Ce que cette page répond
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 p
- DeepSeek · deepseek/deepseek-v3.2-speciale
- text->text · route modèle Chine
- 163 840 context · 0,40 $US input