Back to all models
deepseek
deepseekDeepSeek: DeepSeek V3.2
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...
deepseek/deepseek-v3.2
Context Size
131.072K
Input Price
34,320 pts/M
Output Price
51,480 pts/M
Architecture
Text
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Details
TokenizerDeepSeek
Max Completion64,000 tokens
Provider Context128K tokens
ModeratedNo
CreatedDec 1, 2025