Mmodel.kanadakurniwan
deepseekBerbayar

DeepSeek: DeepSeek V4 Flash 0423

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...

Harga input / 1M token
$0.0886
Harga output / 1M token
$0.1772
Context length
1.048.576

Modalitas

Input
text
Output
text

Parameter yang didukung

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p

Rilis

24 April 2026

Buka di OpenRouter ↗