Failed to create an image content analysis in ChatGPT[model_not_found] The model `gpt-4-vision-preview` has been deprecated

Hi @cjlums 

In your Zap step, you’ll need to update to use an available ChatGPT model.

@Troy Tessalone I need it to analyse a picture, so is there any work around for gpt? Thanks

@cjlums 

Did you try changing the model as suggest to:

gpt-4o

@Troy Tessalone I did change it, but when I upload the file there seems to be an issue with it when analysing 

@cjlums 

Or try using this Zap action: ChatGPT - Analyze Image Content with Vision

@Troy Tessalone That was my original problem, it seems that action is deprecated:

 

@cjlums 

I just tested and it worked. (screenshot)

The Image field description states: GPT-4 access is required.

Do you have GPT-4 access via a ChatGPT+ subscription?

Help articles for using ChatGPT in Zaps: https://zapier.com/apps/chatgpt/help

@Troy Tessalone Werid. My api key is working, and I do have a gpt-4 subscription, as well as $8 credit for api usage. I have no clue why this wouldn’t be working, I get this answer in the troubleshoot beta: 

@cjlums 

Are you using the most updated version of the ChatGPT Zap app integration? (top option)

@cjlums 

Are you passing in the URL of the image(s) as indicated in the Image field description?

@Troy Tessalone I have the top GPT and I am passing the Web content link through. I am trying to have it run every time a new file is uploaded to a google drive folder. Should I be using a different option for the file as the image in the GPT action?

@cjlums 

Can you post a screenshots with how your Zap step is configured in EDIT mode for the ‘Action’ tab section?

@Troy Tessalone 
 

@cjlums 

Check if the link is for a supported image format.

Check if the link is publicly accessible.

@Troy Tessalone It is completely public, no matter what I do it says the model is deprecated: 
 

@cjlums 

You can try opening a ticket with Zapier Support for possible help: https://zapier.com/app/get-help

Hi @cjlums 👋

I did some checking and according to the OpenAI’s documentation at the link the error references, the gpt-4-vision-preview model isn’t being deprecated until December 6th, 2024, but it also mentions that only existing users of these models will be able to continue using them until that shutdown date:

So if you weren’t already using that gpt-4-vision-preview model before the announcement they made on June 6th then I expect that’s why you’re running into this error.

The Analyse Image Content with Vision action will be switched over to use the gpt-4o model ahead of that shutdown date but I can’t provide an estimate on when that will be exactly. Once it is that should help to prevent those errors you’re currently seeing and allow you to use that action. 

In the meantime, perhaps you could try using the Conversation With Assistant (ChatGPT) action, or Conversation (ChatGPT) action, to analyse the images instead? Both have the option to allow you to select the gpt-4o model and have file/image fields that you could use to pass it image files that you want it to analyse. 

Can you give that other action a try and let me know if that works as hoped?