Why am I getting invalid model error with "gpt-35-turbo-16k" model in Azure Open AI but not with "gpt-35-turbo"?

Question

I have built a very simple application using Azure Open AI, Langchain and Streamlit. Following is my code:

from dotenv import load_dotenv,find_dotenv
load_dotenv(find_dotenv())

import streamlit as st
from langchain.llms import AzureOpenAI

from langchain.prompts import PromptTemplate


LLM = AzureOpenAI(max_tokens=1500, deployment_name="gpt-35-turbo-16k", model="gpt-35-turbo-16k")


prompt_template = """
If you don't know the answer, just say that you don't know, don't try to make up an answer.

Question: {question}
"""
PROMPT = PromptTemplate(template=prompt_template, input_variables=["question"])
st.title('Experiment AzureOpenAI :)')
user_question = st.text_input('Your query here please')

if user_question:
    prompt = prompt_template.format(question = user_question)
    response = LLM(prompt)
    st.write(response)
    st.write('done')

When I run the above code, I am getting the following error back:

InvalidRequestError: The completion operation does not work with the specified model, gpt-35-turbo-16k. Please choose different model and try again. You can learn more about which models can be used with each operation here: https://go.microsoft.com/fwlink/?linkid=2197993.

However my code runs perfectly fine if I change the model from gpt-35-turbo-16k to gpt-35-turbo. So the following code works:

LLM = AzureOpenAI(max_tokens=1500, deployment_name="gpt-35-turbo", model="gpt-35-turbo")

I am wondering why is this error occurring?

From this link, only difference I could see is that gpt-35-turbo-16k supports up to 16k input tokens whereas gpt-35-turbo supports up to 4k input tokens.

Answer 1

Based on documentation, the plausible reason is: the version (0613) only supports the Chat Completions API.

https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#gpt-35-models

GPT-3.5 Turbo is used with the Chat Completion API. GPT-3.5 Turbo (0301) can also be used with the Completions API. GPT3.5 Turbo (0613) only supports the Chat Completions API.