Class ApiChatCompletionsResponseUsageCompletionTokenDetails
java.lang.Object
de.xima.fc.prompt.ms.impl.service.generic_oai.client.json.ApiChatCompletionsResponseUsageCompletionTokenDetails
Breakdown of tokens used in a completion.
- Since:
- 8.5.0
-
Method Summary
Modifier and TypeMethodDescriptionWhen using Predicted Outputs, the number of tokens in the prediction that appeared in the completion.Audio input tokens generated by the model.Tokens generated by the model for reasoning.When using Predicted Outputs, the number of tokens in the prediction that did not appear in the completion.
-
Method Details
-
acceptedPredictionTokens
When using Predicted Outputs, the number of tokens in the prediction that appeared in the completion.- Returns:
- The number of accepted prediction tokens.
-
audioTokens
Audio input tokens generated by the model.- Returns:
- The number of audio tokens.
-
reasoningTokens
Tokens generated by the model for reasoning.- Returns:
- The number of reasoning tokens.
-
rejectedPredictionTokens
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.- Returns:
- The number of rejected prediction tokens.
-