Back to Models
DeepSeekOpen Source
DeepSeek-OCR
DeepSeek-OCR is a visual large model developed by DeepSeek-AI. It has approximately 30.0B parameter scale and is released under the MIT license.
Parameters
30.0B
Context Window
License
MIT
Release Date
2025-10-20
API Pricing
API pricing for this model is not yet available
Strengths
- ・30-billion parameter scale
- ・Available under an open license
- ・Advanced visual information processing
Weaknesses
- ・Specialization for specific tasks
- ・Requires computational resources for operation
- ・Lack of general-purpose dialogue capabilities
Use Cases
- ・Optical character recognition from images
- ・Visual data analysis
- ・Document digitization
Deep Analysis
OCR Precision
97% at <10x compression
Vision Tokens
64-1853 per page
Production Speed
200k+ pages/day (single A100)
Languages
~100
License
Apache 2.0
Release Date
October 20, 2025
Strengths
- ・Revolutionary compression (97% at 10x)
- ・200k+ pages/day on single GPU
- ・~100 language support
- ・Deep parsing (charts, formulas)
Weaknesses
- ・Not a general VLM
- ・Degrades at 20x compression
- ・No SFT stage (not a chatbot)
Competitor Comparison
| Model |
|---|
| GOT-OCR2.0 |
| MinerU2.0 |
DeepSeek-OCR pioneers optical compression: 97% precision at 10x compression. 200k+ pages/day on single A100, ~100 languages.
Sources
Analysis generated: 2026-05-24