InternVL3.5 vs Chunkr
Pick InternVL3.5 if you want a self-hosted vision language model for document question answering under Apache-2.0, in a size that fits your GPUs. Pick Chunkr if you need layout parsing with bounding boxes and HTML or Markdown output for RAG chunking of PDFs and slides. The main split is that InternVL3.5 is a general VLM with no layout output by default, while Chunkr is a parsing service built for layout.
InternVL3.5opengvlab/internvl | Chunkrchunkr/chunkr | |
|---|---|---|
| Type | Vision model | OCR API |
| Price | 2 credits / page | 14 credits / page |
| Per 1,000 pages | $2.00 | $14.00 |
| Typical speed | 3.0 s / page | 3.0 s / page |
| Best for | Self-hosted document understanding | Layout-aware chunks for RAG |
| Inputs | images | PDF, images, DOCX |
| Languages | Multilingual | Multilingual |
| Max pages per request | 500 | 1,000 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | No | ✓ Yes |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | ✓ Yes |
| On OCRRouter | Available | Available |
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 ships in nine sizes from 1B to 241B-A28B, so you can trade accuracy for cost.
- It is Apache-2.0, with no commercial license needed for closed products.
- Models up to 30B run on a single A100, and the 20B-A4B and 30B-A3B MoE variants activate few parameters per token.
Choose Chunkr if
- It returns OCR with bounding boxes, plus HTML, Markdown and JSON, which InternVL3.5 does not give by default.
- It accepts PDF, PPT, Word and images, and is built for RAG chunking of PDFs and slides.
- It offers both a hosted cloud API and a Docker self-host with GPU, CPU-only and Mac ARM options.
Key differences
| InternVL3.5 | Chunkr | |
|---|---|---|
| What it is | Open-weight vision language model family from OpenGVLab | Document parsing service from Lumina AI with layout analysis and semantic chunking |
| Licence | Apache-2.0 | AGPL-3.0 or commercial license; closed-source products need the commercial license |
| How you run it | Self-host only, with Transformers, LMDeploy or vLLM | Cloud API or self-host via Docker; self-host still needs an external OpenAI-compatible LLM endpoint |
| Price | Free, you pay for compute | Hosted credit-based plans, official prices not verified; open-source version is free, you pay for compute and an LLM endpoint |
| Output formats | Plain text, Markdown, JSON | HTML, Markdown, JSON, bounding boxes |
| Coordinates and layout | No bounding boxes or layout output by default | OCR with bounding boxes and layout analysis |
| Known limits | OCR scores are published only as chart images; 38B needs two A100s and 241B-A28B needs eight | Open-source version uses community models that are less accurate than the cloud's, and does not support Excel |
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 detailsChunkr
Document parsing API that segments and chunks pages for RAG. Self-hostable version available.
Chunkr detailsTry both on your own file
Run the file once with each model and compare the output.
Use one, fall back to the other
{"model": "opengvlab/internvl","fallbacks": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
InternVL3.5 alternativesChunkr alternativesBest OCR models in 2026