Back to all models
deepseek
deepseekDeepSeek: DeepSeek V4 Pro 0423
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
deepseek/deepseek-v4-pro
Context Size
1,048.576K
Input Price
143,289 pts/M8,812 Ks/M
Output Price
286,578 pts/M17,625 Ks/M
Architecture
Text
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Details
TokenizerDeepSeek
Max Completion384,000 tokens
Provider Context1,024K tokens
ModeratedNo
CreatedApr 24, 2026