OCRRouter

Qianfan OCR vs Florence-2

Pick Qianfan OCR for full-page document parsing: it outputs Markdown, JSON, HTML and LaTeX, covers 192 languages and handles handwriting, tables and formulas. Pick Florence-2 for small, English scene text or short labels where you need boxes and a 0.23B or 0.77B model. The main split is structure and language: Florence-2 returns only text and boxes, and its Chinese output is mostly wrong.

Qianfan OCRbaidu/qianfan-ocrFlorence-2microsoft/florence-2
TypeOCR APIOpen source
Price2 credits / page1 credit / page
Per 1,000 pages$2.00$1.00
Typical speed2.0 s / page0.8 s / page
Best forChinese documentsLightweight OCR with boxes
InputsPDF, imagesimages
LanguagesChinese, English and moreEnglish
Max pages per request200500
Tables✓ YesNo
Handwriting✓ YesNo
Math✓ YesNo
Bounding boxesNo✓ 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 Qianfan OCR if

  • You need structured output such as Markdown, JSON, HTML, LaTeX or bounding boxes from full documents.
  • You parse multilingual files, handwriting or scene text, since it covers 192 languages.
  • You want a measured document score: 93.12 on OmniDocBench v1.5, plus 79.8 on olmOCR-Bench and 880 on OCRBench.

Choose Florence-2 if

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

Key differences

Qianfan OCRFlorence-2
Model size4B (Qwen3-4B language model)0.23B (base), 0.77B (large)
LicenceApache-2.0, allows commercial useMIT
How you run itSelf-host the open weights, or use the Baidu Qianfan platformSelf-host via Transformers only
Output formatsMarkdown, JSON, HTML, LaTeX, bounding boxesPlain text and bounding boxes. No Markdown, tables or LaTeX
Languages and handwriting192 languages, handwriting and scene textChinese output mostly wrong because the vocabulary lacks CJK characters. Spelling errors and missing spaces on cursive handwriting and French text in one test
BenchmarksOmniDocBench v1.5 93.12, olmOCR-Bench 79.8, OCRBench 880TextCaps CIDEr zero-shot 72.8 (large), COCO detection mAP zero-shot 37.5 (large). No document OCR benchmark published
Known limits1.024 pages per second on an A100 even with W8A8. Thinking mode can emit up to 16,384 tokens. Not suited to CPU-only deploymentModel card notes the continued-pretrained checkpoint used only 0.1B samples and might not be well trained

Sources

What each one is

Qianfan OCR

Baidu's OCR-tuned vision model. Strong on Chinese documents and tables.

Qianfan 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": "baidu/qianfan-ocr","fallbacks": ["microsoft/florence-2"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Qianfan OCR alternativesFlorence-2 alternativesBest OCR models in 2026