---
title: "cachedPromptTokens"
sidebar_label: "cachedPromptTokens"
description: "Kotlin binding reference: cachedPromptTokens."
---

<!-- Generated by tools/api_reference/generate_api_docs.py. Do not edit. -->

//[clika-runtime](../../../index.md)/[io.clika.modelverse](../index.md)/[GenerationReport](index.md)/[cachedPromptTokens](cachedPromptTokens.md)

# cachedPromptTokens

[common]\
val [cachedPromptTokens](cachedPromptTokens.md): [Int](https://kotlinlang.org/api/core/kotlin-stdlib/kotlin/-int/index.html) = 0

Of [promptTokens](promptTokens.md), the tokens the model's cache served from an earlier turn instead of computing them again: a chat sends the whole conversation on every turn, and the text model keeps a finished turn's cache for the next; 0 when nothing was served.