OCRRouter

Chandra vs Donut

Pick Chandra for full-page conversion of scanned PDFs to Markdown, HTML or JSON, especially multilingual ones, with no training step. Pick Donut only if you have a narrow, fixed-layout document type such as receipts or forms and will fine-tune it. The main split: Chandra works out of the box, Donut is a base model you must train first.

Chandradatalab/chandraDonutnaver/donut
TypeOpen sourceOpen source
Price2 credits / page1 credit / page
Per 1,000 pages$2.00$1.00
Typical speed2.0 s / page1.0 s / page
Best forComplex layouts and handwritingReceipt and form fields after fine-tuning
InputsPDF, imagesimages
Languages40+ languagesEnglish, Chinese, Japanese, Korean
Max pages per request500100
Tables✓ YesNo
Handwriting✓ YesNo
Math✓ YesNo
Bounding boxes✓ YesNo
ConfidenceNoNo
Forms✓ Yes✓ Yes
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 Chandra if

  • You need whole pages as Markdown, HTML or JSON, with bounding boxes and labels per block, for RAG pipelines.
  • You work with multilingual scans: the authors report 77.8% average across 43 languages and 85.8 on olmOCR-bench.
  • You want a hosted option too: the Datalab API costs $1, $3 or $7.50 per 1,000 pages, with $20/month free usage.

Choose Donut if

  • You want an MIT licence with no revenue or funding cap on commercial self-hosting.
  • You have a narrow, fixed-layout document type, such as receipts or forms, and will fine-tune for field extraction or classification.
  • You want to skip a separate OCR step: it maps the document image straight to structured JSON, and a practitioner reports about 200 fine-tuning documents can reach human-level accuracy on narrow data.

Key differences

ChandraDonut
Out-of-the-box useConverts pages to Markdown, HTML or JSON with layout as releasedBase checkpoint is pretrain-only and must be fine-tuned before use
LicenceCode Apache-2.0; weights modified OpenRAIL-M, free for research, personal use and companies under $2M funding/revenueMIT
How you run itSelf-host with vLLM or Hugging Face, or use the hosted Datalab APISelf-host only, via Hugging Face Transformers
PriceSelf-hosted: free within licence terms. API: $1, $3 or $7.50 per 1,000 pagesFree, self-hosted (you pay for compute)
Output formatsMarkdown, HTML, JSON, bounding boxesJSON, plain text
Published benchmarksolmOCR-bench 85.8 (Chandra 2); 77.8% across 43 languagesNot published
Known failureToken-loop hallucinations reported on some Russian/Kazakh scans; weak on Urdu (43.2%) and old scansMisses tiny text in large images because of input resolution limits; Transformers v5 dropped image-to-text pipeline support, so load it directly or use v4

Sources

What each one is

Chandra

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

Chandra details

Donut

OCR-free document understanding model. Fine-tuned for receipts, forms and document Q&A.

Donut 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": ["naver/donut"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Chandra alternativesDonut alternativesBest OCR models in 2026