Deepseek OCR
DeepSeek-OCR as an initial investigation into the feasibility of compressing long contexts via optical 2D mapping. DeepSeek-OCR consists of two components: DeepEncoder and DeepSeek3B-MoE-A570M as the decoder.
Input
Output
Context
8K
Max Output
—
Parameters
—
Technical Specifications
Model TypeChat
Context Window8K
Max Output Tokens—
Parameters—
Training Cutoff—
Licensemit
Capabilities
Input Modalities
textimage
Output Modalities
text
Features
vision
Benchmarks
353
Speed (tok/s)
0.213
TTFA (s)
0.213
TTFT (s)
Resources & Links
Related Tools
Data sourced from official provider APIs and documentation
Last updated: May 5, 2026
Start building with the right model.
From model selection to production, one platform, no fragmentation.