Model comparison
Nanonets-OCR-s vs Gemini 2.5 Pro
Capability radar, value bars, and side-by-side posture.
Nanonets-OCR-s
Not scored
value score
Gemini 2.5 Pro
93
value score
Nanonets-OCR-s ctx
—
Gemini 2.5 Pro ctx
1.0M
Capability radar
Value · context · multimodal · openness · speed posture
Value head-to-head
- Gemini 2.5 Pro93
Attribute tape
| Field | Nanonets-OCR-s | Gemini 2.5 Pro |
|---|---|---|
| Developer | nanonets | Google DeepMind |
| Context | — | 1.0M |
| Modalities | Text, Code, Image, Audio, Video | |
| Openness | — | Proprietary Model |
| Speed | — | — |
| Price | — | $1.25/1M in · $10/1M out |
| Value score | — | 93 |
| Summary | Nanonets-OCR-s is an open-weight vision-language model that converts scanned documents, PDFs, and document images into structured Markdown, preserving layout elements such as tables, equations, signatures, watermarks, and checkboxes. It is designed to produce LLM-ready structured output for downstream AI and RAG workflows. | Google frontier multimodal model. |