DeepSeek V3 0324 chat
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the DeepSeek V3 model and performs really well...
Capabilities
Context Window 163k tokens
Max Output 16k tokens
Inputs
Outputs
Pricing (per 1M tokens)
Input $0.20
Output $0.77
Cache Read $0.14
Cache Write -
Supported Parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p