OCRRouter

DeepSeek-OCR vs Florence-2

Pick DeepSeek-OCR for self-hosted bulk conversion of full pages into Markdown, HTML or text with boxes, as long as you add checks for repeated tokens. Pick Florence-2 for short English text, scene text and labels where you need boxes from a 0.23B or 0.77B model, or where the same model must also do captioning or detection. The main split is output: DeepSeek-OCR returns document formats, Florence-2 returns only text and boxes.

DeepSeek-OCRdeepseek/deepseek-ocrFlorence-2microsoft/florence-2
TypeOpen sourceOpen source
Price1 credit / page1 credit / page
Per 1,000 pages$1.00$1.00
Typical speed1.1 s / page0.8 s / page
Best forCheap bulk conversionLightweight OCR with boxes
InputsPDF, imagesimages
Languages100+ languagesEnglish
Max pages per request200500
Tables✓ YesNo
HandwritingNoNo
Math✓ YesNo
Bounding boxes✓ Yes✓ Yes
ConfidenceNoNo
FormsNoNo
Multilingual✓ YesNo
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 DeepSeek-OCR if

  • You need page-level output in Markdown, plain text, HTML or bounding boxes, and Florence-2 gives no Markdown, tables or LaTeX.
  • You run bulk OCR on your own GPU and want throughput: the authors quote about 2,500 tokens per second on one A100-40G.
  • You want to tune cost per page, since resolution modes range from 64 to 400 vision tokens.

Choose Florence-2 if

  • You need a very small model: 0.23B base or 0.77B large, MIT licensed, for lightweight English OCR.
  • You want quadrilateral boxes per text line from OCR_WITH_REGION for scene text or short labels.
  • You also need captioning, detection or grounding from the same model in one pipeline.

Key differences

DeepSeek-OCRFlorence-2
LicenceMIT, commercial use allowedMIT
How you run itSelf-host with Transformers or vLLM; CUDA GPU, reference setup CUDA 11.8 and PyTorch 2.6 in bfloat16Self-host via Transformers; 0.23B (base) or 0.77B (large) parameters
PriceFree, you pay for computeFree, you pay for compute
Output formatsMarkdown, plain text, HTML, bounding boxesPlain text and bounding boxes only; no tables or LaTeX
ScopeOCR model that compresses pages into few vision tokensGeneral vision model: OCR plus captioning, detection and grounding
Languages and handwritingNot covered in the sourcesChinese output mostly wrong because the vocabulary lacks CJK characters; spelling errors and missing spaces on cursive handwriting and French text in the HF blog test
Known failureRepeated tokens and looping over table headers (GitHub issues #12 and #16); it corrects nonsense words instead of copying them, so odd codes may changeThe continued-pretrained checkpoint used only 0.1B samples, and the model card says it might not be well trained

Sources

What each one is

DeepSeek-OCR

Open-source vision model that compresses pages into few tokens.

DeepSeek-OCR 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": "deepseek/deepseek-ocr","fallbacks": ["microsoft/florence-2"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

DeepSeek-OCR alternativesFlorence-2 alternativesBest OCR models in 2026