IMPORTANT: In July 2025, we stopped releasing new versions of KTX modules, and we removed the KTX libraries from the Firebase Android BoM (v34.0.0). If you use KTX APIs from the previously released KTX modules, we recommend that you migrate your app to use KTX APIs from the main modules instead. For details, see the FAQ about this initiative.

UsageMetadata

class UsageMetadata

Usage metadata about response(s).

Summary

Public constructors
`UsageMetadata( promptTokenCount: Int, candidatesTokenCount: Int?, totalTokenCount: Int, promptTokensDetails: List<ModalityTokenCount>, candidatesTokensDetails: List<ModalityTokenCount>, thoughtsTokenCount: Int )`

Public properties
`Int?`	`candidatesTokenCount` Number of tokens in the response(s).
`List<ModalityTokenCount>`	`candidatesTokensDetails` The breakdown, by modality, of how many tokens are consumed by the candidates.
`Int`	`promptTokenCount` Number of tokens in the request.
`List<ModalityTokenCount>`	`promptTokensDetails` The breakdown, by modality, of how many tokens are consumed by the prompt.
`Int`	`thoughtsTokenCount` The number of tokens used by the model's internal "thinking" process.
`Int`	`totalTokenCount` Total number of tokens.

Public constructors

UsageMetadata

UsageMetadata(
    promptTokenCount: Int,
    candidatesTokenCount: Int?,
    totalTokenCount: Int,
    promptTokensDetails: List<ModalityTokenCount>,
    candidatesTokensDetails: List<ModalityTokenCount>,
    thoughtsTokenCount: Int
)

Parameters
`promptTokenCount: Int`	Number of tokens in the request.
`candidatesTokenCount: Int?`	Number of tokens in the response(s).
`totalTokenCount: Int`	Total number of tokens.
`promptTokensDetails: List<ModalityTokenCount>`	The breakdown, by modality, of how many tokens are consumed by the prompt.
`candidatesTokensDetails: List<ModalityTokenCount>`	The breakdown, by modality, of how many tokens are consumed by the candidates.
`thoughtsTokenCount: Int`	The number of tokens used by the model's internal "thinking" process.

Public properties

candidatesTokenCount

val candidatesTokenCount: Int?

Number of tokens in the response(s).

candidatesTokensDetails

val candidatesTokensDetails: List<ModalityTokenCount>

The breakdown, by modality, of how many tokens are consumed by the candidates.

promptTokenCount

val promptTokenCount: Int

Number of tokens in the request.

promptTokensDetails

val promptTokensDetails: List<ModalityTokenCount>

The breakdown, by modality, of how many tokens are consumed by the prompt.

thoughtsTokenCount

val thoughtsTokenCount: Int

The number of tokens used by the model's internal "thinking" process.

totalTokenCount

val totalTokenCount: Int

Total number of tokens.