OCRRouter

olmOCR vs Donut

Pick olmOCR to turn full PDF pages into Markdown for RAG or LLM training, including papers with equations and pages with handwriting. Pick Donut when you have a narrow, fixed-layout document type such as receipts or forms and can fine-tune a model to extract fields as JSON. The main split is that olmOCR works out of the box on whole pages, while Donut is a base checkpoint that must be trained before use.

olmOCRallenai/olmocrDonutnaver/donut
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 datasetsReceipt and form fields after fine-tuning
InputsPDF, imagesimages
LanguagesMainly EnglishEnglish, Chinese, Japanese, Korean
Max pages per request1,000100
Tables✓ YesNo
Handwriting✓ YesNo
Math✓ YesNo
Bounding boxesNoNo
ConfidenceNoNo
FormsNo✓ Yes
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

  • You need full-page PDF to Markdown output without training anything, and it scores 82.4 on olmOCR-Bench.
  • Your documents include equations, tables or handwriting, and you want headers and footers stripped in natural reading order.
  • You process large volumes: self-hosting costs under $200 per million pages per Ai2, and hosted olmOCR-2-7B on DeepInfra costs $0.09 input / $0.19 output per million tokens.

Choose Donut if

  • You extract fields from receipts or forms with a fixed layout and can fine-tune a model for them.
  • You want a permissive MIT licence, and the model loads in Hugging Face Transformers with no external OCR step.
  • You classify documents, or you want JSON output straight from the image. One HN practitioner reports about 200 fine-tuning documents can reach human-level accuracy on narrow data.

Key differences

olmOCRDonut
Out-of-the-box useConverts PDFs and images to Markdown as shippedBase checkpoint is pretrain-only and must be fine-tuned before use
LicenceApache-2.0 (toolkit)MIT
How you run itSelf-host with vLLM on a GPU, or call third-party hosted endpointsSelf-host only; you pay for compute
HardwareNVIDIA GPU with at least 12 GB VRAM and 30 GB free disk. Out of memory reported on a 12 GB GPU (issue #424)Not published
Output formatsMarkdown, JSONJSON, plain text
Benchmark82.4 on olmOCR-Bench (v0.4.0), above Marker (76.1), MinerU 2.5.4 (75.2) and Mistral OCR (72.0)Not published
Known failureCan get stuck on the last few pages (issue #433). Image bounding box coordinates are unreliable (issue #437)Misses tiny text in large images because of input resolution limits. Transformers v5 dropped image-to-text pipeline support, so use direct loading or v4

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

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

Questions

More comparisons

olmOCR alternativesDonut alternativesBest OCR models in 2026