UsageMetadata
io.cequence.openaiscala.gemini.domain.response.UsageMetadata
case class UsageMetadata(promptTokenCount: Int, cachedContentTokenCount: Option[Int], candidatesTokenCount: Option[Int], totalTokenCount: Int, promptTokensDetails: Seq[ModalityTokenCount], cacheTokensDetails: Seq[ModalityTokenCount], candidatesTokensDetails: Seq[ModalityTokenCount])
Metadata on the generation request's token usage.
Attributes
- cacheTokensDetails
Output only. List of modalities of the cached content in the request input.
- cachedContentTokenCount
Number of tokens in the cached part of the prompt (the cached content).
- candidatesTokenCount
Total number of tokens across all the generated response candidates.
- candidatesTokensDetails
Output only. List of modalities that were returned in the response.
- promptTokenCount
Number of tokens in the prompt. When cachedContent is set, this is still the total effective prompt size meaning this includes the number of tokens in the cached content.
- promptTokensDetails
Output only. List of modalities that were processed in the request input.
- totalTokenCount
Total token count for the generation request (prompt + response candidates).
- Graph
- Supertypes
- trait Serializabletrait Producttrait Equalsclass Objecttrait Matchableclass Any