Firebase.
Token usage metadata for processing the generate content request.
Summary
Properties |
|
|---|---|
CacheTokensDetails
|
IReadOnlyList< ModalityTokenCount >
Detailed breakdown of the cached tokens by modality (e.g., text, image).
|
CachedContentTokenCount
|
int
The number of tokens in the prompt that were served from the cache.
|
CandidatesTokenCount
|
int
The total number of tokens across the generated response candidates.
|
CandidatesTokensDetails
|
IReadOnlyList< ModalityTokenCount >
The breakdown, by modality, of how many tokens are consumed by the candidates.
|
PromptTokenCount
|
int
The number of tokens in the request prompt.
|
PromptTokensDetails
|
IReadOnlyList< ModalityTokenCount >
The breakdown, by modality, of how many tokens are consumed by the prompt.
|
ThoughtsTokenCount
|
int
The number of tokens used by the model's internal "thinking" process.
|
ToolUsePromptTokenCount
|
int
The number of tokens used by any enabled tools.
|
ToolUsePromptTokensDetails
|
IReadOnlyList< ModalityTokenCount >
The breakdown, by modality, of how many tokens were consumed by the tools used to process the request.
|
TotalTokenCount
|
int
The total number of tokens in both the request and response.
|
Properties
CacheTokensDetails
IReadOnlyList< ModalityTokenCount > Firebase::AI::UsageMetadata::CacheTokensDetails
Detailed breakdown of the cached tokens by modality (e.g., text, image).
This list provides granular insight into which parts of the content were cached.
CachedContentTokenCount
int Firebase::AI::UsageMetadata::CachedContentTokenCount
The number of tokens in the prompt that were served from the cache.
If implicit caching is not active or no content was cached, this will be 0.
CandidatesTokenCount
int Firebase::AI::UsageMetadata::CandidatesTokenCount
The total number of tokens across the generated response candidates.
CandidatesTokensDetails
IReadOnlyList< ModalityTokenCount > Firebase::AI::UsageMetadata::CandidatesTokensDetails
The breakdown, by modality, of how many tokens are consumed by the candidates.
PromptTokenCount
int Firebase::AI::UsageMetadata::PromptTokenCount
The number of tokens in the request prompt.
PromptTokensDetails
IReadOnlyList< ModalityTokenCount > Firebase::AI::UsageMetadata::PromptTokensDetails
The breakdown, by modality, of how many tokens are consumed by the prompt.
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.
ToolUsePromptTokenCount
int Firebase::AI::UsageMetadata::ToolUsePromptTokenCount
The number of tokens used by any enabled tools.
ToolUsePromptTokensDetails
IReadOnlyList< ModalityTokenCount > Firebase::AI::UsageMetadata::ToolUsePromptTokensDetails
The breakdown, by modality, of how many tokens were consumed by the tools used to process the request.
TotalTokenCount
int Firebase::AI::UsageMetadata::TotalTokenCount
The total number of tokens in both the request and response.