The model: `gpt-4` does not exist

[UpsetStarship]

I'm getting this error on Blender v3.4.1 with a paid account I just opened with 0 usage. (It's a "Plus" ChatGPT account with billing tied to the openAI organization as well).

GPT-4: Error: Python: Traceback (most recent call last): File "C:\Users\Brian\AppData\Roaming\Blender Foundation\Blender\3.4\scripts\addons\BlenderGPT-main__init__.py", line 174, in execute blender_code = generate_blender_code(context.scene.gpt4_chat_input, context.scene.gpt4_chat_history, context, system_prompt) File "C:\Users\Brian\AppData\Roaming\Blender Foundation\Blender\3.4\scripts\addons\BlenderGPT-main\utilities.py", line 51, in generate_blender_code response = openai.ChatCompletion.create( File "C:\Users\Brian\AppData\Roaming\Blender Foundation\Blender\3.4\scripts\addons\BlenderGPT-main\lib\openai\api_resources\chat_completion.py", line 25, in create return super().create(*args, **kwargs) File "C:\Users\Brian\AppData\Roaming\Blender Foundation\Blender\3.4\scripts\addons\BlenderGPT-main\lib\openai\api_resources\abstract\engine_apiresource.py", line 153, in create response, , api_key = requestor.request( File "C:\Users\Brian\AppData\Roaming\Blender Foundation\Blender\3.4\scripts\addons\BlenderGPT-main\lib\openai\api_requestor.py", line 226, in request resp, got_stream = self._interpret_response(result, stream) File "C:\Users\Brian\AppData\Roaming\Blender Foundation\Blender\3.4\scripts\addons\BlenderGPT-main\lib\openai\api_requestor.py", line 619, in _interpret_response self._interpret_response_line( File "C:\Users\Brian\AppData\Roaming\Blender Foundation\Blender\3.4\scripts\addons\BlenderGPT-main\lib\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

GPT-3.5: Error: Python: Traceback (most recent call last): File "C:\Users\Brian\AppData\Roaming\Blender Foundation\Blender\3.4\scripts\addons\BlenderGPT-main__init__.py", line 174, in execute blender_code = generate_blender_code(context.scene.gpt4_chat_input, context.scene.gpt4_chat_history, context, system_prompt) File "C:\Users\Brian\AppData\Roaming\Blender Foundation\Blender\3.4\scripts\addons\BlenderGPT-main\utilities.py", line 51, in generate_blender_code response = openai.ChatCompletion.create( File "C:\Users\Brian\AppData\Roaming\Blender Foundation\Blender\3.4\scripts\addons\BlenderGPT-main\lib\openai\api_resources\chat_completion.py", line 25, in create return super().create(*args, **kwargs) File "C:\Users\Brian\AppData\Roaming\Blender Foundation\Blender\3.4\scripts\addons\BlenderGPT-main\lib\openai\api_resources\abstract\engine_apiresource.py", line 153, in create response, , api_key = requestor.request( File "C:\Users\Brian\AppData\Roaming\Blender Foundation\Blender\3.4\scripts\addons\BlenderGPT-main\lib\openai\api_requestor.py", line 226, in request resp, got_stream = self._interpret_response(result, stream) File "C:\Users\Brian\AppData\Roaming\Blender Foundation\Blender\3.4\scripts\addons\BlenderGPT-main\lib\openai\api_requestor.py", line 619, in _interpret_response self._interpret_response_line( File "C:\Users\Brian\AppData\Roaming\Blender Foundation\Blender\3.4\scripts\addons\BlenderGPT-main\lib\openai\api_requestor.py", line 682, in _interpret_response_line raise self.handle_error_response( openai.error.RateLimitError: You exceeded your current quota, please check your plan and billing details.

[hunandy14]

I have also encountered the same problem. If you manage to solve it, I hope you can update with the follow-up.

[gd3kr]

Okay so I think there might be a misunderstanding here. You need to upgrade your account to the paid version from https://platform.openai.com/account/billing/overview for GPT-3.5 (GPT-4 is only available via the GPT-4 API Waitlist). ChatGPT plus accounts are not the same and having a ChatGPT Plus account with access to GPT-4 via the web UI will still not give you access to GPT-4 via the API. openai.error.RateLimitError will not trigger unless there is something wrong with payments on your OpenAI account.

[Taljansen]

so it means people who have subscription and use the plus model still cannot use this addon right now (without changing the original code) and have to wait until full access to model 4 is granted?

[robeyl]

so it means people who have subscription and use the plus model still cannot use this addon right now (without changing the original code) and have to wait until full access to model 4 is granted?

You can drop back the GPT model used by this addon to 3.5.

You will just need to add a payment method in https://platform.openai.com/account/billing/payment-methods to get it to work, as GPT API and ChatGPT are currently considered separate products by OpenAI. It's quite cheap though, I've been using it for various projects over the last few days and I'm still under 50c usage.