Skip to main content

​
MaxTokens

A class to be used on spawning an agent or decorating an agentic function to control the maximum number of output tokens generated by the underlying model. 
export class MaxTokens {
    constructor(
        public perInvocation: number | null = null,
        public perRound: number | null = null,
        public rounds: number | null = null
    ) {}
}
Parameters
​
per_invocation
int | null
The maximum number of output tokens generated over all rounds of inference in a single invocation.Defaults to null meaning unlimited.
​
per_round
int | null
The maximum number of output tokens generated in a single round of inference in a single invocation.Defaults to null meaning unlimited.
​
rounds
int | null
The maximum number of rounds of inference in a single invocation.Defaults to null meaning unlimited.

​
Usage

A class outlining the token usage of the underlying model of an agent or agentic function. 
export class Usage {
    /**
     * Note: `totalTokens` is not always equal to `inputTokens + outputTokens`.
     * It represents the total tokens involved within the timeframe.
     */
    constructor(
        public readonly inputTokens: number,
        public readonly outputTokens: number,
        public readonly totalTokens: number,
        public readonly cachedTokens: number = 0,
        public readonly reasoningTokens: number = 0
    ) {}
}
Parameters
​
inputTokens
number
The number of input tokens consumed by the model.
​
outputTokens
number
The number of output tokens generated by the model.
​
totalTokens
number
The total number of tokens processed, not double-counting generated then re-consumed tokens.
​
cachedTokens
number
The number of input tokens that were served from cache. Defaults to 0.
​
reasoningTokens
number
The number of tokens used for internal reasoning / chain-of-thought. Defaults to 0.