1

Currently working on a project with GPT completions and it worked perfectly fine with the model set as “text-davinci-003” but when I changed it to “gpt-4” it stopped working and I’m getting the error I set in my code. BTW I have the beta invite to gpt 4 api.
Here’s a snippet from my code:

response = requests.post("https://api.openai.com/v1/completions", json={
        "model": "gpt-4",
        "prompt": prompt,
        "max_tokens": 8000,
        "n": 1,
        "stop": None,
        "temperature": 0.3,
    }, headers={
        "Content-Type": "application/json",
        "Authorization": f"Bearer {API_KEY}"
    })

    response_data = response.json()

    if 'choices' in response_data:
        definition = response_data['choices'][0]['text'].strip()
    else:
        definition = "Error: Could not get a translation."
2

I believe GPT 4 isn’t available yet for regular completions, only chat completions.
If you reformat your request to have the format of the Chat endpoint, then it should work!
There are a few notes in the documentation about this.

Hope that helps!

1 Like
3

I followed ur advice and im still getting the same error.

response = requests.post("https://api.openai.com/v1/chat/completions", json={
        "model": "gpt-4",
        "prompt": prompt,

Is there anything else I’m doing wrong? I’ve been looking through documentation and I’m pretty sure I’m doing everything right.

4

Welcome to the community @anmar

GPT-4 works with the ChatCompletions endpoint instead of the completions endpoint.

These docs on chat completions will be helpful in migrating to the GPT-4 model.

2 Likes
5

Hi
If you are getting the same error you may not have access to gpt-4. I don’t have access and I get that error too via the same chat/completions end point.

The model: gpt-4 does not exist

6

thank you this fixed my problem! keep a lookout for a post in the next few days of my project!

1 Like
7

I am getting same error , I have chatgpt plus too, still this api is not working

getting error in translating text