Consistency - used to control the degree of randomness or creativity in the generated text. A high consistency value will lead to more deep and diverse responses, while a low consistency value will lead to more predictable and conservative responses. Another way to think of it is that a high temperature value allows more exploration of the model's knowledge. In contrast, a low temperature value encourages exploitation of what the model already knows.
Maximum tokens - limits the maximum amount of *tokens bot can use for it’s response.
*Token - is resource AI bot consume to generate the response.