firebase-js-sdk/docs-devsite/ai.usagemetadata.md

Project: /docs/reference/js/_project.yaml Book: /docs/reference/_book.yaml page_type: reference

{% comment %} DO NOT EDIT THIS FILE! This is generated by the JS SDK team, and any local changes will be overwritten. Changes should be made in the source code at https://github.com/firebase/firebase-js-sdk {% endcomment %}

UsageMetadata interface

Usage metadata about a GenerateContentResponse.

Signature:

export interface UsageMetadata 

Properties

Property	Type	Description
cachedContentTokenCount	number	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.
cacheTokensDetails	ModalityTokenCount[]	Detailed breakdown of the cached tokens by modality (for example, text or image). This list provides granular insight into which parts of the content were cached.
candidatesTokenCount	number
candidatesTokensDetails	ModalityTokenCount[]
promptTokenCount	number
promptTokensDetails	ModalityTokenCount[]
thoughtsTokenCount	number	The number of tokens used by the model's internal "thinking" process.
toolUsePromptTokenCount	number	The number of tokens used by tools.
toolUsePromptTokensDetails	ModalityTokenCount[]	A list of tokens used by tools, broken down by modality.
totalTokenCount	number

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.

Signature:

cachedContentTokenCount?: number;

UsageMetadata.cacheTokensDetails

Detailed breakdown of the cached tokens by modality (for example, text or image). This list provides granular insight into which parts of the content were cached.

Signature:

cacheTokensDetails?: ModalityTokenCount[];

UsageMetadata.candidatesTokenCount

Signature:

candidatesTokenCount: number;

UsageMetadata.candidatesTokensDetails

Signature:

candidatesTokensDetails?: ModalityTokenCount[];

UsageMetadata.promptTokenCount

Signature:

promptTokenCount: number;

UsageMetadata.promptTokensDetails

Signature:

promptTokensDetails?: ModalityTokenCount[];

UsageMetadata.thoughtsTokenCount

The number of tokens used by the model's internal "thinking" process.

Signature:

thoughtsTokenCount?: number;

UsageMetadata.toolUsePromptTokenCount

The number of tokens used by tools.

Signature:

toolUsePromptTokenCount?: number;

UsageMetadata.toolUsePromptTokensDetails

A list of tokens used by tools, broken down by modality.

Signature:

toolUsePromptTokensDetails?: ModalityTokenCount[];

UsageMetadata.totalTokenCount

Signature:

totalTokenCount: number;