OCRRouter

InternVL3.5 vs DeepSeek-VL2

Pick InternVL3.5 if you want one Apache-2.0 model family you can scale from 1B to 241B-A28B and run in Transformers, LMDeploy or vLLM. Pick DeepSeek-VL2 for single-page document and chart question answering, where it has published scores: DocVQA 93.3 and ChartQA 86.0. The main split is licence and evidence: InternVL3.5 is the more permissive licence with more size options, while DeepSeek-VL2 has OCR numbers you can check.

InternVL3.5opengvlab/internvlDeepSeek-VL2deepseek/deepseek-vl2
TypeVision modelVision model
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed3.0 s / page3.0 s / page
Best forSelf-hosted document understandingCharts and tables
Inputsimagesimages
LanguagesMultilingualMainly English and Chinese
Max pages per request500500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ YesNo
Bounding boxesNo✓ Yes
ConfidenceNoNo
FormsNoNo
Multilingual✓ YesNo
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 InternVL3.5 if

  • It is Apache-2.0, built on Apache-2.0 Qwen3, so there is no custom weights licence to review.
  • It comes in nine sizes from 1B to 241B, and models up to 30B fit on a single A100.
  • It outputs plain text, Markdown and JSON, which suits document question answering and self-hosted multimodal pipelines.

Choose DeepSeek-VL2 if

  • It has published OCR and document scores: DocVQA 93.3 for the full model, OCRBench 834 for Small and ChartQA 86.0.
  • Its mixture-of-experts design activates only 1.0B to 4.5B parameters per token.
  • The weights allow commercial use, and it targets document and chart question answering on single pages.

Key differences

InternVL3.5DeepSeek-VL2
LicenceApache-2.0MIT for code; DeepSeek Model License for weights (commercial use allowed)
SizesNine sizes, 1B to 241B-A28B (8B variant is 8.5B)Three sizes: Tiny 3.37B (1.0B active), Small 16.1B, full 27.5B (4.5B active)
GPU needsUp to 30B on a single A100; 38B needs two A100s; 241B-A28B needs eight A100sSmall may need 80GB, or 40GB with incremental prefilling; Tiny runs under 40GB
Published OCR scoresNot published as text; the model card shows OCR scores only as chart imagesDocVQA 93.3 (full), OCRBench 834 (Small), ChartQA 86.0 (full), from the authors' paper
Output formatsPlain text, Markdown, JSONPlain text, Markdown
Multi-image inputNot publishedOnly a few images per session; dynamic tiling turns off with more than two images
Known failureNo bounding boxes or layout output by default, so no word coordinatesStruggles with blurry images, so phone photos are a risk

Sources

What each one is

InternVL3.5

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

InternVL3.5 details

DeepSeek-VL2

DeepSeek's mixture-of-experts vision models (December 2024) with OCR and table and chart understanding.

DeepSeek-VL2 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": "opengvlab/internvl","fallbacks": ["deepseek/deepseek-vl2"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

InternVL3.5 alternativesDeepSeek-VL2 alternativesBest OCR models in 2026