Overview
DeepSeek's flagship reasoning text model with 1M context and configurable thinking depth
Key Features
- 1.6T total parameters, 49B activated per token — DeepSeek's most powerful model
- Extended chain-of-thought reasoning with transparent thinking process
- Configurable thinking depth: standard (high) or maximum (expert/xhigh)
- Text-only model — supports code, documents, and structured data inputs
- Competitive with top frontier reasoning models at a fraction of the cost
Input Capabilities
Text
Technical Specifications
Context Window
1,000,000
Max Output
64,000
Model Information
Provider: DeepSeek
Model Code: deepseek-v4-pro
Category: Chat
File Support
Max Files
10
Max Size
10MB
Supported Formats
.txt
.md
.csv
.json
.html
.css
+10 more