Confusion Regarding Google AI Studio API Pricing

[shenoyajith]

Hi Team,
I am very confused about calculating pricing of the gemini API using AI Studio.
The pricing stated is :
Prompts up to 128k tokens
Input Pricing
$0.075 / 1 million tokens

output Pricing
$0.30 / 1 million tokens

Say , my input is 1000 tokens , Output is 2000 tokens, will I be charged a flat charge of (1000* 0.075) + (2000 * 0.3)  , or will I be charged at a pro-rata basis? 
i.e I pay for only the total token amount I use ?
(1000 * (cost for 1000 input tokens , derived from a million)) + (2000 * (cost for 2000 output tokens , derived from a million)) ?

thanks

[ronnelg]

Hi @shenoyajith, 

Welcome to Google Cloud Community!

To answer your question, you will be charged on a pro-rata basis. You will pay for the exact number of tokens used. The pricing is based on the total number of tokens used for both input and output.

Please be informed also that the pricing is different for each model.

Was this helpful? If so, please accept this answer as “Solution”. If you need additional assistance, reply here within 2 business days and I’ll be happy to help.

[shenoyajith]

Thanks , as a follow up. The rate limits for the Gemini models on ai studio seem 10x as that of vertex ai models. (200 RPM vs 2000RPM) for us east region.

Is that accurate ?

Would it be a better idea to use ai studio If I need higher RPM for my usecases ?

[ronnelg]

Yes, Gemini models on AI Studio have more RPM if you will get the paid tier. Also, you can request for a higher rate limit depending on your request.