OCRRouter

Chandra vs Qwen-VL

Pick Chandra for scanned documents, multilingual pages, and PDF to Markdown for RAG, where faithful transcription matters. Pick Qwen-VL when you want one Apache-2.0 model that also answers questions about images, photos and screenshots. The main split is accuracy: Chandra 2 scores 85.8 on olmOCR-bench, while Qwen 3 VL 8B scores 64.6.

Chandradatalab/chandraQwen-VLqwen/qwen-vl
TypeOpen sourceOpen source
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed2.0 s / page2.0 s / page
Best forComplex layouts and handwritingFlexible extraction with prompts
InputsPDF, imagesPDF, images
Languages40+ languages30+ languages
Max pages per request500200
Tables✓ Yes✓ Yes
Handwriting✓ Yes✓ Yes
Math✓ Yes✓ Yes
Bounding boxes✓ Yes✓ Yes
ConfidenceNoNo
Forms✓ YesNo
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 Chandra if

  • It scores 85.8 on olmOCR-bench (Chandra 2), well above the 64.6 reported for Qwen 3 VL 8B.
  • It averages 77.8% across 43 languages and returns Markdown, HTML or JSON with bounding boxes per block.
  • You can self-host it or use the Datalab API at $1, $3 or $7.50 per 1,000 pages, with $20 a month free.

Choose Qwen-VL if

  • Its Apache-2.0 licence has no revenue limit, while Chandra's weights need a paid licence for companies above $2M funding or revenue.
  • It comes in sizes from 2B to 235B-A22B MoE, so you can match the model to your GPU budget.
  • It is a general model, so one deployment can do OCR, reasoning and visual question answering on photos and screenshots.

Key differences

ChandraQwen-VL
LicenceCode Apache-2.0; weights modified OpenRAIL-M, free under $2M funding/revenue, paid above thatApache-2.0
How you run itSelf-host with vLLM or Hugging Face, or the hosted Datalab APISelf-host open weights, or hosted on Alibaba Cloud; hosted pricing not verified
PriceFree self-hosted within licence terms; API $1, $3 or $7.50 per 1,000 pagesFree self-hosted, you pay for compute; hosted price varies by model
olmOCR-bench85.8 overall (Chandra 2)64.6 (Qwen 3 VL 8B)
Languages43-language average of 77.8%; weak on Urdu (43.2%) and Sanskrit (51.1%)OCR in 32 languages
Output formatsMarkdown, HTML, JSON, bounding boxesPlain text, HTML, bounding boxes, JSON, Markdown
Known failureToken loops reported on 5-6 of about 60 Russian/Kazakh scans; weak on old degraded scansRepeating-text loops, worse with greedy decoding and on low-quality images; loops on 10-37% of outputs with transformers 5.17

Sources

What each one is

Chandra

Datalab's OCR model that keeps layout and handles forms, tables and handwriting.

Chandra 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/chandra","fallbacks": ["qwen/qwen-vl"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Chandra alternativesQwen-VL alternativesBest OCR models in 2026