All ModelschatDeepSeek V4 Flash

DeepSeek V4 Flash

Name: DeepSeek V4 Flash
Availability: InStock
Author: DeepSeek

by DeepSeekFast

1M context, thinking + non-thinking modes, tool calls

Detailed content for this model is coming soon.

Input$0.182 per 1M tokens

Output$0.364 per 1M tokens

Context Window1000K

Streaming Yes

Vision No

Reasoning Yes

Tool Use Yes

ProviderDeepSeek

Overall#4

Programming#7

Similar Models

DeepSeek

Legacy — maps to V4 Flash non-thinking mode. Deprecated 2026-07-24.

DeepSeek

Flagship model — 1M context, thinking + non-thinking modes

MiniMax

M2.7 at ~100 tps — same performance, faster and more agile

MiniMax

M2.5 at ~100 tps — same performance, faster and more agile