Skip to content

TokenUsage

Structure Class

TokenUsage dataclass

Bases: _SerdeShape

The token consumption statistics for language model operations during evaluation. Provides detailed breakdown of input, output, and total tokens used for cost tracking and performance monitoring.

Attributes

input_tokens class-attribute instance-attribute
input_tokens: int | None = ...

The number of tokens consumed for input processing during the evaluation. Includes tokens from the evaluation prompt, agent traces, and any additional context provided to the evaluator model.

output_tokens class-attribute instance-attribute
output_tokens: int | None = ...

The number of tokens generated by the evaluator model in its response. Includes tokens for the score, explanation, and any additional output produced during the evaluation process.

total_tokens class-attribute instance-attribute
total_tokens: int | None = ...

The total number of tokens consumed during the evaluation, calculated as the sum of input and output tokens. Used for cost calculation and rate limiting within the service limits.