OCRRouter

Donut vs Florence-2

Pick Donut if you will fine-tune a model for one fixed document type, such as receipts or forms, and want JSON out. Pick Florence-2 if you need text with bounding boxes from scene text or short labels, or a small English OCR model that also does detection. Neither one converts full pages to Markdown, and Donut needs training before it works at all.

Donutnaver/donutFlorence-2microsoft/florence-2
TypeOpen sourceOpen source
Price1 credit / page1 credit / page
Per 1,000 pages$1.00$1.00
Typical speed1.0 s / page0.8 s / page
Best forReceipt and form fields after fine-tuningLightweight OCR with boxes
Inputsimagesimages
LanguagesEnglish, Chinese, Japanese, KoreanEnglish
Max pages per request100500
TablesNoNo
HandwritingNoNo
MathNoNo
Bounding boxesNo✓ Yes
ConfidenceNoNo
Forms✓ YesNo
MultilingualNoNo
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 Donut if

  • It maps a document image straight to structured JSON with no separate OCR step.
  • It suits narrow, fixed-layout documents like receipts and forms, and a practitioner on Hacker News reports about 200 fine-tuning documents can reach human-level accuracy on narrow data.
  • It also supports document classification after fine-tuning, which Florence-2 does not list.

Choose Florence-2 if

  • It is small: 0.23B (base) or 0.77B (large) parameters, which fits lightweight edge OCR in English.
  • OCR_WITH_REGION returns quadrilateral boxes per text line, so you get positions along with the text.
  • One model also handles captioning, detection and grounding, so a single pipeline can cover more than OCR.

Key differences

DonutFlorence-2
LicenceMITMIT
How you run itSelf-hosted. The base checkpoint is pretrain-only and must be fine-tuned first.Self-hosted via Transformers. It has OCR tasks built in through prompts.
OutputJSON and plain textPlain text and bounding boxes. No Markdown, tables or LaTeX.
Model sizeNot published0.23B (base), 0.77B (large)
BenchmarksNot publishedTextCaps CIDEr zero-shot (large): 72.8. COCO detection mAP zero-shot (large): 37.5. Both reported by the authors.
Languages and handwritingNot publishedChinese output is mostly wrong because the vocabulary lacks CJK characters. A Hugging Face blog test found spelling errors and missing spaces on cursive handwriting and French text.
Known failureMisses tiny text in large images because of input resolution limits. Transformers v5 dropped image-to-text pipeline support, so you need direct loading or v4.Not suited to full-page document conversion. The continued-pretrained checkpoint used only 0.1B samples and might not be well trained.

Sources

What each one is

Donut

OCR-free document understanding model. Fine-tuned for receipts, forms and document Q&A.

Donut details

Florence-2

Small Microsoft vision model (0.23B and 0.77B) with OCR and OCR-with-regions tasks that return text with boxes.

Florence-2 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": "naver/donut","fallbacks": ["microsoft/florence-2"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Donut alternativesFlorence-2 alternativesBest OCR models in 2026