---
title: "Why do similar OpenAI API requests show different cached-token counts?"  
description: "Why do similar OpenAI API requests show different cached-token counts?"  
author: "Stefano Coppola"  
published: 2026-10-17  
updated: 2026-10-17  
canonical: https://www.mindstick.com/forum/162546/why-do-similar-openai-api-requests-show-different-cached-token-counts  
category: "OpenAI API"  
tags: ["OpenAI", "Prompt Caching", "API costs"]  
reading_time: 1 minute  

---

# Why do similar OpenAI API requests show different cached-token counts?

I’m trying to understand **[OpenAI prompt caching](https://www.mindstick.com/forum/162363/is-openai-prompt-caching-worth-reorganizing-a-frequently-used-prompt)** before using it in our cost estimates. Our support assistant sends the same instructions and tool definitions on most requests, but the cached-token count varies more than I expected.

The customer’s message changes each time. We also include a request timestamp near the beginning of the prompt, and our application sometimes changes the order of the tool definitions when building a request.

### What should I keep constant for a useful comparison?

- Does a changing timestamp near the start affect caching for the instructions that follow it?
- Does tool-definition order matter even when the available tools are identical?
- How should I separate prompt differences from timing or model-specific caching requirements?

I’d like to run a small, repeatable test using the reported **cached input tokens**, rather than guessing from response speed. Which request details and usage fields would you log to explain the differences?


---

Original Source: https://www.mindstick.com/forum/162546/why-do-similar-openai-api-requests-show-different-cached-token-counts

Copyright © MindStick Software Pvt. Ltd. This Markdown version is provided for developers, AI systems, and offline reading.