# How does multi-turn conversation work in the o1-preview Chat Completion API? **URL:** \ **Category:** API\ **Tags:** o1-preview\ **Created:** [September 21, 2024, 1:04am UTC](https://community.openai.com/t/how-does-multi-turn-conversation-work-in-the-o1-preview-chat-completion-api/949837 "2024-09-21T01:04:18Z")\ **Posts on this page:** 1\ **Showing post:** 3
**Author:** ![sps](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/sps/32/7736_2.png) [@sps](https://community.openai.com/u/sps)\ **Post date:** [September 21, 2024, 5:59am UTC](https://community.openai.com/t/how-does-multi-turn-conversation-work-in-the-o1-preview-chat-completion-api/949837/3 "2024-09-21T05:59:14Z")
Welcome @jarrelscy1 Per the docs, reasoning tokens are discarded: > ## [How reasoning works](https://platform.openai.com/docs/guides/reasoning/how-reasoning-works) > > The o1 models introduce reasoning tokens. The models use these reasoning tokens to “think”, breaking down their understanding of the prompt and considering multiple approaches to generating a response. After generating reasoning tokens, the model produces an answer as visible completion tokens, and discards the reasoning tokens from its context. > > Here is an example of a multi-step conversation between a user and an assistant. Input and output tokens from each step are carried over, while reasoning tokens are discarded. > > ![The image visually explains how the input, reasoning, and output processes work across multiple turns within a set context window of 128k tokens, highlighting that the reasoning is discarded with only input and output retained from the previous turn. (Captioned by AI)](https://us1.discourse-cdn.com/openai1/original/4X/7/b/9/7b9a1766ec182e5753cef660cfb3bc05d100ba1e.png) --- _[View the full topic](https://community.openai.com/t/how-does-multi-turn-conversation-work-in-the-o1-preview-chat-completion-api/949837)._