[phil42]

But I need an GPT-4 api key for that, right? The normal API keys don't work?

[capableweb]

The keys for GPT3 (`GPT-3.5-turbo` is the actual model ID) is the same as for GPT-4. You define the model when you make the request to the API.

[layer8]

Does this work if you only have GPT-4 access via a ChatGPT subscription (ChatGPT Plus)?

[fredliu]

It doesn't. Even if you have ChatGPT Plus, the key you have only supports 3.5 unless you are explicitly given the gpt-4 key.

[capableweb]

It's true that you need explicit access to the GPT-4 to use the API, but again, it's not a different key. I'm using the same API key for accessing `gpt-3.5-turbo` as I use for `gpt-4`.

[fredliu]

There seems to be already a PR for adding 3.5 support. The community and speed of change in this field is mind blowing!

[capableweb]

Oh yeah, changing 33 lines is truly revolutionary!

[enricoros]

OP: I went to sleep with this as my 1st post and 1 star, and woke up with a PR for 3.5-Turbo pending. Community for the win!

[tonyoconnell]

Seems to fall back to GPT 3 if you haven't got access to GPT 4 API yet

[fredliu]

hmm... doesn't seem to be the case, when I provided my gpt-3 turbo key the error message indicates the gpt-4 model doesn't exist.

[capableweb]

Change this https://github.com/enricoros/nextjs-chatgpt-app/blob/466a366... to say "gpt-3.5-tubo" and it should work for you

[trendoid]

I updated the model in that file, deployed again using Vercel but still same error.

[capableweb]

It seems like it's setting gpt-4 here as well: https://github.com/enricoros/nextjs-chatgpt-app/blob/466a366...

But come on, read through the source, look for the issue, I'm sure you can track down at least something :)

[trendoid]

Sorry, as soon as posted my comment, I looked again and found the other occurrence. It's quite late here and I just followed your advice blindly :)

Works now.