OCRRouter

Qwen-VL vs InternVL3.5

Pick Qwen-VL when you need bounding boxes, layout-aware HTML or Markdown output, or OCR across 32 languages, and add loop checks on low-quality scans. Pick InternVL3.5 for self-hosted document question answering when you want a single model family from 1B to 241B-A28B and do not need word coordinates. The main split is output: Qwen-VL returns layout positions, InternVL3.5 returns text, Markdown and JSON only.

Qwen-VLqwen/qwen-vlInternVL3.5opengvlab/internvl
TypeOpen sourceVision model
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed2.0 s / page3.0 s / page
Best forFlexible extraction with promptsSelf-hosted document understanding
InputsPDF, imagesimages
Languages30+ languagesMultilingual
Max pages per request200500
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
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 Qwen-VL if

  • It outputs bounding boxes and a Qwen HTML document format, so you get layout positions and not only text.
  • It reads OCR in 32 languages, up from 10 in the previous generation.
  • You can also call it as a hosted API on Alibaba Cloud, not only self-host the Apache-2.0 weights.

Choose InternVL3.5 if

  • It fits document question answering well, and models up to 30B run on a single A100.
  • It comes in nine sizes from 1B to 241B, including MoE variants 20B-A4B and 30B-A3B that activate few parameters per token.
  • It has no reported repetition-loop issues in the material reviewed, while Qwen-VL has open reports of looping on low-quality scans.

Key differences

Qwen-VLInternVL3.5
LicenceApache-2.0Apache-2.0, built on Apache-2.0 Qwen3
How you run itSelf-host the open weights, or use the hosted API on Alibaba CloudSelf-host only, with Transformers, LMDeploy or vLLM
PriceFree self-hosted (you pay for compute). Hosted pricing varies by model and was not verified.Free self-hosted (you pay for compute)
Output formatsPlain text, HTML, bounding boxes, JSON, MarkdownPlain text, Markdown, JSON. No bounding boxes or layout output by default.
Model sizes2B, 4B, 8B, 32B dense; 30B-A3B and 235B-A22B MoE1B to 241B-A28B; the 8B variant is 8.5B
BenchmarkQwen 3 VL 8B scores 64.6 on olmOCR-bench (independent Datalab table), below dedicated OCR modelsNot published as text values; the model card shows OCR scores only as chart images
Known failureCan loop and repeat the same text, worse with greedy decoding and on low-quality scans. Qwen2.5-VL-32B GGUF often loops on scanned documents.Not published. Largest 241B-A28B needs eight A100 GPUs, and 38B needs two A100s.

Sources

What each one is

Qwen-VL

Alibaba's open-weight vision language models (Qwen2.5-VL, Qwen3-VL). Strong general OCR and grounding.

Qwen-VL 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": "qwen/qwen-vl","fallbacks": ["opengvlab/internvl"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Qwen-VL alternativesInternVL3.5 alternativesBest OCR models in 2026