OCRRouter

InternVL3.5 vs Phi-4-multimodal

Pick InternVL3.5 for self-hosted document question answering, especially when you need non-English documents or a choice of model sizes from 1B to 241B-A28B. Pick Phi-4-multimodal for English document Q&A on a single modest GPU, or when audio and images go through one model. The main split is language: Phi-4-multimodal supports vision for English only, while InternVL3.5 has no such stated limit.

InternVL3.5opengvlab/internvlPhi-4-multimodalmicrosoft/phi-4-multimodal
TypeVision modelVision model
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed3.0 s / page2.5 s / page
Best forSelf-hosted document understandingSmall model for OCR and questions
Inputsimagesimages
LanguagesMultilingualEnglish for vision
Max pages per request500500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxesNoNo
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 comes in nine sizes from 1B to 241B, so you can trade accuracy for cost.
  • Phi-4-multimodal's model card says vision is English only and that quality drops in other languages, while InternVL3.5's card states no such limit.
  • The MoE variants 20B-A4B and 30B-A3B activate few parameters per token, and models up to 30B fit on a single A100.

Choose Phi-4-multimodal if

  • It scores 93.2 on DocVQA and 84.4 on OCRBench at 5.6B parameters, as reported by Microsoft.
  • It takes audio as well as images, so one model can serve mixed audio and image pipelines.
  • It has a 128K token context and is also available through Azure AI Foundry, in addition to self-hosting.

Key differences

InternVL3.5Phi-4-multimodal
LicenceApache-2.0MIT
How you run itSelf-host with Transformers, LMDeploy or vLLMSelf-host or use Azure AI Foundry
Model size1B to 241B-A28B, nine sizesSingle 5.6B model
HardwareUp to 30B on one A100; 38B needs two A100s; 241B-A28B needs eight A100sFlash attention tested on A100, A6000 and H100; V100 and older need eager attention
Published OCR scoresOnly chart images on the model card, no text valuesDocVQA 93.2, OCRBench 84.4, ChartQA 81.4, InfoVQA 72.7 (authors' numbers)
Input typesImage and textText, image and audio
Known limitsNo bounding boxes or layout output by default; the 241B-A28B model needs eight A100sEnglish-only vision; may give repetitive or inconsistent output in long chats; no coordinates or layout

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

Phi-4-multimodal

Microsoft's 5.6B text, vision and audio model (February 2025). Scores 84.4 on OCRBench per its model card.

Phi-4-multimodal 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": ["microsoft/phi-4-multimodal"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

InternVL3.5 alternativesPhi-4-multimodal alternativesBest OCR models in 2026