DeepSeek V4 Flash

DeepSeek · deepseek/deepseek-v4-flash

← Back to leaderboard

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 weightstexttext->text

Context

Max context: 1048576
Max output: 131072

Pricing

Input / 1M: 0.10
Output / 1M: 0.20
Blend / 1M: 0.15

Quality

Quality index:

Provider

Provider: DeepSeek
Moderated: no