← 模型广场
DeepSeek: DeepSeek V4 Flash
deepseek/deepseek-v4-flash
工具调用JSON推理流式
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
价格
输入
$0.098 / 1M
输出
$0.197 / 1M
参数
上下文
1,048,576 tokens
输入模态
text
输出模态
text
发布：2026-04
支持参数
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p