When I try the "gpt-4" model chat completion in API request, I get an error: That model does not exist

API
7

Same here, API granted access, but not working (404)

4 Likes
8

Same here, I can use GTP4 as a prompt but not via the API.
Is there anything to do except waiting?
Thanks a lot for your help

3 Likes
9

Working now as of this morning. I also redid the API integration, so might have been an issue with my code

1 Like
10

I just got access and I don’t see the model in the ‘completions’ in the playground.

2 Likes
11

Is GPT-4 supposed to be visible in the playground if you have been approved? I thought it was the api only.

1 Like
12

I received the email this morning and am getting the 404 error. Which API library are you using? I’m getting the error with the NodeJS api.

13

Check “chat” mode not “completion” mode, https://i.imgur.com/csiX3l8.png

1 Like
14

Quick update, after running npm install openai --save again, the GPT-4 model seems to be working

15

Yup I see it, I had to call the chatCompletions in the code as well. Thanks!

1 Like
16

I have it in playground and also API

17

I got an invite but was getting the above error. It then worked after I generated a new API key.

18

@benlamm I had the same issue. You must update your version of the openai library. Run pip install openai and try it again, it worked for me.

19

Related to this, I would suggest a more descriptive error message, since it’s public info that the model exists. I think a better error message would reduce the confusion.

20

For me, the problem was that I didn’t set the default organization in this page OpenAI API

Once I set the organization to be the organization that got access to GPT4, I can call GPT-4 sucessfully

1 Like
21

I got the same error after I got an invitation.

In my case, it worked right after I tried GPT4 once on the OpenAI Playground. I’m not 100% sure if it was the actual trigger, though.

22

After getting notified of limited beta access, swapped GPT-3 “text-davinci-003” with “gpt-4”. Gives 404 error. Not sure what else needs to be done. Maybe not turned on for account yet? Need a new token maybe?

		CompletionRequest request = CompletionRequest.builder()
				.model(full_engine)
				.prompt(mood.get(feeling) + prompt)
				.maxTokens(248)
				.temperature(0.8)
				.topP(1.0)
				.frequencyPenalty(0.55)
				.presencePenalty(0.19)
				.user(sndr)
				.echo(false)
				.build();
		List<String> responses = new ArrayList<String>();
23

Flagged to the team, in general, if you want to try GPT-4 in the playground and you have access, you need to use the Chat setup: OpenAI API, same with the API: OpenAI API.

Will talk to the team and see if we can look into this more.

1 Like
24

I had to create a new api key after gaining access to gpt-4 to be able to use it. works now.

25

I’d try the code below which worked for me (JavaScript):

const { Configuration, OpenAIApi } = require("openai");


  const configuration = new Configuration({
    apiKey: "<INSERT-API-KEY-HERE>",
  });

  const openai = new OpenAIApi(configuration);

  const response = await openai.createChatCompletion({
    model: "gpt-4",
    messages: [
      { role: "system", content: "You are a helpful assistant." },
      { role: "user", content: "Who won the world series in 2020?" },
      { role: "assistant", content: "The Los Angeles Dodgers." },
      { role: "user", content: "Where was it played?" },
    ],
    max_tokens: 50,
    n: 1,
    stop: null,
    temperature: 1,
  });

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

Also wrote a quick guide here with some Do’s & Don’ts to get it working - might be of use :+1:

26

For anyone still having issues… I think the invite came out in sets, some did not get the 32k model. Even if you have the invite, but did got the 32k model access, you will get a 404 in node.