InternVL3.5 vs Google Cloud Vision OCR
Pick Google Cloud Vision OCR for high-volume plain text extraction, photos of signs and labels, and handwritten notes where you need word-level bounding boxes without running GPUs. Pick InternVL3.5 when you want to self-host under Apache-2.0 and ask questions about documents, getting Markdown or JSON back. The main split is a hosted, per-page-priced API that returns coordinates versus an open model you run yourself.
InternVL3.5opengvlab/internvl | Google Cloud Vision OCRgoogle/cloud-vision | |
|---|---|---|
| Type | Vision model | OCR API |
| Price | 2 credits / page | 2 credits / page |
| Per 1,000 pages | $2.00 | $2.00 |
| Typical speed | 3.0 s / page | 1.0 s / page |
| Best for | Self-hosted document understanding | Photos and simple scans |
| Inputs | images | PDF, images |
| Languages | Multilingual | 100+ languages |
| Max pages per request | 500 | 2,000 |
| Tables | ✓ Yes | No |
| Handwriting | No | ✓ Yes |
| Math | ✓ Yes | No |
| Bounding boxes | No | ✓ Yes |
| Confidence | No | ✓ Yes |
| 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 is Apache-2.0 and free to self-host, so you pay only for compute and keep documents on your own hardware.
- It comes in nine sizes from 1B to 241B-A28B, and models up to 30B fit on a single A100.
- It can output Markdown and JSON, which suits document question answering and LLM pipelines.
Choose Google Cloud Vision OCR if
- It returns page, block, paragraph, word and symbol hierarchy with bounding polygons, which InternVL3.5 does not give by default.
- It supports handwriting through DOCUMENT_TEXT_DETECTION and language hints, with no GPU to manage.
- It is cheap at volume: the first 1,000 units per month are free, then $1.50 per 1,000, dropping to $0.60 per 1,000 above 5M units.
Key differences
| InternVL3.5 | Google Cloud Vision OCR | |
|---|---|---|
| How you run it | Self-host with Transformers, LMDeploy or vLLM | Hosted REST API on Google Cloud, no on-premise option |
| Licence | Apache-2.0 | Proprietary |
| Price | Free, you pay for compute | First 1,000 units per month free per feature, then $1.50 per 1,000 up to 5M, $0.60 per 1,000 above |
| Output formats | Plain text, Markdown, JSON | JSON, plain text, bounding boxes; no Markdown |
| Word coordinates and layout | No bounding boxes or layout output by default | Bounding polygons at page, block, paragraph, word and symbol level |
| Hardware and limits | Up to 30B on one A100; 38B needs two A100s; 241B-A28B needs eight A100s | PDF and TIFF need async processing via Cloud Storage; async batch takes up to 2,000 image files per request |
| Benchmarks | OCR scores published only as chart images in the model card | Not published |
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 detailsGoogle Cloud Vision OCR
Google Cloud's image OCR with text and document text detection, word boxes and confidence.
Google Cloud Vision OCR 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": ["google/cloud-vision"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
InternVL3.5 alternativesGoogle Cloud Vision OCR alternativesBest OCR models in 2026