Mistral OCR vs InternVL3.5
Pick Mistral OCR for high-volume PDF to Markdown and scanned business documents when you want a hosted API at $2 per 1,000 pages. Pick InternVL3.5 when you need to self-host under Apache-2.0, or want one model family at sizes from 1B to 241B for document question answering. The main split is a priced hosted OCR API versus an open-weight general vision language model you run on your own GPUs.
Mistral OCRmistral/mistral-ocr | InternVL3.5opengvlab/internvl | |
|---|---|---|
| Type | OCR API | Vision model |
| Price | 25 credits / page | 2 credits / page |
| Per 1,000 pages | $25.00 | $2.00 |
| Typical speed | 0.9 s / page | 3.0 s / page |
| Best for | High-volume PDF to Markdown | Self-hosted document understanding |
| Inputs | PDF, images | images |
| Languages | 100+ languages | Multilingual |
| Max pages per request | 1,000 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | ✓ Yes | No |
| 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 Mistral OCR if
- It costs $2 per 1,000 pages, or $1 per 1,000 pages through the Batch API, with no GPUs to run.
- OCR 3 rebuilds tables as HTML with rowspan and colspan, and returns Markdown, HTML, JSON and extracted images.
- It has independent OmniDocBench scores (85.66 on v1.6), while InternVL3.5 has none published as text.
Choose InternVL3.5 if
- It is Apache-2.0 and self-hosted, so you pay only for compute and keep documents on your own machines.
- Nine sizes from 1B to 241B-A28B let you trade accuracy for cost, and models up to 30B fit on a single A100.
- As a general vision language model it can answer questions about a document, not only transcribe it.
Key differences
| Mistral OCR | InternVL3.5 | |
|---|---|---|
| Deployment | Hosted API from Mistral AI | Self-host with Transformers, LMDeploy or vLLM |
| Licence | Proprietary | Apache-2.0 |
| Price | $2 per 1,000 pages; $3 with structured annotations; $1 via Batch API | Free to download; you pay for compute |
| Output formats | Markdown, HTML, JSON, images | Plain text, Markdown, JSON |
| Layout and coordinates | Tables returned as HTML with rowspan and colspan | No bounding boxes or layout output by default |
| OmniDocBench | 78.83 for the first version (v1.5); 85.66 overall on v1.6 | Not published as text; the model card shows OCR scores only as chart images |
| Known failure | Hallucinated text on unreadable handwriting; changed checkbox states and misread characters on a dense financial table | The 38B model needs two A100s and the 241B-A28B model needs eight, so large sizes are hard to run without a GPU cluster |
Sources
- Mistral OCR 3 announcement
- VentureBeat on OCR 3 pricing
- OmniDocBench v1.6 leaderboard
- Reducto test of Mistral OCR
- Hugging Face model card (8B)
- InternVL GitHub
What each one is
Mistral OCR
Fast document OCR that returns clean Markdown with tables and embedded images.
Mistral OCR 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": "mistral/mistral-ocr","fallbacks": ["opengvlab/internvl"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Mistral OCR alternativesInternVL3.5 alternativesBest OCR models in 2026