Understanding which GPT model is ready for production


I’d like to upgrade to one of the less expensive turbo models but I’m not sure which to use. From the docs, it says that:

gpt-4-1106-preview GPT-4 Turbo model featuring improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Returns a maximum of 4,096 output tokens. This preview model is not yet suited for production traffic

At the same time, there’s a new Turbo model that was just launched which doesn’t have the warning:

gpt-4-0125-preview New

GPT-4 Turbo
The latest GPT-4 model intended to reduce cases of “laziness” where the model doesn’t complete a task.

Is there any guidance in terms of which could/should be used in a production environment?


1 Like