prompt-executor-openai-client-base/ai.koog.prompt.executor.clients.openai.base.models/CompletionTokensDetails

CompletionTokensDetails

class CompletionTokensDetails(val acceptedPredictionTokens: Int? = null, val audioTokens: Int? = null, val reasoningTokens: Int? = null, val rejectedPredictionTokens: Int? = null)(source)

Constructors

constructor(acceptedPredictionTokens: Int? = null, audioTokens: Int? = null, reasoningTokens: Int? = null, rejectedPredictionTokens: Int? = null)

Properties

acceptedPredictionTokens

val acceptedPredictionTokens: Int? = null

When using Predicted Outputs, the number of tokens in the prediction that appeared in the completion.

audioTokens

val audioTokens: Int? = null

Audio input tokens generated by the model.

reasoningTokens

val reasoningTokens: Int? = null

Tokens generated by the model for reasoning.

rejectedPredictionTokens

val rejectedPredictionTokens: Int? = null

When using Predicted Outputs, the number of tokens in the prediction that did not appear in the completion. However, like reasoning tokens, these tokens are still counted in the total completion tokens for purposes of billing, output and context window limits.