ChatGPT API stopped working with error message "That model does not exist"

[SimonBaars]

Verify latest release

• [X] I verified that the issue exists in the latest chatgpt release (confirmed on 4.1.3)

Verify webapp is working

• [X] I verify that the ChatGPT webapp is working properly for this account.

Environment details

[simon@simon ~]$ node --version 
v19.6.0
[simon@simon Music]$ hostnamectl
 Static hostname: simon
       Icon name: computer-laptop
         Chassis: laptop 💻
         Kernel: Linux 5.15.91-4-lts
    Architecture: x86-64
 Hardware Vendor: Dell Inc.
  Hardware Model: XPS 15 7590
Firmware Version: 1.7.0

Describe the Bug

Earlier today, this library still worked, now even the basic example gives the following error:

/usr/bin/node ./src/test-api.js
Uncaught ChatGPTError Error: ChatGPT error 404: {
    "error": {
        "message": "That model does not exist",
        "type": "invalid_request_error",
        "param": null,
        "code": null
    }
}
    at <anonymous> (/home/simon/git/Misc-Projects/consequences.app/node_modules/chatgpt/build/index.js:202:29)
    at processTicksAndRejections (internal/process/task_queues:95:5)
    --- await ---
    at processTicksAndRejections (internal/process/task_queues:95:5)
    --- await ---
    at runMainESM (internal/modules/run_main:53:21)
    at executeUserEntryPoint (internal/modules/run_main:79:5)
    at <anonymous> (internal/main/run_main_module:23:47)
Process exited with code 1

This runs the following code:

import { ChatGPTAPI } from 'chatgpt'

const api = new ChatGPTAPI({
  apiKey: process.env.OPENAI
})

const res = await api.sendMessage('Hello World!')
console.log(res.text)

It worked earlier today. Might something have changed with the API?

[iota-unum]

yes, sadly openai shut down the model

[christophebe]

yes, this is the same issue as https://github.com/transitive-bullshit/chatgpt-api/issues/292

Is it possible to find the new model name somewhere ?

[transitive-bullshit]

We're working on a workaround.

In the meantime, you can switch back to using text-davinci-003 via https://github.com/transitive-bullshit/chatgpt-api/releases/tag/v4.2.0

[gigantino]

We're working on a workaround.

In the meantime, you can switch back to using text-davinci-003 via https://github.com/transitive-bullshit/chatgpt-api/releases/tag/v4.2.0

Thank you for the blazingly fast response :)

[transitive-bullshit]

We're working on a workaround. In the meantime, you can switch back to using text-davinci-003 via v4.2.0 (release)

Thank you for the blazingly fast response :)

I promise I'm not a bot 😂 hahahha

[gigantino]

I promise I'm not a bot joy hahahha

Well that's what a bot would say...! On a side note, thank you so much for the work you guys are putting into this.

[SimonBaars]

I'm just catching up on the linked thread https://github.com/transitive-bullshit/chatgpt-api/issues/292. Some takeaways for newcomers like me:

• text-davinci-003 is slightly less optimized for the ChatGPT usecase
• The text-davinci-003 model does incur API costs (!)

[qwertyuu]

I saw text-davinci-002-render in the API calls of chat.openai.com

[transitive-bullshit]

@qwertyuu the text-davinci-002-render model is unfortunately not available to use from OpenAI's API. We were using a previously leaked model that's fine-tuned for chat and was free, but OpenAI just disabled it.

@SimonBaars 100% agreed with your takeaways. Thanks 🙏

[dvargas135]

@qwertyuu the text-davinci-002-render model is unfortunately not available to use from OpenAI's API. We were using a previously leaked model that's fine-tuned for chat and was free, but OpenAI just disabled it.

@SimonBaars 100% agreed with your takeaways. Thanks 🙏

How do you use that model? Do we need to set up another key? I couldn't find how in the docs...

