What is the name of the model that uses "GPT-4o mini"?

[r2nochi]

Hi, your project is very good. I need your help in what is the name of the model in your package that uses the "GPT-4o mini" model, since that model is cheaper than "GPT-3.5 Turbo".
It would be great if you could make a list of available models of the package and which one of the open ai models it matches.

model: Gpt4ChatModel()
model: Gpt41106PreviewChatModel()

[rocboronat]

I'm exactly looking for that.

In constants.dart there's this list, but no model seems like GPT-4o mini.

const kChatGptTurboModel = 'gpt-3.5-turbo'; // gpt 3.5
const kChatGptTurbo0301Model = 'gpt-3.5-turbo-0301';
const kChatGpt4 = 'gpt-4';
const kChatGpt40314 = 'gpt-4-0314';
const kChatGpt432k = 'gpt-4-32k';
const kChatGpt432k0314 = 'gpt-4-32k-0314';
const kChatGptTurbo0613 = 'gpt-3.5-turbo-0613';
const kChatGptTurbo1106 = 'gpt-3.5-turbo-1106';
const kChatGptTurbo16k0613 = 'gpt-3.5-turbo-16k-0613';
const kChatGpt40631 = 'gpt-4-0613';
const kGpt41106Preview = 'gpt-4-1106-preview';
const kGpt4VisionPreview = 'gpt-4-vision-preview';

[redevrx]

@r2nochi @rocboronat you can using ChatModelFromValue('model-name')

[rocboronat]

Great! Thanks a lot, @redevrx ! 🙇

[rocboronat]

We still need to know what's the name of the model that uses GPT-4o mini...

[redevrx]

I add this model in next version ในวันที่ อ. 5 พ.ย. 2024 เวลา 17:09 Roc Boronat ***@***.***> เขียนว่า:

…

We still need to know what's the name of the model that uses GPT-4o mini... — Reply to this email directly, view it on GitHub <#121 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AKLSYJNY53WFY7GGI7MPEZ3Z7CKPBAVCNFSM6AAAAABPMBSCXCVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDINJWG42TOMRWHA> . You are receiving this because you were mentioned.Message ID: ***@***.***>

[rocboronat]

Oh, just an update! The name is gpt-4o-mini and in this project version 3.0.7, it can be used as ChatModelFromValue(model: 'gpt-4o-mini').

A more complete example would be:

final request = ChatCompleteText(
  messages: [
    {"role": "system", "content": system},
    {"role": "user", "content": prompt},
  ],
  maxToken: 1000,
  model: ChatModelFromValue(model: 'gpt-4o-mini'),
);

I think with this we can close this issue ✅