OCRRouter

Qianfan OCR vs Surya

Pick Qianfan OCR if you self-host on a GPU and need handwriting, scene text, key information extraction or Markdown output across 192 languages. Pick Surya if you need layout detection, reading order and bounding boxes, or want to run locally on a laptop or CPU. The main split is scope: Qianfan OCR is a 4B end-to-end parser, while Surya is a 689M toolkit with a lighter footprint and a revenue-based licence limit.

Qianfan OCRbaidu/qianfan-ocrSuryadatalab/surya
TypeOCR APIOpen source
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed2.0 s / page1.5 s / page
Best forChinese documentsLayout and line-level OCR
InputsPDF, imagesPDF, images
LanguagesChinese, English and more90+ languages
Max pages per request200500
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
Math✓ YesNo
Bounding boxesNo✓ Yes
ConfidenceNoNo
FormsNoNo
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 covers 192 languages, handwriting and scene text, which Surya lists as weak spots or not-for-use cases.
  • Apache-2.0 applies to the weights, so there is no revenue or funding cap on commercial use.
  • It scores 93.12 on OmniDocBench v1.5 and outputs Markdown as well as JSON, HTML, LaTeX and bounding boxes.

Choose Surya if

  • It runs on CPU and Apple Silicon through llama.cpp, with peak memory of about 4.3 to 5.9 GB on an M4 Max.
  • One model returns layout labels, reading order, OCR, HTML tables and KaTeX math with per-block bounding boxes.
  • At 689M parameters it scores 83.7% on olmOCR-bench and reaches 4.52 pages per second on one H100 with vLLM.

Key differences

Qianfan OCRSurya
LicenceApache-2.0, commercial use allowedCode Apache-2.0; weights under a modified AI Pubs Open Rail-M, free for research, personal use and companies under $5M funding or revenue
Model size4B (Qwen3-4B language model)689M
How you run itSelf-host the weights, or use the Baidu Qianfan platform. Benchmarked on one A100 with vLLM; CPU-only is not a fitSelf-host only. A client runs against a separate vLLM or llama.cpp server, on an NVIDIA GPU, CPU or Apple Silicon
Output formatsMarkdown, JSON, HTML, LaTeX, bounding boxesJSON, HTML, LaTeX, bounding boxes, plain text
Languages192 languages, plus handwriting and scene text90+ languages; 74.9% pass rate on a 91-language test, and only 21 of 91 languages reach 90%
Speed1.024 pages per second on an A100 with W8A8; thinking mode can emit up to 16,384 tokens4.52 pages per second at 192 DPI on one H100 with vLLM; 0.198 pages per second on an M4 Max with llama.cpp Q8_0 at 96 DPI
Known failureSlower than MinerU 2.5; PaddleOCR-VL 1.5 scores higher at 94.50 on OmniDocBench v1.5Surya 2.5 table output lacks row and column geometry; multilingual tables score 58.1; the README sends handwriting, complex tables and math to the hosted Datalab API

Sources

What each one is

Qianfan OCR

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

Qianfan OCR details

Surya

Open-source OCR toolkit with line detection, layout analysis, reading order and tables.

Surya 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": ["datalab/surya"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Qianfan OCR alternativesSurya alternativesBest OCR models in 2026