OCRRouter

Unlimited OCR vs InternVL3.5

Pick Unlimited OCR to parse long multi-page documents such as reports and books in one request, with Markdown and bounding boxes out. Pick InternVL3.5 for document question answering or a multimodal pipeline where you want one model family in sizes from 1B to 241B. The main split is a dedicated layout-aware parser versus a general vision language model.

Unlimited OCRbaidu/unlimited-ocrInternVL3.5opengvlab/internvl
TypeOpen sourceVision model
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed1.2 s / page3.0 s / page
Best forBooks and very long documentsSelf-hosted document understanding
InputsPDF, imagesimages
Languages30+ languagesMultilingual
Max pages per request1,000500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxes✓ YesNo
ConfidenceNoNo
FormsNoNo
Multilingual✓ Yes✓ 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 Unlimited OCR if

  • It parses 40+ pages in a single forward pass with roughly constant memory, so long reports and books go in as one request.
  • It returns block types and bounding boxes alongside text, which InternVL3.5 does not do by default.
  • It has a published benchmark: Unlimited OCR 2 scores 77.1 on MarathonDocBench against 33.7 for the next model, per Baidu.

Choose InternVL3.5 if

  • It comes in nine sizes from 1B to 241B-A28B, so you can trade accuracy for cost.
  • Models up to 30B run on a single A100, and the 20B-A4B and 30B-A3B MoE variants activate few parameters per token.
  • It suits document question answering and general multimodal work, and it can return JSON as well as Markdown and plain text.

Key differences

Unlimited OCRInternVL3.5
LicenceMITApache-2.0
How you run itSelf-host with vLLM, SGLang or transformers; hosted endpoint in Baidu Cloud's OCR productSelf-host with Transformers, LMDeploy or vLLM
Model size3B total, about 500M active per token; Unlimited OCR 2 is 3.34B1B to 241B-A28B; the 8B variant is 8.5B
HardwareNVIDIA GPU with CUDA 12.9 or 13.0; Unlimited-OCR-2 under SGLang runs out of memory on 12 GB GPUsUp to 30B on a single A100; 38B needs two A100s; 241B-A28B needs eight A100s
OutputMarkdown, plain text, bounding boxesPlain text, Markdown, JSON; no bounding boxes or layout output by default
OCR benchmarkParseBench mean 46.17; MPDocBench 84.6 and MarathonDocBench 77.1 for Unlimited OCR 2 (author-reported)Not published as text; the model card shows OCR scores only as chart images
Known failureText repetition and looping on some pages, reported hallucinated text, and a 32,768 token context cap; text formatting score on ParseBench is only 0.97Largest sizes need multiple A100s; not suited to jobs needing word coordinates

Sources

What each one is

Unlimited OCR

Open-source model from Baidu that reads hundreds of pages in one pass with flat memory use.

Unlimited OCR 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 10 files at onceNo file?

Use one, fall back to the other

{"model": "baidu/unlimited-ocr","fallbacks": ["opengvlab/internvl"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Unlimited OCR alternativesInternVL3.5 alternativesBest OCR models in 2026