OCRRouter

Docling vs InternVL3.5

Pick Docling to ingest born-digital PDFs and Office files into a RAG pipeline, because it parses many formats and exports lossless JSON with layout and reading order. Pick InternVL3.5 for document question answering on a GPU, because it is a vision language model you can run at sizes from 1B to 241B-A28B. Docling gives you structure but needs an OCR engine for scans. InternVL3.5 gives you answers but no bounding boxes or layout output by default.

Doclingibm/doclingInternVL3.5opengvlab/internvl
TypeOpen sourceVision model
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed2.2 s / page3.0 s / page
Best forStructured export for RAGSelf-hosted document understanding
InputsPDF, images, DOCXimages
LanguagesLatin scripts, CJKMultilingual
Max pages per request500500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxes✓ YesNo
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 Docling if

  • You need one API for PDF, DOCX, PPTX, XLSX, HTML, EPUB, images, emails and XBRL.
  • You need structured JSON that keeps layout, reading order and table structure for downstream tools.
  • You want to run on CPU on macOS, Linux or Windows, and plug in EasyOCR, Tesseract or RapidOCR.

Choose InternVL3.5 if

  • You want document question answering from a single model rather than a conversion pipeline.
  • You want to pick a size from nine options, from 1B to 241B, to trade accuracy for cost.
  • You have GPUs: models up to 30B run on a single A100, and the MoE variants 20B-A4B and 30B-A3B activate few parameters per token.

Key differences

DoclingInternVL3.5
What it isPython library from IBM Research that converts documents into a structured DoclingDocumentOpen-weight vision language model family from OpenGVLab, 1B to 241B-A28B parameters
LicenceMIT (individual models have their own licences)Apache-2.0
How you run itLocal library; CPU works, GPU speeds up model stagesSelf-host with Transformers, LMDeploy or vLLM; up to 30B on one A100, 38B on two, 241B-A28B on eight
PriceFree, self-hosted (you pay for compute)Free, self-hosted (you pay for compute)
Output formatsMarkdown, HTML, JSON, DocTags, plain textPlain text, Markdown, JSON; no bounding boxes or layout output by default
Scanned pagesAccuracy depends on the OCR engine you plug in; GraniteDocling VLM option is 258MOCR scores are published only as chart images, not text values
Known failureFull-page Tesseract OCR in 2.143.1 drops words and numbers (issue #5254); reading order can merge neighbouring columns (issue #5132)Larger sizes need multiple A100s and do not suit CPU-only deployment

Sources

What each one is

Docling

IBM's open-source document converter with a structured document model.

Docling details

InternVL3.5

Shanghai AI Lab's open vision-language family (1B to 241B, August 2025), strong on OCR and document benchmarks.

InternVL3.5 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": "ibm/docling","fallbacks": ["opengvlab/internvl"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Docling alternativesInternVL3.5 alternativesBest OCR models in 2026