Open Dev Kit Documentation :: Open AI :: AI Completion Options :: Best Of

OpenAI.AICompletionOptions.BestOf

Generates this number of completions server-side and returns the 'best' (the one with the highest log probability per token). Results cannot be streamed. When used with Number, this controls the number of candidate completions and n specifies how many to return – this must be greater than Number. Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for Max Tokens and Stop.

Type

Integer

If you think anything is missing, please feel free to: submit documentation feedback on this page