[nicksav]

just exactly when I wanted to use it - its down:) what a luck

[ikechan8370]

If we finally couldn't find an available and free chat model, can we turn back to the browser based solution?

[graid2030]

I agree. It looks like it would be better to continue the work based on 3.5.2

[BillGPT]

If we finally couldn't find an available and free chat model, can we turn back to the browser based solution?

Agree. ChatGPT Plus is also free and faster, perhaps even faster than api, may be there is a solution? I can't wait for the official ChatGPT API

[graid2030]

OpenAI seems to be trolling us. text-chat-davinci-002-20221122 works again

[cvpv]

OpenAI seems to be trolling us. text-chat-davinci-002-20221122 works again

I just used it. It is still not as good as before

[basetrade]

OpenAI seems to be trolling us. text-chat-davinci-002-20221122 works again

really? Will it have something to do with Microsoft opening up many public chatgpt applications

[ikechan8370]

When using text-chat-davinci-002-20221122, it always returned 503 error: That model is currently overloaded with other requests. I remember that the response of this model was relatively fast before. Did OpenAI reduce the computing resources that this model can call?

[tyanbiao]

When using text-chat-davinci-002-20221122, it always returned 503 error: That model is currently overloaded with other requests. I remember that the response of this model was relatively fast before. Did OpenAI reduce the computing resources that this model can call?

same issue

[xieccc]

Currently the more stable is the text-davinci-003 model used in version 4.2.0

[graid2030]

Currently the more stable is the text-davinci-003 model used in version 4.2.0

Yes, but the tiny detail is that it is a paid model.

[nevo-david]

Is text-davinci-003 the chatgpt model (gpt3)? or is the chatgpt(gpt3.5 instruct)?

[xieccc]

Is text-davinci-003 the chatgpt model (gpt3)? or is the chatgpt(gpt3.5 instruct)?

GPT-3 model. link

[nevo-david]

So it's not a solution 😛 it's just the old crappy model 🙈

[nevo-david]

I am expecting that it's not working when there is high usage on the ChatGPT website. I was able to generate some a few hours ago.

[tluyben]

We're working on a workaround.

In the meantime, you can switch back to using text-davinci-003 via https://github.com/transitive-bullshit/chatgpt-api/releases/tag/v4.2.0

Are you for hire :) You seem to be an absolute top talent at whack-a-mole. Which is something every software engineer needs to be but hardly ever is skilled at.

But yes, same issue. They are also whacking moles on their side. Hope they release the API really soon; I don't mind paying, but davinci-003 is really not as good for what I use it for. And that's putting it mildly.

[transitive-bullshit]

We're working on a workaround. In the meantime, you can switch back to using text-davinci-003 via v4.2.0 (release)

Are you for hire :) You seem to be an absolute top talent at whack-a-mole. Which is something every software engineer needs to be but hardly ever is skilled at.

But yes, same issue. They are also whacking moles on their side. Hope they release the API really soon; I don't mind paying, but davinci-003 is really not as good for what I use it for. And that's putting it mildly.

You can follow & DM me on my twitter w/ a proposal. It has to be organized and very well paid for me to consider it.

[tluyben]

I am expecting that it's not working when there is high usage on the ChatGPT website. I was able to generate some a few hours ago.

It seems to be much worse than it was; as someone else said, it's probably MS opening up the floodgates. It's not easy straightforward to scale yet as your bog standard web app.

[transitive-bullshit]

I am expecting that it's not working when there is high usage on the ChatGPT website. I was able to generate some a few hours ago.

It seems to be much worse than it was; as someone else said, it's probably MS opening up the floodgates. It's not easy straightforward to scale yet as your bog standard web app.

My best guess is that they've added ACLs on their end to restrict access to certain models.

[transitive-bullshit]

Feel free to join our ChatGPT Hackers Discord if you're currently experiencing issues. https://discord.gg/v9gERj825w

Lots of other hackers in there working on this problem as well.