InvalidRequestError: gpt-4-1106-preview

API
1

I started to receive “InvalidRequestError:You requested a model that is not compatible with this engine. Please contact us through our help center at help.openai.com for further questions.” when I use gpt-4-1106-preview from yesterday. I have checked the documentation and it seems that gpt-4-1106-preview is still available. Does anyone run into the same problem?

2 Likes
2

Yes, it’s ongoing across all gpt-4 models.

You’ll have to update code and add a retry method if you get this error and error message.

2 Likes
3

Thank you so much! Definitely will try.

1 Like
4

Set the model to “gpt-4-turbo-preview”

5

Actually the performance is worse for turbo-preview in my case. But thanks for the suggestion.

6

Yep, but at least it does not throw the error :slight_smile:

7

well whats going on? doesn openai know? more info?
whats the reason for this?
I have the same exact issue.

8

probably just some misconfiguration. will probably resolve in a day or two. or not.

just catch this particular error and retry.

Here’s an example how you could do this

import requests
import json
import os

# Ensure you have your OpenAI API key set in the environment variables
openai_api_key = os.getenv("OPENAI_API_KEY")
if openai_api_key is None:
    raise ValueError("OpenAI API key is not set in environment variables.")

url = "https://api.openai.com/v1/chat/completions"

headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {openai_api_key}"
}

data = {
    "model": "gpt-4-1106-preview",  # Keep only this model
    "temperature": 1, 
    "max_tokens": 10,
    "logit_bias": {1734:-100},
    "messages": [
        {
            "role": "system", 
            "content": "You are the new bosmang of Tycho Station, a tru born and bred belta. You talk like a belta, you act like a belta. The user is a tumang."
        },
        {
            "role": "user",
            "content": "how do I become a beltalowda like you?"
        }
    ],
    "stream": True,  # Changed to True to enable streaming
}

for tries in range(10):
    response = requests.post(url, headers=headers, json=data, stream=True)
    
    if response.status_code == 400:
        print("attempt", tries, "retrying...")
        continue

    if response.status_code == 200:
        for line in response.iter_lines():
            if line:
                decoded_line = line.decode('utf-8')
                # Check if the stream is done
                if '[DONE]' in decoded_line:
                    # print("\nStream ended by the server.")
                    break
                json_str = decoded_line[len('data: '):]
                try:
                    json_response = json.loads(json_str)
                    delta = json_response['choices'][0]['delta']
                    if 'content' in delta and delta['content']:
                        print(delta['content'], end='', flush=True) 
                except json.JSONDecodeError as e:
                    raise Exception(f"Non-JSON content received: {decoded_line}")
    else:
        print("Error:", response.status_code, response.text)
    break #!important!
2 Likes
9

any updates? about this? are you still experiencing this issue?

10

Still same. I think it takes some time to fix the issue…
I wish it will be short.