Deepseek V4 Pro
DeepSeek develops the Deepseek V 4 Pro, a chat model that excels at handling long-context conversations with its support for up to 1,048,576 tokens. It is particularly effective in coding benchmarks and demonstrates strong performance in various intelligence and reasoning tasks.
Input
Output
Context
1049K
Max Output
384K
Parameters
861.6B
Technical Specifications
Model TypeChat
Context Window1,048,576 tokens
Max Output Tokens384,000 tokens
Parameters861.6B
Release DateApr 22, 2026
Training CutoffNot available
Licensemit
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
35.9%
HLE
88.8%
GPQA
50.0%
SciCode
47.5
Coding
44.3
Intelligence
77.0
Speed (tok/s)
57.9
TTFA (s)
1.0
TTFT (s)
Resources & Links
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.