AutoBE
    Preparing search index...

    Detailed token usage component with comprehensive input and output breakdowns.

    Provides granular tracking of token consumption for a specific agent or processing phase, including detailed analysis of input tokens (with caching considerations) and output tokens (with different generation types). This detailed breakdown enables precise cost analysis and performance optimization.

    interface IComponent {
        input: IInput;
        output: IOutput;
        total: number;
    }

    Implemented by

    Index

    Properties

    Properties

    input: IInput

    Detailed breakdown of input token consumption.

    Provides specific analysis of tokens used for input processing, including both fresh token consumption and cached token reuse. This breakdown helps understand the efficiency of caching mechanisms and input processing optimization opportunities.

    output: IOutput

    Detailed breakdown of output token generation.

    Provides specific analysis of tokens used for output generation, including different types of generation such as reasoning, predictions, and rejected alternatives. This breakdown helps understand the AI's processing efficiency and quality of generated content.

    total: number

    Total token usage combining all input and output tokens.

    Represents the complete token consumption for this component, providing a single metric for overall resource utilization that can be used for cost calculations and performance comparisons across different agents and processing phases.