Deepseek OCR 2
DeepSeek OCR 2 is a chat model developed by DeepSeek, capable of processing both text and image inputs with a context window of 8,192 tokens. It is genuinely best at exploring human-like visual encoding, leveraging its vision capabilities to analyze and understand visual data.
Input
Output
Context
8K
Max Output
8K
Parameters
3.4B
Technical Specifications
Model TypeChat
Context Window8,192 tokens
Max Output Tokens8,192 tokens
Parameters3.4B
Release DateJan 27, 2026
Training CutoffNot available
Licenseapache-2.0
Open SourceYes
Input Modalities
TextImage
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Deepseek OCR 2
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.