OCRRouter

RolmOCR vs Chunkr

Pick RolmOCR if you want free, Apache-2.0 plain text transcription of scanned pages on your own GPU. Pick Chunkr if you need layout-aware output (HTML, Markdown, JSON with bounding boxes) for RAG chunking of PDFs and slides. The main split is output: RolmOCR returns plain text only, while Chunkr returns structure and coordinates.

RolmOCRreducto/rolmocrChunkrchunkr/chunkr
TypeOpen sourceOCR API
Price2 credits / page14 credits / page
Per 1,000 pages$2.00$14.00
Typical speed3.0 s / page3.0 s / page
Best forFast open PDF to textLayout-aware chunks for RAG
InputsPDF, imagesPDF, images, DOCX
LanguagesNot stated by the authorsMultilingual
Max pages per request5001,000
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
MathNo✓ Yes
Bounding boxesNo✓ Yes
ConfidenceNoNo
FormsNoNo
MultilingualNo✓ 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 RolmOCR if

  • You only need plain text from scanned pages, including rotated or skewed ones, since about 15% of its training data was rotated.
  • You want Apache-2.0 weights that are usable commercially, with no copyleft or commercial license to negotiate.
  • You want a single self-hosted model on one GPU, with no extra LLM endpoint to run.

Choose Chunkr if

  • You need bounding boxes, which RolmOCR cannot output according to its model card.
  • You need HTML, Markdown or JSON output and semantic chunking for RAG over PDFs, PPT, Word and images.
  • You want the choice of a hosted cloud API or a self-host via Docker with GPU, CPU-only and Mac ARM options.

Key differences

RolmOCRChunkr
What it isOpen-weight OCR model from Reducto, fine-tuned from Qwen2.5-VL-7B-Instruct (8B params)Document parsing service from Lumina AI: layout analysis, OCR with bounding boxes, semantic chunking
Output formatsPlain textHTML, Markdown, JSON, bounding boxes
DeploymentSelf-host only, for example with vLLMCloud API or self-host via Docker (GPU, CPU-only, Mac ARM)
LicenceApache-2.0, usable commerciallyAGPL-3.0 or commercial license; closed-source use needs the commercial license
PriceFree, you pay for computeHosted credit-based plans, official prices not verified. Open-source version is free, you pay for compute and an LLM endpoint
Input typesScanned pages, including rotated or skewed onesPDF, PPT, Word and images; Excel is not supported in the open-source version
Known failureModel card says it can hallucinate or drop content. Reducto shows it omitting a table subtitle. Needl.ai overall score 0.663Open-source version uses community models that are less accurate than the cloud's in-house models. Benchmarks: Not published

Sources

What each one is

RolmOCR

Reducto's open PDF-to-text model, built on Qwen2.5-VL-7B with the olmOCR recipe. Needs no PDF metadata and handles rotated pages.

RolmOCR details

Chunkr

Document parsing API that segments and chunks pages for RAG. Self-hostable version available.

Chunkr 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": "reducto/rolmocr","fallbacks": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

RolmOCR alternativesChunkr alternativesBest OCR models in 2026