TokenUsage¶
Structure Class¶
dataclass
¶
The tokens used in a message API inference call.
Attributes¶
class-attribute
instance-attribute
¶
cache_details: list[CacheDetail] | None = None
Detailed breakdown of cache writes by TTL. Empty if no cache creation occurred. Sorted by TTL duration (1h before 5m).
class-attribute
instance-attribute
¶
cache_read_input_tokens: int | None = None
The number of input tokens read from the cache for the request.
class-attribute
instance-attribute
¶
cache_write_input_tokens: int | None = None
The number of input tokens written to the cache for the request.
instance-attribute
¶
input_tokens: int
The number of tokens sent in the request to the model.
instance-attribute
¶
output_tokens: int
The number of tokens that the model generated for the request.
instance-attribute
¶
total_tokens: int
The total of input tokens and tokens generated by the model.