OCRRouter

Chandra vs SmolDocling

Pick Chandra for production conversion of multilingual or scanned documents, where it outputs Markdown, HTML or JSON with bounding boxes and has a hosted API option. Pick SmolDocling only for English experiments on small hardware: it is a 256M preview model, and its authors point users to Granite-Docling for updates and support. The main split is maturity and language coverage: Chandra scores 77.8% on a 43-language benchmark, while SmolDocling is English only.

Chandradatalab/chandraSmolDoclinghuggingface/smoldocling
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 handwritingVery cheap page conversion
InputsPDF, imagesPDF, images
Languages40+ languagesMainly English
Max pages per request500500
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
Math✓ Yes✓ Yes
Bounding boxes✓ Yes✓ Yes
ConfidenceNoNo
Forms✓ YesNo
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

  • Your documents are not only English: Chandra 2 averages 77.8% across 43 languages, and 72.7% on a 90-language benchmark.
  • You want a hosted option as well as open weights: the Datalab API costs $1, $3 or $7.50 per 1,000 pages, with a $20/month free tier.
  • You need Markdown, HTML or JSON with bounding boxes and labels per block, for RAG pipelines or documents with tables, forms and math.

Choose SmolDocling if

  • You want the smallest model: 256M parameters, small enough for modest hardware.
  • You need a free licence with no revenue threshold: Apache-2.0 per the model summary, self-hosted only.
  • You want speed on English pages: about 0.35 seconds per page on an A100 with vLLM.

Key differences

ChandraSmolDocling
LicenceCode Apache-2.0; weights modified OpenRAIL-M, free for research, personal use and companies under $2M funding/revenueApache-2.0 per model summary (metadata tag says CDLA-Permissive-2.0)
How you run itSelf-host via vLLM or Hugging Face, or use the hosted Datalab APISelf-host only
PriceSelf-hosted: free within licence terms. API: $1, $3 or $7.50 per 1,000 pagesFree, self-hosted (you pay for compute)
Languages43-language average 77.8%; weak on Urdu (43.2%) and Sanskrit (51.1%)English only
Output formatsMarkdown, HTML, JSON, bounding boxesDocTags, Markdown, HTML, JSON, LaTeX, bounding boxes
BenchmarkolmOCR-bench overall 85.8 (Chandra 2, authors' table)Table TEDS 0.82 on FinTabNet, full-page OCR F1 0.80; below Granite-Docling on every reported task
Known failureToken-loop hallucinations on 5-6 of about 60 Russian/Kazakh scans in one issue report; one reviewer measured 66 seconds per page on an RTX 4090 with the Hugging Face pathEndless token repetition and missing closing tags; output loops on some images, making generation very slow even on sparse pages

Sources

What each one is

Chandra

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

Chandra details

SmolDocling

Tiny 256M vision model from Hugging Face and IBM that outputs DocTags. Predecessor of Granite Docling.

SmolDocling 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": ["huggingface/smoldocling"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Chandra alternativesSmolDocling alternativesBest OCR models in 2026