DeepSeek V4 Pro reasoning

openrouter
deepseek
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,...

Capabilities

Context Window 1M tokens
Max Output 384k tokens
Inputs
Outputs

Pricing (per 1M tokens)

Input $0.43
Output $0.87
Cache Read $0.04
Cache Write -

Supported Parameters

frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningresponse_formatseedstoptemperaturetool_choicetoolstop_ktop_logprobstop_p

Move Chat

Select a destination folder:

Move Folder

Select a parent folder:

Folder Settings