TheoKanning
I find the completion API could be very slow, any solution?
Like if can pay more to get better service? or there is just no way and I have to wait?
ChatGPT does have a premium paid service, but they haven't released the API as of yet.
There are initial quotas.
Because this technology is new, we also want to make sure that rollouts are done responsibly. When you sign up, you’ll be granted an initial spend limit, or quota, and we’ll increase that limit over time as you build a track record with your application. If you need more tokens, you can always request a quota increase.
You can request an increase, but I think that's only token limited, not performance. They will be publishing an SLA on the apis and models.
We will be publishing an SLA soon. In the meantime you can visit our [Status page](https://status.openai.com/) to monitor service availability and view historical uptime. If your company or application has specific requirements, please [contact our sales team](https://openai.com/contact-sales).
https://openai.com/contact-sales/
The other thing to confirm is that it really is a congestion issue. Make sure your use case aligns w/ the model. Depending on the complexity of the completion, fine-tuning, and other factors, sometimes Ada, Babbage, or Curie are much faster and work better than Davinci due to the congestion.
Finally, sometimes they just have growing pains. Always check the status page. https://status.openai.com/
