Back to Models
DeepSeekProprietary

DeepSeek-OCR 2

DeepSeek-OCR 2 is a multimodal large model developed by DeepSeek-AI. It has a parameter scale of approximately 3.5 billion and is an efficient model supporting a context length of 32K.

Parameters

3.5B

Context Window

32K

License

https://github.com/deepseek-ai/deepseek-LLM/blob/main/LICENSE-MODEL

Release Date

2026-01-28

API Pricing

API pricing for this model is not yet available

Strengths

  • Lightweight 3.5B parameters
  • Sufficient 32K context length
  • Efficient model size

Weaknesses

  • Closed license restrictions
  • Limited parameter scale
  • Lack of general descriptive information

Use Cases

  • Advanced OCR processing
  • Extracting text from images
  • Multimodal document analysis

Deep Analysis

Parameters

3.5B

OmniDocBench v1.5

91.09%

Best end-to-end

Improvement

+3.73% over OCR 1

Vision Tokens

1120 max per page

License

Apache 2.0

Release Date

January 27, 2026

Strengths

  • SOTA 91.09% OmniDocBench v1.5
  • Novel Visual Causal Flow architecture
  • +3.73% over OCR 1
  • Lower repetition rates

Weaknesses

  • Specialized for OCR
  • Newspaper recognition challenging
  • Higher token budget than OCR 1 compressed modes

Competitor Comparison

Model
DeepSeek-OCR
Gemini-3 Pro
Qwen3-VL-235B

DeepSeek-OCR 2 achieves 91.09% on OmniDocBench v1.5 with novel Visual Causal Flow architecture. Best end-to-end OCR model.

Sources

Analysis generated: 2026-05-24