Why can‘t I access GPT-4 models via API, although GPT-3.5 models work?

news2024/11/25 6:55:02

题意：为什么我无法通过API访问GPT-4模型，尽管GPT-3.5模型可以工作？

问题背景：

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.

Is it possible to access the gpt-4 model via Python + API, and if so, how?

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}])
    print(result['choices'][0]['message']['content'])

# Call the function above
ask_GPT4(system_intel, prompt)