CacheUsageMetadata#

class langchain_google_vertexai.model_garden.CacheUsageMetadata[source]#
input_tokens: int#
output_tokens: int#
total_tokens: int#
input_token_details: NotRequired[InputTokenDetails]#
output_token_details: NotRequired[OutputTokenDetails]#
cache_creation_input_tokens: int | None#

The number of input tokens used to create the cache entry.

cache_read_input_tokens: int | None#

The number of input tokens read from the cache.