Am I using the latest version of GPT Vision?

API
,
1

Hi, I have seen reference to ‘GPT4 Turbo Vision’ and struggling to work out what the latest version of the GPT4 Vision API to use.

Right now, I am calling ‘gpt-4-vision-preview’ from my code, and the header response returns two fields that look a bit outdated.

‘openai-version’: ‘2020-10-01’
‘model": "gpt-4-1106-vision-preview’

Can anyone explain why the ‘openai’ version is so out of date? and is the ‘gpt-4-1106-vision-preview’ model the latest one to use? If not, how can I update these?

On another note, with regards to rate limits, is the RPD (Requests Per Day) calculated by the number of images you send, or can you send 1 POST request with 5 Images and that counts as one RPD?

Many Thanks

2

Latest model is gpt-4-turbo-2024-04-09

GPT-4 Turbo with Vision
The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Currently points to gpt-4-turbo-2024-04-09 .

Ref: https://platform.openai.com/docs/models/continuous-model-upgrades

1 Like
3

Oh wow sorry I never realised the turbo models include Vision - all makes sense now thank you!