当前位置:   article > 正文

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

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

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?

  1. openai_key = "sk..."
  2. openai.api_key = openai_key
  3. system_intel = "You are GPT-4, answer my questions as if you were an expert in the field."
  4. prompt = "Write a blog on how to use GPT-4 with python in a jupyter notebook"
  5. # Function that calls the GPT-4 API
  6. def ask_GPT4(system_intel, prompt):
  7. result = openai.ChatCompletion.create(model="gpt-3.5-turbo-0301",
  8. messages=[{"role": "system", "content": system_intel},
  9. {"role": "user", "content": prompt}])
  10. print(result['choices'][0]['message']['content'])
  11. # Call the function above
  12. ask_GPT4(system_intel, prompt)

问题解决:

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.

声明:本文内容由网友自发贡献,不代表【wpsshop博客】立场,版权归原作者所有,本站不承担相应法律责任。如您发现有侵权的内容,请联系我们。转载请注明出处:https://www.wpsshop.cn/w/Li_阴宅/article/detail/843342?site
推荐阅读
相关标签
  

闽ICP备14008679号