Optional
cachedOutput only. Number of tokens in the cached part in the input (the cached content).
Optional
cacheOutput only. List of modalities of the cached content in the request input.
Optional
candidatesNumber of tokens in the response(s).
Optional
candidatesOutput only. List of modalities that were returned in the response.
Optional
promptNumber of tokens in the request. When cached_content
is set, this is still the total effective prompt size meaning this includes the number of tokens in the cached content.
Optional
promptOutput only. List of modalities that were processed in the request input.
Optional
thoughtsOutput only. Number of tokens present in thoughts output.
Optional
toolOutput only. Number of tokens present in tool-use prompt(s).
Optional
toolOutput only. List of modalities that were processed for tool-use request inputs.
Optional
totalTotal token count for prompt, response candidates, and tool-use prompts (if present).
Optional
trafficOutput only. Traffic type. This shows whether a request consumes Pay-As-You-Go or Provisioned Throughput quota.
Usage metadata about response(s).