DeepSeek V4 Flash Latest
DeepSeek馃嚚馃嚦
deepseek/deepseek-v4-flash-latestThis is an alias that always points to DeepSeek's latest V4-Flash model.
Cost rate
0.2x
Context
1M
Released
Aug 1, 2026
Input
Text
Output
Text
Support
ReasoningTool callingStructured outputs
Best at
The categories where this model ranks highest.
Medicine & Healthcare
#93 路 top 24%
Legal & Government
#94 路 top 24%
Life, Physical, & Social Science
#95 路 top 23%
Writing, Literature, & Language
#99 路 top 24%
Performance
Median latency and throughput measured across recent requests.
Throughput216 tok/s
Latency