OCRRouter

RolmOCR vs InternVL3.5

Pick RolmOCR for plain text transcription of scanned pages, including rotated or skewed ones, on a single GPU. Pick InternVL3.5 when you want Markdown or JSON output, document question answering, or a choice of model sizes from 1B to 241B. Neither gives you bounding boxes, so look elsewhere if you need coordinates.

RolmOCRreducto/rolmocrInternVL3.5opengvlab/internvl
TypeOpen sourceVision model
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed3.0 s / page3.0 s / page
Best forFast open PDF to textSelf-hosted document understanding
InputsPDF, imagesimages
LanguagesNot stated by the authorsMultilingual
Max pages per request500500
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
MathNo✓ Yes
Bounding boxesNoNo
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

  • It was fine-tuned on olmOCR-mix-0225 for document transcription, and about 15% of its training data was rotated to handle off-angle scans.
  • It is a single 8B model, so a one-GPU self-hosted pipeline is simple to plan.
  • It has an independent score on the Needl.ai PDF extraction benchmark (0.663 overall) and 7 hallucination issues counted there, versus 11 for olmocr-2-7b.

Choose InternVL3.5 if

  • It can output Markdown and JSON as well as plain text, while RolmOCR outputs plain text only.
  • It comes in nine sizes from 1B to 241B, so you can trade accuracy for cost. Models up to 30B fit on a single A100.
  • It is a general vision language model, which suits document question answering and multimodal pipelines beyond transcription.

Key differences

RolmOCRInternVL3.5
LicenceApache-2.0, usable commerciallyApache-2.0, built on Apache-2.0 Qwen3
How you run itSelf-host, for example with vLLMSelf-host with Transformers, LMDeploy or vLLM
Model sizeOne model, 8B (Qwen2.5-VL-7B base)1B to 241B-A28B; the 8B variant is 8.5B
Output formatsPlain textPlain text, Markdown, JSON
HardwareSelf-hosted on one GPUUp to 30B on a single A100; 38B needs two A100s; 241B-A28B needs eight A100s
Published benchmarkNeedl.ai PDF extraction overall: 0.663 (independent)Not published as text; the model card gives OCR scores only as chart images
Known failureCan hallucinate or drop content; omitted a table subtitle that olmOCR extractedNo bounding boxes or layout output by default

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

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

Questions

More comparisons

RolmOCR alternativesInternVL3.5 alternativesBest OCR models in 2026