And what happens when you reach the limit of tokens that allows you? I think that in Davinci 003 it was around 4000, with the chatgpt turbo api, how much is this limit? Why do I remember that when I tried it, when I got close to the limit, it stopped responding and I had to restart the conversation. Is it the same here? unlike chatgpt plus on the web you can talk without any kind of limit as much as you want, here it is the same I have that curiosity friend.
Hei enrique. There is a slightly noticeable difference between the web version and the API. You mainly use the API for your own application; unfortunately, it is not free. The pricing is really different from the web consumer version. Here you pay by token, as you mentioned, and you are limited by the amount of money you have literally. As far as I can tell, I have integrated OpenAI API in many apps, and it seems cheaper for common apps. If you don't have millions of users using your app regularly, you will spend less than 50$/month (16 million tokens).
And what happens when you reach the limit of tokens that allows you? I think that in Davinci 003 it was around 4000, with the chatgpt turbo api, how much is this limit? Why do I remember that when I tried it, when I got close to the limit, it stopped responding and I had to restart the conversation. Is it the same here? unlike chatgpt plus on the web you can talk without any kind of limit as much as you want, here it is the same I have that curiosity friend.
Hei enrique. There is a slightly noticeable difference between the web version and the API. You mainly use the API for your own application; unfortunately, it is not free. The pricing is really different from the web consumer version. Here you pay by token, as you mentioned, and you are limited by the amount of money you have literally. As far as I can tell, I have integrated OpenAI API in many apps, and it seems cheaper for common apps. If you don't have millions of users using your app regularly, you will spend less than 50$/month (16 million tokens).