OpenAI API: Why can't I access GPT-4 models via API, although GPT-3.5 models work?

I'm able to use the gpt-3.5-turbo-0301 model to access the ChatGPT API, but not any of the gpt-4 models. Here is the code I am using to test this (it excludes my openai API key). The code runs as written, but when I replace "gpt-3.5-turbo-0301" with "gpt-4", "gpt-4-0314", or "gpt-4-32k-0314", it gives me an error "openai.error.InvalidRequestError: The model: gpt-4 does not exist". I have a ChatGPT+ subscription, am using my own API key, and can use gpt-4 successfully via OpenAI's own interface.

It's the same error if I use gpt-4-0314 or gpt-4-32k-0314. I've seen a couple articles claiming this or similar code works using 'gpt-4' works as the model specification, and the code I pasted below is from one of them. Does anybody know if it's possible to access the gpt-4 model via Python + API, and if so, how do you do it?

openai_key = "sk..."
openai.api_key = openai_key
system_intel = "You are GPT-4, answer my questions as if you were an expert in the field."
prompt = "Write a blog on how to use GPT-4 with python in a jupyter notebook"
# Function that calls the GPT-4 API

def ask_GPT4(system_intel, prompt): 
    result = openai.ChatCompletion.create(model="gpt-3.5-turbo-0301",
                                 messages=[{"role": "system", "content": system_intel},
                                           {"role": "user", "content": prompt}])

# Call the function above
ask_GPT4(system_intel, prompt)


  • Currently the GPT 4 API is restricted, Even to users with a Chat GPT + subscription.

    You may need to join the Waitlist for the API.