Loading...
Loading...
DeepSeek-V3.2-Speciale is a high-compute variant of DeepSeek-V3.2 optimized for maximum reasoning and agentic performance. It builds on DeepSeek Sparse Attention (DSA) for efficient long-context processing, then scales post-training reinforcement learning...
Input
$0.29
per 1M tokens
Output
$0.43
per 1M tokens
Blended
$0.32
per 1M tokens
Cheaper than 61% of models. Median price is $0.56/1M tokens.
Daily
$0.32
Monthly
$9.69
Context Window
164K
tokens
Larger than 52% of models
Max Output
164K
tokens
100% of context
Context Window Comparison
Quality Index
29.4
155th of 507
Top 31%
Coding Index
37.9
59th of 417
Top 14%
Math Index
96.7
4th of 269
Top 2%
Price/1M
$0.32
249th cheapest
42% below median
Top 39%
Context Window
164K
191st largest
Top 48%