CompletionTokenDetails

@Serializable
class CompletionTokenDetails(val reasoningTokens: Int)

Breakdown of how the completion_tokens count in Usage was spent.

Populated when the model runs in thinking mode, which produces separate reasoning output in addition to the visible assistant message.

Constructors

Link copied to clipboard
constructor(reasoningTokens: Int)

Properties

Link copied to clipboard

Number of tokens the model produced as reasoning content.

Functions

Link copied to clipboard
open operator override fun equals(other: Any?): Boolean
Link copied to clipboard
open override fun hashCode(): Int
Link copied to clipboard
open override fun toString(): String