Model 3.5-turbo is the fastest, cheapest model, other models are not avialble for everyone they are in limited beta so if you did not apply on the waitlist and get access already, do not pick any of them.
What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. Defaults to 1
Tests showed that setting this value to something high makes the request processing time go from 30 seconds to more than 5 minutes, better leave as-is.
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or temperature but not both. Defaults to 1.
Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. Defaults to 0.
Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. Defaults to 0.
If you have a fine tuned model, you can use it here, if you do not have one, leave this field empty.