Mmodel.kanadakurniwan
deepseekBerbayar

DeepSeek: DeepSeek V3.2

deepseek/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...

Harga input / 1M token
$0.2690
Harga output / 1M token
$0.4000
Context length
163.840

Modalitas

Input
text
Output
text

Parameter yang didukung

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Rilis

1 Desember 2025

Buka di OpenRouter ↗