Firebase. AI. UsageMetadata
Token usage metadata for processing the generate content request.
Summary
Properties |
|
---|---|
CandidatesTokenCount
|
int
The total number of tokens across the generated response candidates.
|
CandidatesTokensDetails
|
IReadOnlyList< ModalityTokenCount >
|
PromptTokenCount
|
int
The number of tokens in the request prompt.
|
PromptTokensDetails
|
IReadOnlyList< ModalityTokenCount >
|
ThoughtsTokenCount
|
int
The number of tokens used by the model's internal "thinking" process.
|
TotalTokenCount
|
int
The total number of tokens in both the request and response.
|
Properties
CandidatesTokenCount
int Firebase::AI::UsageMetadata::CandidatesTokenCount
The total number of tokens across the generated response candidates.
CandidatesTokensDetails
IReadOnlyList< ModalityTokenCount > Firebase::AI::UsageMetadata::CandidatesTokensDetails
PromptTokenCount
int Firebase::AI::UsageMetadata::PromptTokenCount
The number of tokens in the request prompt.
PromptTokensDetails
IReadOnlyList< ModalityTokenCount > Firebase::AI::UsageMetadata::PromptTokensDetails
ThoughtsTokenCount
int Firebase::AI::UsageMetadata::ThoughtsTokenCount
The number of tokens used by the model's internal "thinking" process.
For models that support thinking (like Gemini 2.5 Pro and Flash), this represents the actual number of tokens consumed for reasoning before the model generated a response. For models that do not support thinking, this value will be 0
.
When thinking is used, this count will be less than or equal to the thinkingBudget
set in the ThinkingConfig
.
TotalTokenCount
int Firebase::AI::UsageMetadata::TotalTokenCount
The total number of tokens in both the request and response.