API error: "'The model:' gpt-4-32k 'does not exist."

[ashen saffron]

Does anyone know why I keep getting this error when I call the API?
Thank You.

[rigid tangle]

You can only use the 8k model for now. And to call it:
model: "gpt-4"

[ashen saffron]

Ok. Yes, "gpt-4" works. I was using the Go library suggested in the OpenAI documentation, and the 32k model was one of the config options. So, I erroneously assumed it was live. Thanks.

[frozen mirage]

@ashen saffron does it still work for you? I'm getting an error that says "gpt-4 does not exist" now.

[rigid tangle]

Did you get access to it?

[frozen mirage]

Yes. I was using it last month, and now when I try to test it again, it's not working. I can use it on the playground, though. Did OpenAI change its endpoint or something?

[rigid tangle]

That's odd. It seems to be working for me. Maybe submit a bug report or contact support?

[frozen mirage]

Could you share with me a snippet of your code with the endpoint? Probably, I'm missing something here.

Will try to contact support as well

[rigid tangle]

I'm not using an endpoint just plain old openai's npm package for nodejs. Here' my backend:

var prompt = req.body.writing;
var result = [];
var resultLength = [];

var gptResponse = await openai.createChatCompletion({
    model: "gpt-4",
    messages: [{
        role: "user",
        content: prompt
    }],
    max_tokens: 100,
    
  }); 

console.log(gptResponse.data.choices[0].message);

[frozen mirage]

Thanks. Let me try this

Still not working. I guess I'll just use gpt4 on playground for now