Update about image input in APIs

I am looking forward to utilize GPT-4 API image capabilities as taking an input and giving the output in text to build a pipeline as part of our AI product.

Does anybody have any ideas on when this will be released?

Thank you!

2 Likes

Hi and welcome to the developer forum!

There is currently no release date for multi modal GPT, it is still a research modal. There is sure to be an announcement when it is released.

3 Likes

@Foxabilo Thank you for the update!

1 Like

Bing uses it and it’s free. I understand what your doing but maybe that will help temporarily. What are you planning to do about the letters not correctly spelling in the pictures generated. Currently gpt4 is connected to Microsoft Bing and even it can’t fix the pictures to have correct spelling or generate new photos with correct spelling. Do you have a plan for that?

It’s available now for the API. Yippee!

1 Like

can You please give me the doc link.

I saw that input option is available through beta, any way to get access to this beta? Would love to test it out.

2 Likes

How do I access it, I haven’t foud any docs

1 Like

Kindly share whatever you can :slight_smile:

1 Like

I’m also curious, where did you find it in the API docs?

1 Like