OCRRouter

DeepSeek-OCR vs InternVL3.5

Pick DeepSeek-OCR for cheap self-hosted bulk OCR of pages where you want Markdown, HTML or bounding boxes back, and you can add safeguards against repeated tokens. Pick InternVL3.5 for document question answering or a multimodal pipeline where you want one model family in several sizes and JSON output. The main split is that DeepSeek-OCR is a dedicated OCR model with layout output, while InternVL3.5 is a general vision language model without bounding boxes by default.

DeepSeek-OCRdeepseek/deepseek-ocrInternVL3.5opengvlab/internvl
TypeOpen sourceVision model
Price1 credit / page2 credits / page
Per 1,000 pages$1.00$2.00
Typical speed1.1 s / page3.0 s / page
Best forCheap bulk conversionSelf-hosted document understanding
InputsPDF, imagesimages
Languages100+ languagesMultilingual
Max pages per request200500
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 DeepSeek-OCR if

  • It returns bounding boxes and HTML as well as Markdown and plain text, so you get layout from the model itself.
  • It offers resolution modes from 64 to 400 vision tokens per page, and its authors quote about 2,500 tokens per second of PDF throughput on one A100-40G.
  • It uses the MIT license, which allows commercial use, and it is built for cheap self-hosted bulk OCR.

Choose InternVL3.5 if

  • It comes in nine sizes from 1B to 241B, so you can trade accuracy for cost within one model family.
  • It can output JSON and suits document question answering and self-hosted multimodal pipelines.
  • Models up to 30B fit on a single A100, and the 20B-A4B and 30B-A3B MoE variants activate few parameters per token.

Key differences

DeepSeek-OCRInternVL3.5
Model typeOpen-weight OCR model that compresses pages into few vision tokensGeneral open-weight vision language model family from OpenGVLab
LicenseMITApache-2.0
How you run itSelf-host with Transformers or vLLM on a CUDA GPU (reference setup CUDA 11.8, PyTorch 2.6, bfloat16)Self-host with Transformers, LMDeploy or vLLM; up to 30B on one A100, 38B on two A100s, 241B-A28B on eight A100s
PriceFree, you pay for computeFree, you pay for compute
Output formatsMarkdown, plain text, HTML, bounding boxesPlain text, Markdown, JSON; no bounding boxes or layout output by default
SizesOne model with resolution modes of 64 to 400 vision tokens per pageNine sizes from 1B to 241B-A28B (8B variant is 8.5B parameters)
Known failureRepeated tokens and looping over table headers (GitHub issues #12 and #16); it corrects nonsense words instead of copying themOCR scores are published only as chart images, not text values

Sources

What each one is

DeepSeek-OCR

Open-source vision model that compresses pages into few tokens.

DeepSeek-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 20 MB each, 10 files.No file?

Use one, fall back to the other

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

Questions

More comparisons

DeepSeek-OCR alternativesInternVL3.5 alternativesBest OCR models in 2026