Loading...
Loading...
DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
Input
$0.25
per 1M tokens
Output
$0.38
per 1M tokens
Blended
$0.28
per 1M tokens
Cheaper than 63% of models. Median price is $0.56/1M tokens.
Daily
$0.28
Monthly
$8.50
80
tokens/sec
Faster than 47% of models
0.74
seconds
Faster than 65% of models
0.74
seconds
Faster than 74% of models
Market Median
86 tok/s
7% slower
Median TTFT
1.07s
31% faster
Throughput/Dollar
283
tok/s per $/1M
Speed Comparison
Context Window
131K
tokens
Larger than 33% of models
Max Output
66K
tokens
50% of context
Quality Index
32.1
130th of 507
Top 26%
Coding Index
34.6
87th of 417
Top 21%
Math Index
59.0
118th of 269
Top 44%
Price/1M
$0.28
233rd cheapest
49% below median
Top 37%
Speed
80 tok/s
Top 53%
TTFT
0.74s
Context Window
131K
201st largest
Top 67%