DeepSeekOfficial

DeepSeek: DeepSeek V4 Flash

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...

Pricing

Input

$0.14/1M tokens

Output

$0.28/1M tokens

Cache Read

$0.0028/1M tokens

Capabilities

Context Window1.0M tokens

Max Output384K tokens

SpeedFast

Release2026-04

Vision

Tool Use

API Access

Local / Open

API Access

Official API

Official Links

Official Website

Compare DeepSeek: DeepSeek V4 Flash

See how it stacks up side by side.

Compare Models →