Type Alias Usage

Usage: {
    cached_tokens_by_modality?: ModalityTokens[];
    grounding_tool_count?: GroundingToolCount[];
    input_tokens_by_modality?: ModalityTokens[];
    output_tokens_by_modality?: ModalityTokens[];
    tool_use_tokens_by_modality?: ModalityTokens[];
    total_cached_tokens?: number;
    total_input_tokens?: number;
    total_output_tokens?: number;
    total_thought_tokens?: number;
    total_tokens?: number;
    total_tool_use_tokens?: number;
}

Statistics on the interaction request's token usage.

Type declaration

  • Optionalcached_tokens_by_modality?: ModalityTokens[]

    A breakdown of cached token usage by modality.

  • Optionalgrounding_tool_count?: GroundingToolCount[]

    Grounding tool count.

  • Optionalinput_tokens_by_modality?: ModalityTokens[]

    A breakdown of input token usage by modality.

  • Optionaloutput_tokens_by_modality?: ModalityTokens[]

    A breakdown of output token usage by modality.

  • Optionaltool_use_tokens_by_modality?: ModalityTokens[]

    A breakdown of tool-use token usage by modality.

  • Optionaltotal_cached_tokens?: number

    Number of tokens in the cached part of the prompt (the cached content).

  • Optionaltotal_input_tokens?: number

    Number of tokens in the prompt (context).

  • Optionaltotal_output_tokens?: number

    Total number of tokens across all the generated responses.

  • Optionaltotal_thought_tokens?: number

    Number of tokens of thoughts for thinking models.

  • Optionaltotal_tokens?: number

    Total token count for the interaction request (prompt + responses + other

    Remarks

    internal tokens).

  • Optionaltotal_tool_use_tokens?: number

    Number of tokens present in tool-use prompt(s).

Settings