.5, plus 79.8 on olmOCR-Bench and 880 on OCRBench.
Choose Donut if
- You have a narrow, fixed-layout document type such as receipts or forms and can fine-tune a model for it.
- You want a permissive MIT licence and loading through Hugging Face Transformers, with no external OCR step.
- You want a base model to adapt for classification or VQA, not only parsing.
Key differences
| Qianfan OCR | Donut | |
|---|---|---|
| Ready to use | Used directly for document parsing; also offered hosted on the Baidu Qianfan platform | Base checkpoint is pretrain-only and must be fine-tuned before use |
| Licence | Apache-2.0, allows commercial use | MIT |
| Output formats | Markdown, JSON, HTML, LaTeX, bounding boxes | JSON, plain text |
| Benchmarks | OmniDocBench v1.5 overall 93.12; olmOCR-Bench 79.8; OCRBench 880 (author-reported) | Not published |
| Languages and content | 192 languages, handwriting and scene text | Not published |
| Hardware and speed | 4B parameters; benchmarked on one A100 with vLLM at 1.024 pages per second with W8A8; not suited to CPU-only deployment | Not published |
| Known failure | Thinking mode can emit up to 16,384 tokens, adding latency | Misses tiny text in large images because of input resolution limits; Transformers v5 dropped image-to-text pipeline support, so use direct loading or v4 |
Sources
What each one is
Qianfan OCR
Baidu's OCR-tuned vision model. Strong on Chinese documents and tables.
Qianfan OCR detailsDonut
OCR-free document understanding model. Fine-tuned for receipts, forms and document Q&A.
Donut 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": "baidu/qianfan-ocr","fallbacks": ["naver/donut"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Qianfan OCR vs GOT-OCR 2.0Qianfan OCR vs NougatPaddleOCR-VL vs DonutJina OCR vs DonutQianfan OCR vs PaddleOCR (PP-OCR)Donut vs ABBYY FineReaderQianfan OCR vs Adobe Acrobat OCRDonut vs Tesseract.js
Qianfan OCR alternativesDonut alternativesBest OCR models in 2026