Loading...
Loading...
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
$0.14
per 1M tokens
Output
$0.28
per 1M tokens
Blended
$0.18
per 1M tokens
Cheaper than 73% of models. Median price is $0.56/1M tokens.
Daily
$0.18
Monthly
$5.25
72
tokens/sec
Faster than 42% of models
0.81
seconds
Faster than 63% of models
78.36
seconds
Faster than 3% of models
Market Median
86 tok/s
16% slower
Median TTFT
1.07s
24% faster
Throughput/Dollar
414
tok/s per $/1M
Speed Comparison
Context Window
1.0M
tokens
Larger than 91% of models
Max Output
384K
tokens
37% of context
Quality Index
46.5
37th of 507
Top 7%
Coding Index
38.7
53rd of 417
Top 13%
Price/1M
$0.18
173rd cheapest
69% below median
Top 27%
Speed
72 tok/s
Top 58%
TTFT
0.81s
Context Window
1.0M
15th largest
Top 9%