Google Document AI vs InternVL3.5
Pick InternVL3.5 if you want to run the model yourself under Apache-2.0 and ask questions about documents. Pick Google Document AI if you want a managed API that returns bounding boxes and JSON and bills per page. The main split is hosted service versus self-hosted vision language model: Document AI sells page-level OCR and layout output, InternVL3.5 sells open weights you size to your own GPUs.
Google Document AIgoogle/document-ai | InternVL3.5opengvlab/internvl | |
|---|---|---|
| Type | OCR API | Vision model |
| Price | 10 credits / page | 2 credits / page |
| Per 1,000 pages | $10.00 | $2.00 |
| Typical speed | 1.4 s / page | 3.0 s / page |
| Best for | Multilingual scans | Self-hosted document understanding |
| Inputs | PDF, images | images |
| Languages | 200+ languages | Multilingual |
| Max pages per request | 500 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | ✓ Yes | No |
| Math | No | ✓ Yes |
| Bounding boxes | ✓ Yes | No |
| Confidence | ✓ Yes | No |
| Forms | ✓ Yes | 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 Google Document AI if
- Enterprise Document OCR costs $1.50 per 1,000 pages, drops to $0.60 above 5M pages a month, and the first 1,000 pages are free.
- Layout Parser adds chunking for RAG at $10 per 1,000 pages, and its output includes bounding boxes and JSON.
- Batch requests accept up to 500 pages, so you can run bulk OCR on Google Cloud without managing GPUs.
Choose InternVL3.5 if
- The Apache-2.0 licence and open weights let you self-host with Transformers, LMDeploy or vLLM, and you pay only for compute.
- Nine sizes from 1B to 241B-A28B let you trade accuracy for cost, and models up to 30B fit on a single A100.
- It suits document question answering and self-hosted multimodal pipelines, and it returns plain text, Markdown or JSON.
Key differences
| Google Document AI | InternVL3.5 | |
|---|---|---|
| How you run it | Hosted API on Google Cloud | Self-hosted with Transformers, LMDeploy or vLLM |
| Licence | Proprietary | Apache-2.0 |
| Price | Enterprise Document OCR $1.50 per 1,000 pages ($0.60 above 5M a month, first 1,000 free); Layout Parser $10; Form Parser $30 | Free; you pay for compute |
| Output formats | JSON, plain text, bounding boxes, chunks | Plain text, Markdown, JSON; no bounding boxes or layout output by default |
| Size and hardware limits | Online requests limited to 15 pages (30 in imageless mode); batch up to 500 pages; Form Parser batch up to 100 pages | 1B to 241B-A28B; up to 30B on one A100, 38B needs two A100s, 241B-A28B needs eight A100s |
| Table benchmark | 64.6% on RD-TableBench (independent), behind Azure and Textract | Not published; the model card shows OCR scores only as chart images |
| Best fit | Bulk OCR on Google Cloud, RAG chunking; not for long PDFs in one synchronous call or complex tables | Document question answering, one model family at several sizes; not for CPU-only deployment of larger sizes or jobs needing word coordinates |
Sources
- Document AI pricing
- Document AI limits
- Reducto RD-TableBench
- Hugging Face model card (8B)
- InternVL GitHub
What each one is
Google Document AI
Google Cloud OCR with layout parsing and specialised processors.
Google Document AI detailsInternVL3.5
Shanghai AI Lab's open vision-language family (1B to 241B, August 2025), strong on OCR and document benchmarks.
InternVL3.5 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": "google/document-ai","fallbacks": ["opengvlab/internvl"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Google Document AI alternativesInternVL3.5 alternativesBest OCR models in 2026