Because it’s charged per input tokens too. If you have 5000 token conversation and model spist out 100 token answer you’re paying for full 5100 tokens. You can see this getting really huge really quickly with long conversations.
If you use it for Q&A, that’s a lot of tokens. If you use it to write software somewhat autonomously, it’s easy to go through a million tokens every few hours. Do that every day and you’ll be paying over $100 a month at that rate.
How fast do you burn through tokens that $4 for a million of them was a lot of money?
Because it’s charged per input tokens too. If you have 5000 token conversation and model spist out 100 token answer you’re paying for full 5100 tokens. You can see this getting really huge really quickly with long conversations.
If you use it for Q&A, that’s a lot of tokens. If you use it to write software somewhat autonomously, it’s easy to go through a million tokens every few hours. Do that every day and you’ll be paying over $100 a month at that rate.