This OpenAI API proxy injects Val Town's API keys. For usage documentation, check out https://www.val.town/v/std/openai

We have a 10 req/min per user ratelimiting.

If you're looking to use this proxy at a production capacity, please use your own API key by forking this val and removing this snippet of code (unless you want to ratelimit yourself):

const rlimit = new RateLimit({
  namespace: Deno.env.get("rlimit_namespace"),
  maximum: 10,
  interval: "1m",
});