DeepSeek · deepseek/deepseek-v4-flash

deepseek-v4-flash

Junior Developer 1049k context Hermes Limited

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...

Input / M

$0.089

Output / M

$0.177

Value score

910.98

30d price Δ

Reasoning (AA)

24.2

Coding (AA)

56.2

Tool / agentic

—

Knowledge cutoff

—

Price history

Not enough history yet — newer than the backfill window.

Capability snapshot

Last-known Artificial Analysis indexes via OpenRouter.

Index	Score
coding	56.2
context	100.0
general_intelligence	24.2
reasoning	24.2
tool_use	22.2