DeepSeek Kotlin SDK/org.oremif.deepseek.models/PromptTokensDetails

PromptTokensDetails

@Serializable

class PromptTokensDetails(val cachedTokens: Int? = null)

Breakdown of the prompt tokens counted by Usage, decoded from the OpenAI-compatible prompt_tokens_details key.

Current responses omit that key and report cache accounting through the flat Usage.promptCacheHitTokens / Usage.promptCacheMissTokens fields instead.

Constructors

PromptTokensDetails

constructor(cachedTokens: Int? = null)

Properties

val cachedTokens: Int?

Number of prompt tokens served from the context cache, or null when the server did not report this breakdown.

Functions

open operator override fun equals(other: Any?): Boolean

open override fun hashCode(): Int

open override fun toString(): String