Deprecated internal demo server due to costs. Inflation is real 🥲.

Conversation (scrollable)
💁‍♀️ There's nothing here. Yet.



Due to Vercel Edge function rate limiting, requests/responds that require more than 10 seconds of execution time or 30 seconds of initial response time will return a rate limiting error message from Vercel server.

Data IO

Parameters


Request Body

{
  "max_tokens": 500,
  "top_p": 1,
  "presence_penalty": 0,
  "frequency_penalty": 0,
  "temperature": 1,
  "model": "gpt-4",
  "prompt": ""
}

Raw Response
Nothing here yet!