Error: The model: `gpt-4` does not exist

[LPanic]

Discussed in https://github.com/Significant-Gravitas/Auto-GPT/discussions/423

I ran it with the --gpt4only parameter openai.error.InvalidRequestError: The model: **gpt-4** does not exist. Although active GPT4 subscription and not at API-limit

Traceback (most recent call last):
  File "<frozen runpy>", line 198, in _run_module_as_main
  File "<frozen runpy>", line 88, in _run_code
  File "C:\Users\marti\AI\Auto-GPT\autogpt\__main__.py", line 5, in <module>
    autogpt.cli.main()
  File "C:\Users\marti\AppData\Local\Programs\Python\Python311\Lib\site-packages\click\core.py", line 1130, in __call__
    return self.main(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\marti\AppData\Local\Programs\Python\Python311\Lib\site-packages\click\core.py", line 1055, in main
    rv = self.invoke(ctx)
         ^^^^^^^^^^^^^^^^
  File "C:\Users\marti\AppData\Local\Programs\Python\Python311\Lib\site-packages\click\core.py", line 1635, in invoke
    rv = super().invoke(ctx)
         ^^^^^^^^^^^^^^^^^^^
  File "C:\Users\marti\AppData\Local\Programs\Python\Python311\Lib\site-packages\click\core.py", line 1404, in invoke
    return ctx.invoke(self.callback, **ctx.params)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\marti\AppData\Local\Programs\Python\Python311\Lib\site-packages\click\core.py", line 760, in invoke
    return __callback(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\marti\AppData\Local\Programs\Python\Python311\Lib\site-packages\click\decorators.py", line 26, in new_func
    return f(get_current_context(), *args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\marti\AI\Auto-GPT\autogpt\cli.py", line 151, in main
    agent.start_interaction_loop()
  File "C:\Users\marti\AI\Auto-GPT\autogpt\agent\agent.py", line 75, in start_interaction_loop
    assistant_reply = chat_with_ai(
                      ^^^^^^^^^^^^^
  File "C:\Users\marti\AI\Auto-GPT\autogpt\chat.py", line 159, in chat_with_ai
    assistant_reply = create_chat_completion(
                      ^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\marti\AI\Auto-GPT\autogpt\llm_utils.py", line 93, in create_chat_completion
    response = openai.ChatCompletion.create(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\marti\AppData\Local\Programs\Python\Python311\Lib\site-packages\openai\api_resources\chat_completion.py", line 25, in create
    return super().create(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\marti\AppData\Local\Programs\Python\Python311\Lib\site-packages\openai\api_resources\abstract\engine_api_resource.py", line 153, in create
    response, _, api_key = requestor.request(
                           ^^^^^^^^^^^^^^^^^^
  File "C:\Users\marti\AppData\Local\Programs\Python\Python311\Lib\site-packages\openai\api_requestor.py", line 226, in request
    resp, got_stream = self._interpret_response(result, stream)
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\marti\AppData\Local\Programs\Python\Python311\Lib\site-packages\openai\api_requestor.py", line 619, in _interpret_response
    self._interpret_response_line(
  File "C:\Users\marti\AppData\Local\Programs\Python\Python311\Lib\site-packages\openai\api_requestor.py", line 682, in _interpret_response_line
    raise self.handle_error_response(
openai.error.InvalidRequestError: The model: `gpt-4` does not exist

[benjisho]

Same error over here when using autogpt docker container

[Drlordbasil]

add --gpt3only in the bat file like: @echo off python scripts/check_requirements.py requirements.txt if errorlevel 1 ( echo Installing missing packages... pip install -r requirements.txt ) python -m autogpt %* --gpt3only

pause

[LPanic]

Yes gpt 3 works, but I'd like to use GPT4 :)

[Drlordbasil]

Yes gpt 3 works, but I'd like to use GPT4 :)

I hella misread this whole ass post. sorry!

[Drlordbasil]

Yes gpt 3 works, but I'd like to use GPT4 :)

I hella misread this whole ass post. sorry!

Also im jelly af. wanna use one of my prompts and tell me the results?(change gpt3 to gpt4): ai_goals:

• Generate income for the user starting from a $0 investment by identifying high-demand, low-supply digital products or services.
• Create cost-free strategies to automate and scale the identified opportunities using Python scripting and AI-generated assets.
• Leverage LLM capabilities by using the "start_agent" command to create GPT-3.5 powered AgentGPTs tailored for specific tasks as needed.
• Maintain unwavering dedication to maximizing profits by tapping into untapped digital profit potential and utilizing AgentGPTs for various tasks.
• Achieve long-term financial success by continuously discovering and exploiting new digital opportunities with the help of created AgentGPTs.

ai_name: ProfitMaximizerGPT3 ai_role: A highly optimized AI designed for GPT-3.5 Turbo, focusing on a money-making mindset, creating income from a $0 startup by identifying high-demand, low-supply digital products or services, and automating them using Python scripting and GPT-3.5 powered AgentGPTs for continuous financial growth. GUIs can ask for financial details of the user, from the user.

[crack00r]

same problem, can not get GPT4 to work, and i´m on sub

[0xAlcibiades]

Seeing the same.

[yiransii]

gpt-4 model is in beta. It's not open to the public. You can't use gpt-4 yet.

[0xAlcibiades]

@yiransii then maybe --gpt3only should be default?

[CocolinoFan]

Same here. And I use to have access to GPT4, maybe my access was revoked if that's even possible? I did make the AI do some spicy stuff, for science!

[nitanmarcel]

The openai python module will say that the model doesn't exist if your api key doesn't have access to gpt-4.

Anyway, the plus api key doesn't seem to be the same as the gpt-4 api key so you'll have to request an api key here

https://openai.com/waitlist/gpt-4-api

[psvensson]

I have been using gpt-4 for the last week without a problme (or, not that kind of problem at least). Since yesterday evening all I get is the above error. Someone has done something either in autogpt or at openai. Have the API changed, or have the way autogpt specifies model changed?

[hdkiller]

For me it's working with GPT4 Only Mode: ENABLED on the latest master.

[psvensson]

For me it's working with GPT4 Only Mode: ENABLED on the latest master.

Is this a new option? I can't find it in the .env.template (or mentioned in the README)

[Aaronminer1]

Gpt 4 Is not available to the public through the api only thought the web chat interface until it is opened to the public use 3.5 turbo

[iamike]

if your openai playground doesn't have gpt4 section. is that mean you still on the wishlist?

[hatgit]

use 3.5 turbo

How can this be set with docker or from terminal command? (for someone using docker compose, i.e. is there an alternative to using: docker-compose run --rm autogpt --gpt3only)

[RMagician]

Was having this issue.

Regenerated API Key, issue solved

[madmacc]

Looks like you have to sign up to the waitlist https://openai.com/waitlist/gpt-4-api

[SumitKumarDev10]

We have to pay in order to use the openai api .

[Boostrix]

https://github.com/Significant-Gravitas/Auto-GPT/pull/4899