OCRRouter

Surya vs Qwen-VL

Pick Surya for local, high-volume transcription of printed documents where you need layout labels, reading order and bounding boxes. It is 689M parameters, scores 83.7% on olmOCR-bench, and runs on a laptop CPU or Apple Silicon. Pick Qwen-VL when the job mixes OCR with reasoning or VQA, or covers photos and screenshots with text, and accept that you must guard against repetition loops.

Suryadatalab/suryaQwen-VLqwen/qwen-vl
TypeOpen sourceOpen source
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed1.5 s / page2.0 s / page
Best forLayout and line-level OCRFlexible extraction with prompts
InputsPDF, imagesPDF, images
Languages90+ languages30+ languages
Max pages per request500200
Tables✓ Yes✓ Yes
HandwritingNo✓ Yes
MathNo✓ Yes
Bounding boxes✓ Yes✓ 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 Surya if

  • It scores 83.7% on olmOCR-bench with 689M parameters, while Qwen 3 VL 8B scores 64.6 in an independent table.
  • It runs on CPU and Apple Silicon through llama.cpp, with peak memory of about 4.3-5.9 GB on an M4 Max.
  • One model returns layout labels, reading order, OCR, HTML tables and KaTeX math with per-block bounding boxes in 90+ languages.

Choose Qwen-VL if

  • It is a general vision-language model, so one deployment covers OCR, reasoning and VQA on photos and screenshots.
  • It comes in sizes from 2B to 235B-A22B MoE under Apache-2.0, and Alibaba Cloud also serves it as a hosted API.
  • It handles low light, blur and tilted text per Qwen, and outputs layout positions and a Qwen HTML document format.

Key differences

SuryaQwen-VL
LicenceCode Apache-2.0; weights under a modified AI Pubs Open Rail-M. Free for research, personal use and companies under $5M funding or revenue.Apache-2.0 for the Qwen3-VL repository, with no revenue cap listed.
How you run itSelf-host only. A lightweight client talks to a separately running vLLM or llama.cpp server.Self-host the open weights, or use the hosted API on Alibaba Cloud. FP8 checkpoints need an H100-class GPU and CUDA 12+.
Model size689M parameters.2B, 4B, 8B, 32B dense; 30B-A3B and 235B-A22B MoE.
olmOCR-bench83.7% (Surya 2.5, reported by the authors).64.6 for Qwen 3 VL 8B (independent, in the Chandra table).
Languages90+ languages. The 91-language pass rate is 74.9%, and only 21 languages reach 90%.OCR in 32 languages, up from 10 in the previous generation.
Known failureSurya 2.5 table output lacks row/column geometry, and multilingual tables score 58.1. Handwriting, complex tables and math are better sent to the hosted Datalab API.Can loop and repeat the same text, worse with greedy decoding and on low-quality images. One report saw loops on 10-37% of OCR outputs versus 2-3% baseline, and a Qwen2.5-VL-32B GGUF often got stuck on scanned documents.
Output formatsJSON, HTML, LaTeX, bounding boxes, plain text.Plain text, HTML, bounding boxes, JSON, Markdown.

Sources

What each one is

Surya

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

Surya details

Qwen-VL

Alibaba's open-weight vision language models (Qwen2.5-VL, Qwen3-VL). Strong general OCR and grounding.

Qwen-VL 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": "datalab/surya","fallbacks": ["qwen/qwen-vl"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Surya alternativesQwen-VL alternativesBest OCR models in 2026