Captured photo
DeepSeek V4 Flash
5 +

About

DeepSeek's fast, low-cost flagship model with 1M token context and dual thinking/non-thinking modes

Settings

Response length-  The maximum number of tokens to generate in the output.
Temperature-  The temperature of the model. Higher values make the model more creative and lower values make it more focused.
Diversity control-  Top_p. Filters AI responses based on probability.
Lower values = top few likely responses,
Higher values = larger pool of options.
Context length-  The maximum number of tokens to use as input for a model.