Price for API request with <1000 tokens?

Hi there,

Building a solution based on GPT3 API and would like to make cost prediction.

However, the following point is not clear from the documentation and different API vendors approach this differently, so I want to be sure to plan soland searching the forum didn’t help either.
For example, 1000 tokens for GPT-3 davinci-003 model costs $0.02.

So if my API request (prompt request + model response) contains, say, 100 tokens, I will be charged $0.002 (for 100 tokens only), or it will be charged $0.02 as for 1000 tokens batch (which I did not use however)?


I’m not an authority but I have interpreted it as 100 tokens will cost 10% of the cost of 1000. And while I have not done the maths, looking at my billing history suggests that’s what’s happening.

1 Like

thanks! Good as a workaround, but it is also great to have some reference to official doc or authority’ point of view.

I think the documentation is pretty clear with out being explicit that you are charged for actual token usage Pricing.

But beyond that I can’t help

I think I’ll stick with that opinion, too, until there are more inputs

appreciate this!

BTW Welcome to the community.

1 Like


Looking at it 8 months later, what did you find out @gregf?

You’re charged per individual token, not in blocks of 1000.