# Gpt-3.5-turbo-1106 performance

**URL:** <https://community.openai.com/t/gpt-3-5-turbo-1106-performance/616666>\
**Category:** API\
**Tags:** embeddings, gpt-4, llm, rag, assistants-api\
**Created:** [February 6, 2024, 3:40pm UTC](https://community.openai.com/t/gpt-3-5-turbo-1106-performance/616666 "2024-02-06T15:40:49Z")\
**Posts on this page:** 1\
**Showing post:** 6

<div class="post-metadata">

**Author:** ![\_j](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/_j/32/766292_2.png) [@\_j](https://community.openai.com/u/_j)\
**Post date:** [February 7, 2024, 7:07am UTC](https://community.openai.com/t/gpt-3-5-turbo-1106-performance/616666/6 "2024-02-07T07:07:24Z")

</div>

> [@SomebodySysop](#):
>
> > [@sreekanth850](#):
> >
> > Did you checked gpt-3.5-turbo-0125
> 
> Isn’t the alias gpt-3.5-turbo?

The stable model is not switched yet. As I replied four days ago:

> [@What is the context window of the the new GPT 3.5 Turbo model (gpt-3.5-turbo-0125)?](https://community.openai.com/t/what-is-the-context-window-of-the-the-new-gpt-3-5-turbo-model-gpt-3-5-turbo-0125/609532/4):
>
> gpt-3.5-turbo as an alias has never left being directed to gpt-3.5-turbo-0613 as the stable model. The schedule for re-pointing to -0125 is “two weeks after release” according to the blog. The API return will tell you what model you are getting the response from. The error will tell you what input context length you exceeded. openai.BadRequestError: Error code: 400 - {‘error’: {‘message’: “This model’s maximum context length is 16385 tokens. However, your messages resulted in 18565 tokens …

* * *

call to `gpt-3.5-turbo` just now:

> {‘id’: ‘chatcmpl-xxx’, ‘choices’: [{‘finish\_reason’: ‘stop’, ‘index’: 0, ‘logprobs’: None, ‘message’: {‘content’: ‘Hello! How can I assist you today?’, ‘role’: ‘assistant’, ‘function\_call’: None, ‘tool\_calls’: None}}], ‘created’: 1707289999, ‘model’: **‘gpt-3.5-turbo-0613’** , ‘object’: ‘chat.completion’, ‘system\_fingerprint’: None, ‘usage’: {‘completion\_tokens’: 9, ‘prompt\_tokens’: 8, ‘total\_tokens’: 17}}

The reason why 3.5 is not as good as gpt-4, which costs 10x as much? I’m guessing that one could answer this on their own. You can significantly decrease the API temperature parameter for less common languages where the AI is less certain and test.

---

_[View the full topic](https://community.openai.com/t/gpt-3-5-turbo-1106-performance/616666)._