Class UsageMetadata (2.8.0)

UsageMetadata(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Usage metadata about the content generation request and response. This message provides a detailed breakdown of token usage and other relevant metrics.

Attributes

Name Description
prompt_token_count int
The total number of tokens in the prompt. This includes any text, images, or other media provided in the request. When cached_content is set, this also includes the number of tokens in the cached content.
candidates_token_count int
The total number of tokens in the generated candidates.
total_token_count int
The total number of tokens for the entire request. This is the sum of prompt_token_count, candidates_token_count, tool_use_prompt_token_count, and thoughts_token_count.
tool_use_prompt_token_count int
Output only. The number of tokens in the results from tool executions, which are provided back to the model as input, if applicable.
thoughts_token_count int
Output only. The number of tokens that were part of the model's generated "thoughts" output, if applicable.
cached_content_token_count int
Output only. The number of tokens in the cached content that was used for this request.
prompt_tokens_details MutableSequence[google.cloud.aiplatform_v1beta1.types.ModalityTokenCount]
Output only. A detailed breakdown of the token count for each modality in the prompt.
cache_tokens_details MutableSequence[google.cloud.aiplatform_v1beta1.types.ModalityTokenCount]
Output only. A detailed breakdown of the token count for each modality in the cached content.
candidates_tokens_details MutableSequence[google.cloud.aiplatform_v1beta1.types.ModalityTokenCount]
Output only. A detailed breakdown of the token count for each modality in the generated candidates.
tool_use_prompt_tokens_details MutableSequence[google.cloud.aiplatform_v1beta1.types.ModalityTokenCount]
Output only. A detailed breakdown by modality of the token counts from the results of tool executions, which are provided back to the model as input.
traffic_type google.cloud.aiplatform_v1beta1.types.UsageMetadata.TrafficType
Output only. The traffic type for this request.

Classes

TrafficType

TrafficType(value)

The type of traffic that this request was processed with, indicating which quota gets consumed.

Methods

UsageMetadata

UsageMetadata(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Usage metadata about the content generation request and response. This message provides a detailed breakdown of token usage and other relevant metrics.