OCRRouter

olmOCR vs SmolDocling

Pick olmOCR when you need accurate PDF to Markdown at volume on a GPU, including papers with equations and pages with handwriting. Pick SmolDocling only to experiment with a 256M model on modest hardware, and only for English pages. The main reason is size and maturity: olmOCR is a 7B model that scores 82.4 on olmOCR-Bench, while SmolDocling is a 256M preview that its authors say is superseded by Granite-Docling.

olmOCRallenai/olmocrSmolDoclinghuggingface/smoldocling
TypeOpen sourceOpen source
Price2 credits / page1 credit / page
Per 1,000 pages$2.00$1.00
Typical speed1.5 s / page1.0 s / page
Best forBulk PDF to text for datasetsVery cheap page conversion
InputsPDF, imagesPDF, images
LanguagesMainly EnglishMainly English
Max pages per request1,000500
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
Math✓ Yes✓ Yes
Bounding boxesNo✓ Yes
ConfidenceNoNo
FormsNoNo
MultilingualNoNo
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 olmOCR if

  • It scores 82.4 on olmOCR-Bench, above Marker (76.1), MinerU 2.5.4 (75.2) and Mistral OCR (72.0) in the same table.
  • It handles equations, tables and handwriting, and strips headers and footers in natural reading order.
  • Self-hosting costs under $200 per million pages per Ai2, and a hosted olmOCR-2-7B endpoint on DeepInfra costs $0.09 input / $0.19 output per million tokens.

Choose SmolDocling if

  • At 256M parameters it is small enough for modest hardware, and it runs at about 0.35 seconds per page on an A100 with vLLM.
  • It outputs DocTags, Markdown, HTML, JSON, LaTeX and bounding boxes, so you get location tags that olmOCR does not reliably give.
  • One model covers text, tables (OTSL), code, formulas and charts, and it is free to self-host apart from compute.

Key differences

olmOCRSmolDocling
Model size7B parameters256M parameters
StatusCurrent toolkit with an olmOCR-2-7B modelPreview release, superseded by Granite-Docling
How you run itSelf-host with vLLM on an NVIDIA GPU with at least 12 GB VRAM, or use hosted endpointsSelf-host only
LicenceApache-2.0 (toolkit)Apache-2.0 per model summary (metadata tag says CDLA-Permissive-2.0)
Output formatsMarkdown, JSONDocTags, Markdown, HTML, JSON, LaTeX, bounding boxes
LanguagesNot publishedEnglish only
Known failureOut of memory on a 12 GB GPU (issue #424), stuck on the last few pages (issue #433), unreliable image bounding boxes (issue #437)Endless token repetition and missing closing tags; output loops on some images and generation becomes very slow (Docling issue #1515)

Sources

What each one is

olmOCR

Open-source vision model from Ai2 (often searched as olm ocr) that turns PDFs into clean, reading-order text. Latest release: olmOCR 2.

olmOCR 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": "allenai/olmocr","fallbacks": ["huggingface/smoldocling"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

olmOCR alternativesSmolDocling alternativesBest OCR models in 2026