Back to all models
~deepseek
~deepseekDeepSeek: DeepSeek V4 Flash Latest
This model always redirects to the latest model in the DeepSeek V4 Flash family.
~deepseek/deepseek-v4-flash-latest
Context Size
1,048.576K
Input Price
4,965 pts/M305 Ks/M
Output Price
45,000 pts/M2,767 Ks/M
Architecture
Text
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p
Details
TokenizerRouter
Max Completion943,718 tokens
Provider Context1,048.576K tokens
ModeratedNo
CreatedAug 1, 2026