DeepSeek V3.2 Speciale reasoning

openrouter
deepseek
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...

Capabilities

Context Window 163k tokens
Max Output 163k tokens
Inputs
Outputs

Pricing (per 1M tokens)

Input $0.29
Output $0.43
Cache Read $0.06
Cache Write -

Supported Parameters

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_p