public sealed class GenerateContentResponse.Types.UsageMetadata : IMessage<GenerateContentResponse.Types.UsageMetadata>, IEquatable<GenerateContentResponse.Types.UsageMetadata>, IDeepCloneable<GenerateContentResponse.Types.UsageMetadata>, IBufferMessage, IMessageReference documentation and code samples for the Cloud AI Platform v1beta1 API class GenerateContentResponse.Types.UsageMetadata.
Usage metadata about response(s).
Implements
IMessageGenerateContentResponseTypesUsageMetadata, IEquatableGenerateContentResponseTypesUsageMetadata, IDeepCloneableGenerateContentResponseTypesUsageMetadata, IBufferMessage, IMessageNamespace
Google.Cloud.AIPlatform.V1Beta1Assembly
Google.Cloud.AIPlatform.V1Beta1.dll
Constructors
UsageMetadata()
public UsageMetadata()UsageMetadata(UsageMetadata)
public UsageMetadata(GenerateContentResponse.Types.UsageMetadata other)| Parameter | |
|---|---|
| Name | Description |
other |
GenerateContentResponseTypesUsageMetadata |
Properties
CachedContentTokenCount
public int CachedContentTokenCount { get; set; }Output only. Number of tokens in the cached part in the input (the cached content).
| Property Value | |
|---|---|
| Type | Description |
int |
|
CandidatesTokenCount
public int CandidatesTokenCount { get; set; }Number of tokens in the response(s).
| Property Value | |
|---|---|
| Type | Description |
int |
|
PromptTokenCount
public int PromptTokenCount { get; set; }Number of tokens in the request. When cached_content is set, this is
still the total effective prompt size meaning this includes the number of
tokens in the cached content.
| Property Value | |
|---|---|
| Type | Description |
int |
|
TotalTokenCount
public int TotalTokenCount { get; set; }Total token count for prompt and response candidates.
| Property Value | |
|---|---|
| Type | Description |
int |
|