# The generated code varies every time, even with a low temperature **URL:** \ **Category:** API\ **Tags:** assistants-api\ **Created:** [August 26, 2024, 2:46am UTC](https://community.openai.com/t/the-generated-code-varies-every-time-even-with-a-low-temperature/921970 "2024-08-26T02:46:20Z")\ **Posts on this page:** 6\ **Page:** 1
**Author:** ![takashi.asano](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/takashi.asano/32/146909_2.png) [@takashi.asano](https://community.openai.com/u/takashi.asano)\ **Post date:** [August 26, 2024, 2:46am UTC](https://community.openai.com/t/the-generated-code-varies-every-time-even-with-a-low-temperature/921970/1 "2024-08-26T02:46:21Z")
I am using “Assistants API” with gpt4o to generate the python code. We use “temprature=0.01” to get more less randomness with some instructions. With this environment, the generated code varies in every threads even if it is exact the same prompt. I am wondering if the instruction is interfering, or temperature have no effect on the code generation… Does anyone solve this issue? I would appreciate your help. Thanks. ---
**Author:** ![stevenic](https://avatars.discourse-cdn.com/v4/letter/s/e480ec/32.png) [@stevenic](https://community.openai.com/u/stevenic)\ **Post date:** [August 26, 2024, 4:48am UTC](https://community.openai.com/t/the-generated-code-varies-every-time-even-with-a-low-temperature/921970/2 "2024-08-26T04:48:41Z")
> [@takashi.asano](#): > > We use “temprature=0.01” to get more less randomness with some instructions. > With this environment, the generated code varies in every threads even if it is exact the same prompt. Setting **temperature** to 0.0 helps but it’s pretty much impossible to get completely deterministic outputs from the model. Setting the **seed** for your request to a constant value will get you even closer to the same output but I’ll tell you that even that doesn’t really work. In addition to the fact these models are non-deterministic, OpenAI is constantly fine tuning the model so the weights are changing on you several times a day. ---
**Author:** ![takashi.asano](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/takashi.asano/32/146909_2.png) [@takashi.asano](https://community.openai.com/u/takashi.asano)\ **Post date:** [August 26, 2024, 5:17am UTC](https://community.openai.com/t/the-generated-code-varies-every-time-even-with-a-low-temperature/921970/3 "2024-08-26T05:17:51Z")
As far as I understand, the assistant API does not support the seed parameter yet. Is this correct? ---
**Author:** ![stevenic](https://avatars.discourse-cdn.com/v4/letter/s/e480ec/32.png) [@stevenic](https://community.openai.com/u/stevenic)\ **Post date:** [August 26, 2024, 7:16am UTC](https://community.openai.com/t/the-generated-code-varies-every-time-even-with-a-low-temperature/921970/4 "2024-08-26T07:16:19Z")
I’m not sure but you could be right. ---
**Author:** ![takashi.asano](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/takashi.asano/32/146909_2.png) [@takashi.asano](https://community.openai.com/u/takashi.asano)\ **Post date:** [August 27, 2024, 4:32am UTC](https://community.openai.com/t/the-generated-code-varies-every-time-even-with-a-low-temperature/921970/5 "2024-08-27T04:32:12Z")
I found out this which may help to control the temp and top\_p at the same time for the code generation purpose: > [@Cheat Sheet: Mastering Temperature and Top\_p in ChatGPT API](https://community.openai.com/t/cheat-sheet-mastering-temperature-and-top-p-in-chatgpt-api/172683): > > Hello everyone! Ok, I admit had help from OpenAi with this. But what I “helped” put together I think can greatly improve the results and costs of using OpenAi within your apps and plugins, specially for those looking to guide internal prompts for plugins… @ruv I’d like to introduce you to two important parameters that you can use with OpenAI’s GPT API to help control text generation behavior: temperature and top\_p sampling. These parameters are especially useful when working with GPT for tas… ---
**Author:** ![MrFriday](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/mrfriday/32/350887_2.png) [@MrFriday](https://community.openai.com/u/MrFriday)\ **Post date:** [August 27, 2024, 5:35am UTC](https://community.openai.com/t/the-generated-code-varies-every-time-even-with-a-low-temperature/921970/6 "2024-08-27T05:35:12Z")
Correct. It’s only available for Chat Completion as chat completion as a standard don’t maintain previous conversation state.