google.generativeai.protos.GenerateContentResponse.UsageMetadata
Metadata on the generation request’s token usage.
Attributes |
|---|
|
`prompt_token_count`
|
`int`
Number of tokens in the prompt. When ``cached_content`` is
set, this is still the total effective prompt size meaning
this includes the number of tokens in the cached content.
|
|
`cached_content_token_count`
|
`int`
Number of tokens in the cached part of the
prompt (the cached content)
|
|
`candidates_token_count`
|
`int`
Total number of tokens across all the
generated response candidates.
|
|
`total_token_count`
|
`int`
Total token count for the generation request
(prompt + response candidates).
|
View source on GitHub