OCRRouter

Qianfan OCR vs Nanonets-OCR

Pick Qianfan OCR for self-hosted multilingual parsing, tables, formulas and key information extraction, where it has an Apache-2.0 licence and a published OmniDocBench v1.5 score of 93.12. Pick Nanonets-OCR for printed business documents that need signatures, watermarks and checkboxes tagged, or flowcharts turned into Mermaid. Nanonets-OCR scores 69.5 on olmOCR-Bench against 79.8 for Qianfan OCR, so it is the weaker general parser.

Qianfan OCRbaidu/qianfan-ocrNanonets-OCRnanonets/nanonets-ocr
TypeOCR APIOpen source
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed2.0 s / page1.8 s / page
Best forChinese documentsMarkdown with semantic tags
InputsPDF, imagesPDF, images
LanguagesChinese, English and moreMultilingual
Max pages per request200500
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
Math✓ Yes✓ Yes
Bounding boxesNoNo
ConfidenceNoNo
FormsNo✓ Yes
Multilingual✓ Yes✓ Yes
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

  • It scores 79.8 on olmOCR-Bench, against 69.5 for Nanonets-OCR2-3B.
  • It covers 192 languages, handwriting and scene text, while Nanonets-OCR was not trained on handwriting and can hallucinate.
  • It is Apache-2.0 licensed, so commercial use is allowed, and it can also be used hosted on the Baidu Qianfan platform.

Choose Nanonets-OCR if

  • It tags signatures, watermarks and image descriptions, and converts checkboxes to unicode symbols.
  • It extracts flowcharts and org charts as Mermaid code, which Qianfan OCR does not list as an output.
  • It is a 3B model fine-tuned from Qwen2.5-VL-3B, and it distinguishes inline and display LaTeX equations.

Key differences

Qianfan OCRNanonets-OCR
LicenceApache-2.0Not stated on the Nanonets-OCR2-3B model card (no license tag)
How you run itSelf-host the open weights, or use the Baidu Qianfan platformSelf-host the weights from Hugging Face only
Output formatsMarkdown, JSON, HTML, LaTeX, bounding boxesMarkdown, HTML, LaTeX, Mermaid
olmOCR-Bench79.869.5 (OCR2-3B)
HandwritingListed as supported, along with scene textNot trained on handwriting. One handwriting test saw generation loops with CER up to 2100%
PromptsThinking mode can emit up to 16,384 tokens, adding latencyTrained on a fixed prompt. The team says hallucination with other prompts is expected
Speed and hardware1.024 pages per second on one A100 with W8A8. Not suited to CPU-only deploymentNot published

Sources

What each one is

Qianfan OCR

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

Qianfan OCR details

Nanonets-OCR

Open image-to-Markdown model that tags tables, equations, signatures, watermarks and checkboxes.

Nanonets-OCR 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": ["nanonets/nanonets-ocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Qianfan OCR alternativesNanonets-OCR alternativesBest OCR models in 2026