DeepSeek: DeepSeek V3.2 Specialedeepseek
DeepSeek: DeepSeek V3.2 Speciale: $0.29/1M input, $0.43/1M output, 164K context, CPS grade A. 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...
API Pricing (per 1M tokens)
| Input | $0.29 |
| Output | $0.43 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.32 |
Specs & Performance
| Context Length | 164K |
| Max Output | 164K |
| Intelligence | 15 |
| Coding | 38 |
| Math | 97 |
| Speed | — |
| TTFT | — |
| CPS Grade | A |
| Input / Output Modalities | text → text |
More from deepseek
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the DeepSeek: DeepSeek V3.2 Speciale API cost?
DeepSeek: DeepSeek V3.2 Speciale costs $0.29/1M input tokens and $0.43/1M output tokens. Blended cost at a 3:1 ratio is about $0.32/1M tokens.
What is the context window of DeepSeek: DeepSeek V3.2 Speciale?
DeepSeek: DeepSeek V3.2 Speciale supports a 164K token context window with up to 164K output tokens.
Is DeepSeek: DeepSeek V3.2 Speciale worth it?
DeepSeek: DeepSeek V3.2 Speciale has a CPS grade of A (score 67), intelligence index 15, coding index 38. Use the compare page to benchmark against rivals.