Tesseract vs Donut
Pick Tesseract for clean printed scans, offline searchable PDFs and cheap CPU batch OCR in many languages. Pick Donut when you have a narrow, fixed-layout document type such as receipts or forms and can fine-tune a model to return JSON fields. The main split is that Tesseract reads text out of the box, while Donut only works after you train it.
Tesseracttesseract/tesseract | Donutnaver/donut | |
|---|---|---|
| Type | Open source | Open source |
| Price | Free | 1 credit / page |
| Per 1,000 pages | $0.00 | $1.00 |
| Typical speed | 0.6 s / page | 1.0 s / page |
| Best for | Clean printed text, free | Receipt and form fields after fine-tuning |
| Inputs | PDF, images | images |
| Languages | 100+ languages | English, Chinese, Japanese, Korean |
| Max pages per request | 500 | 100 |
| Tables | No | No |
| Handwriting | No | No |
| Math | No | 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 Tesseract if
- It recognizes more than 100 languages out of the box, and you can train it for more.
- It runs on CPU only with no model server, so it suits small machines and offline use.
- It outputs plain text, hOCR, searchable PDF, TSV, ALTO and PAGE XML, and it is the engine behind OCRmyPDF.
Choose Donut if
- It maps a document image straight to structured JSON with no separate OCR step.
- It suits receipt and form field extraction and document classification on fixed layouts once fine-tuned.
- One Hacker News practitioner reports that about 200 documents of fine-tuning can reach human-level accuracy on narrow data.
Key differences
| Tesseract | Donut | |
|---|---|---|
| Licence | Apache-2.0 | MIT |
| How you run it | Local CLI or C++ library with an LSTM recognizer, CPU only, no GPU needed | Self-hosted transformer (Swin encoder, BART decoder) loaded through Hugging Face Transformers |
| Ready out of the box | Yes, with official models for printed text | No. The base checkpoint is pretrain-only and must be fine-tuned first |
| Output | Plain text, hOCR, searchable PDF, TSV, ALTO, PAGE XML | JSON, plain text |
| Price | Free, self-hosted (you pay for compute) | Free, self-hosted (you pay for compute) |
| Input handling | Accuracy drops sharply without binarization, deskew and roughly 300 DPI input | Misses tiny text in large images because of input resolution limits |
| Known failure | Confuses digit 1 with lowercase l (issue #2753); no table, formula or reading-order output; not built for handwriting | One HN user found results on personal documents did not match the promised scores; Transformers v5 dropped image-to-text pipeline support, so you need direct loading or v4 |
Sources
- Tesseract GitHub README
- Improving quality (tessdoc)
- Issue #2753 1 vs l
- donut-base model card
- Donut ECCV paper
- Hacker News thread
What each one is
Donut
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": "tesseract/tesseract","fallbacks": ["naver/donut"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Tesseract vs GOT-OCR 2.0Tesseract vs NougatPaddleOCR (PP-OCR) vs DonutDocling vs DonutAmazon Textract vs TesseractPaddleOCR-VL vs TesseractDocling vs TesseractTesseract vs Qwen-VL
Tesseract alternativesDonut alternativesBest OCR models in 2026