ThePromptBuddy logoThePromptBuddy

DeepSeek

DeepSeek: DeepSeek V4 Flash

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...

Specifications
ProviderDeepSeek
Input pricing$0.09/M tokens
Output pricing$0.19/M tokens
Context length1.0M tokens
Input modalities
text
Output modalities
text
TokenizerDeepSeek
Content moderatedNo
HuggingFacedeepseek-ai/DeepSeek-V4-Flash

Supported Parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p