It seems like a free GPT API has a rate limit of 3 requests per minute.
Now that the API can be set server-side, we should be able to have multiple API keys stored on the server, and it tracks the use of each one and balances it out, so users are not rate-limited.
Seems like this GPT frontend has this feature already, I'd love it being a feature here :D
It seems like a free GPT API has a rate limit of 3 requests per minute.
Now that the API can be set server-side, we should be able to have multiple API keys stored on the server, and it tracks the use of each one and balances it out, so users are not rate-limited.
Seems like this GPT frontend has this feature already, I'd love it being a feature here :D