← All models
DeepSeek: DeepSeek V4 Flash 0423 logo

Deepseek · Text

DeepSeek: DeepSeek V4 Flash 0423

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

Open-weightIn: TextOut: Text

Input / M

$0.09 / M

Output / M

$0.18 / M

Cache read / M

$0.02 / M

Context

1M

Released

Apr 24, 2026