Which endpoint to parse image-to-text with GPT-4?

I just got my API access to GPT-4 and I’d try to get text from an image.

Is this possible and which endpoint/body request should I use ?

Thanks a lot.

This feature is still unavailable, even with early access to the GPT-4 chat completion API.



May I please ask if it is available now?

Thank you very much.

You may certainly ask. The answer is now an optimistic “sometime in the future”.