Loading...
Loading...
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
Input
$0.43
per 1M tokens
Output
$0.87
per 1M tokens
Blended
$0.54
per 1M tokens
Cheaper than 50% of models. Median price is $0.56/1M tokens.
Daily
$0.54
Monthly
$16.31
34
tokens/sec
Faster than 6% of models
1.14
seconds
Faster than 46% of models
128.36
seconds
Faster than 0% of models
Market Median
86 tok/s
60% slower
Median TTFT
1.07s
6% slower
Throughput/Dollar
63
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
51.5
16th of 507
Top 3%
Coding Index
47.5
17th of 417
Top 4%
Price/1M
$0.54
318th cheapest
3% below median
Top 50%
Speed
34 tok/s
Top 94%
TTFT
1.14s
Context Window
1.0M
15th largest
Top 9%