[BUG] That model does not exit

[Leewaldoe]

Description I'm experiencing a strange error. The response message is simply "That model does not exit".

Output

Spawning browser...
Browser spawned.
Found Cloudflare Cookie!
<tk_button_send>click event <ButtonPress event state=Mod2 num=1 x=30 y=23>
{"detail":{"message":"That model does not exist","type":"invalid_request_error","param":null,"code":null}}
Exception in Tkinter callback
Traceback (most recent call last):
  File "/usr/lib/python3.10/tkinter/__init__.py", line 1924, in __call__
    return self.func(*args)
  File "/home/user/programming/gpt/api-connector/tkinter-gpt/app/main.py", line 90, in bot_ask
    asyncio.run(self.wait_for_response(inputs_question))
  File "/usr/lib/python3.10/asyncio/runners.py", line 44, in run
    return loop.run_until_complete(main)
  File "/usr/lib/python3.10/asyncio/base_events.py", line 649, in run_until_complete
    return future.result()
  File "/home/user/programming/gpt/api-connector/tkinter-gpt/app/main.py", line 77, in wait_for_response
    async for i in await self.chatbot.ask(inputs):
  File "/home/user/programming/gpt/api-connector/tkinter-gpt/venv/lib/python3.10/site-packages/revChatGPT/ChatGPT.py", line 159, in ask
    raise HTTPError(
requests.exceptions.HTTPError: Wrong response code: 404! Refreshing session...

Environment

• OS: Windows (WSL2)
• Python version: python 3.10
• ChatGPT Version: revChatGPT 1.0.11

[qcwthu]

I have the same problem. Does anyone know how to solve it?

[BNDSllx]

same problem

[acheong08]

Could be expired session tokens

[acheong08]

Maybe try using official API (no expiry)

[acheong08]

Yeah use official API. The unofficial one is a bit unstable

[qcwthu]

How to use the official API?

[acheong08]

Check Readme. It has been updated.https://github.com/acheong08/ChatGPT#official-api-browserless

[Leewaldoe]

Regarding the official API. How long do you think before someone decides to shut it down @acheong08?

[acheong08]

How long do you think before someone decides to shut it down

According to some connections of @transitive-bullshit, this won't be taken down as it's in use by YC/VC partners of OpenAI

[transitive-bullshit]

You will get this problem if you're using the old browser-based approach and it's still using text-davinci-002-render, which seems to no longer be valid.

From my testing, the browser-based version updated to use text-davinci-002-render-next and text-davinci-002-render-paid if you're on a pro chatgpt plan.

@acheong08 I think you just need to update these in the old version. I agree that you shouldn't encounter this issue using the new model fine-tuned for chat.

[acheong08]

@transitive-bullshit Thanks. Will fix

[acheong08]

Fixed

[acheong08]

text-davinci-002-render-paid if you're on a pro chatgpt plan.

I won't be supporting paid tier

[F33RNI]

Same text-davinci-002-render-next also not working =(

[0xdevalias]

See Also:

• https://github.com/acheong08/ChatGPT/issues/504
• https://github.com/acheong08/ChatGPT/issues/517
• https://github.com/acheong08/ChatGPT/issues/523
• https://github.com/acheong08/ChatGPT/issues/530

[hunkim]

Hmm. Both do not work for me.

GPT3 Error: That model does not exist

[0xdevalias]

From my testing, the browser-based version updated to use text-davinci-002-render-next and text-davinci-002-render-paid if you're on a pro chatgpt plan.

Looking at the requests made from the browser version just now (non-paid), it seems to be using text-davinci-002-render (unsure what model the paid version would be using)

[acheong08]

These are just aliases for the model on the back end. The real name is not revealed