模型资料变化
缓存命中价格:0.006 → 0.012
AI 模型档案 · 当前可用
DeepSeek 的 AI 模型,支持 工具调用、结构化输出、图片理解,上下文窗口 1.05M 词元。
deepseek/deepseek-v4.1-flash
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p
缓存命中价格:0.006 → 0.012