Package org.springframework.ai.google.genai.metadata

Class GoogleGenAiUsage

java.lang.Object

org.springframework.ai.chat.metadata.DefaultUsage

org.springframework.ai.google.genai.metadata.GoogleGenAiUsage

All Implemented Interfaces:

Usage

public class GoogleGenAiUsage
extends DefaultUsage

Extended usage metadata for Google GenAI responses that includes thinking tokens, cached content, tool-use tokens, and modality breakdowns.

Since:

1.1.0

Author:

Dan Dobrin

Constructor Summary

Constructors

Constructor

Description

GoogleGenAiUsage(Integer promptTokens, Integer completionTokens, Integer totalTokens, Integer thoughtsTokenCount, Integer cachedContentTokenCount, Integer toolUsePromptTokenCount, List<GoogleGenAiModalityTokenCount> promptTokensDetails, List<GoogleGenAiModalityTokenCount> candidatesTokensDetails, List<GoogleGenAiModalityTokenCount> cacheTokensDetails, List<GoogleGenAiModalityTokenCount> toolUsePromptTokensDetails, GoogleGenAiTrafficType trafficType, com.google.genai.types.GenerateContentResponseUsageMetadata nativeUsage)

Creates a new GoogleGenAiUsage instance with all extended metadata.

Method Summary

Modifier and Type	Method	Description
static GoogleGenAiUsage	from(com.google.genai.types.GenerateContentResponseUsageMetadata usageMetadata)	Creates a GoogleGenAiUsage instance from the Google GenAI SDK response metadata.
Integer	getCachedContentTokenCount()	Returns the number of tokens in the cached content.
Long	getCacheReadInputTokens()	Returns the number of input tokens read from the prompt cache, if the provider supports prompt caching.
List<GoogleGenAiModalityTokenCount>	getCacheTokensDetails()	Returns the list of modalities of the cached content in the request input.
List<GoogleGenAiModalityTokenCount>	getCandidatesTokensDetails()	Returns the list of modalities that were returned in the response.
List<GoogleGenAiModalityTokenCount>	getPromptTokensDetails()	Returns the list of modalities that were processed in the request input.
Integer	getThoughtsTokenCount()	Returns the number of tokens present in thoughts output for thinking-enabled models.
Integer	getToolUsePromptTokenCount()	Returns the number of tokens present in tool-use prompts.
List<GoogleGenAiModalityTokenCount>	getToolUsePromptTokensDetails()	Returns the list of modalities that were processed for tool-use request inputs.
GoogleGenAiTrafficType	getTrafficType()	Returns the traffic type showing whether a request consumes Pay-As-You-Go or Provisioned Throughput quota.
String	toString()

Methods inherited from class org.springframework.ai.chat.metadata.DefaultUsage

equals, fromJson, getCacheWriteInputTokens, getCompletionTokens, getNativeUsage, getPromptTokens, getTotalTokens, hashCode

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Constructor Details

GoogleGenAiUsage

public GoogleGenAiUsage(Integer promptTokens,
 Integer completionTokens,
 Integer totalTokens,
 @Nullable
 Integer thoughtsTokenCount,
 @Nullable
 Integer cachedContentTokenCount,
 @Nullable
 Integer toolUsePromptTokenCount,
 @Nullable
 List<GoogleGenAiModalityTokenCount> promptTokensDetails,
 @Nullable
 List<GoogleGenAiModalityTokenCount> candidatesTokensDetails,
 @Nullable
 List<GoogleGenAiModalityTokenCount> cacheTokensDetails,
 @Nullable
 List<GoogleGenAiModalityTokenCount> toolUsePromptTokensDetails,
 @Nullable
 GoogleGenAiTrafficType trafficType,
 @Nullable
 com.google.genai.types.GenerateContentResponseUsageMetadata nativeUsage)

Creates a new GoogleGenAiUsage instance with all extended metadata.

Method Details

from

public static GoogleGenAiUsage from(com.google.genai.types.GenerateContentResponseUsageMetadata usageMetadata)

Creates a GoogleGenAiUsage instance from the Google GenAI SDK response metadata.

Parameters:

usageMetadata - the usage metadata from the Google GenAI SDK

Returns:

a new GoogleGenAiUsage instance with all available metadata

getThoughtsTokenCount

@Nullable
public Integer getThoughtsTokenCount()

Returns the number of tokens present in thoughts output for thinking-enabled models.

Returns:

the thoughts token count, or null if not available

getCachedContentTokenCount

@Nullable
public Integer getCachedContentTokenCount()

Returns the number of tokens in the cached content.

Returns:

the cached content token count, or null if not available

getCacheReadInputTokens

@Nullable
public Long getCacheReadInputTokens()

Description copied from interface: Usage

Returns the number of input tokens read from the prompt cache, if the provider supports prompt caching. Cached tokens are tokens that were previously processed and stored by the provider, reducing cost and latency for repeated prompt prefixes.

Specified by:

getCacheReadInputTokens in interface Usage

Overrides:

getCacheReadInputTokens in class DefaultUsage

Returns:

the number of cached input tokens read, or null if the provider does not support prompt caching or no cache hit occurred.

getToolUsePromptTokenCount

@Nullable
public Integer getToolUsePromptTokenCount()

Returns the number of tokens present in tool-use prompts.

Returns:

the tool-use prompt token count, or null if not available

getPromptTokensDetails

@Nullable
public List<GoogleGenAiModalityTokenCount> getPromptTokensDetails()

Returns the list of modalities that were processed in the request input.

Returns:

the prompt tokens details by modality, or null if not available

getCandidatesTokensDetails

@Nullable
public List<GoogleGenAiModalityTokenCount> getCandidatesTokensDetails()

Returns the list of modalities that were returned in the response.

Returns:

the candidates tokens details by modality, or null if not available

getCacheTokensDetails

@Nullable
public List<GoogleGenAiModalityTokenCount> getCacheTokensDetails()

Returns the list of modalities of the cached content in the request input.

Returns:

the cache tokens details by modality, or null if not available

getToolUsePromptTokensDetails

@Nullable
public List<GoogleGenAiModalityTokenCount> getToolUsePromptTokensDetails()

Returns the list of modalities that were processed for tool-use request inputs.

Returns:

the tool-use prompt tokens details by modality, or null if not available

getTrafficType

@Nullable
public GoogleGenAiTrafficType getTrafficType()

Returns the traffic type showing whether a request consumes Pay-As-You-Go or Provisioned Throughput quota.

Returns:

the traffic type, or null if not available

toString

public String toString()

Overrides:

toString in class DefaultUsage