Hi, GPT-4 official OpenAI api has a hard quota of 25 requests per hour for one API Token, we try to use as many tokens as possible, but it is still not enough to cover all api requests on here. This API uses GPT-4 when possible and when the quota is reached, it switches to 3.5-turbo.
Hi, GPT-4 official OpenAI api has a hard quota of 25 requests per hour for one API Token, we try to use as many tokens as possible, but it is still not enough to cover all api requests on here. This API uses GPT-4 when possible and when the quota is reached, it switches to 3.5-turbo.
Thanks for understanding,
ChatGPT API++ Team