What's the difference between "Enable usage-based pricing" and "Enable usage-based pricing for premium models"?

If I enable “Enable usage-based pricing”, but turn off “Enable usage-based pricing for premium models”?

It means when using a premium model not in max mode you will not be charged for requests, if you run out of fast requests, you will be switched into using slow requests.

For non-premium models which are not free you will be charged their usage.

For any model using max mode you will be charged through your fast requests first and when your fast requests run out you will need to enable usage-based pricing, this even includes for premium models as max mode usage is not covered through slow requests.

Hope this helps.

1 Like