API key used from one account gives avg 2 minutes response time, when used from other account its 12s to 16s response time with same request

Hi! I have web app for generating recipes from ingredients via open ai api. I am sending post request and using API key in Bearer Token for Authorization. Issue is: when I use open ai key from my account then the request takes more than 2 minutes and then gives the response. But when I used the api key from my friends account, then the response time becomes 12s to 16s. I couldn’t found any solution to this.

I am doing it in Nextjs. Here is my request body:

const getRecipes = async () => {
    router.push("/recipes");
    toggleLoadingRecipes();

    try {
      const response = await fetch(
        "https://api.openai.com/v1/chat/completions",
        {
          method: "POST",
          headers: {
            Authorization: `Bearer ${process.env.NEXT_PUBLIC_OPENAI_API_KEY}`,
            "Content-type": "application/json",
          },
          body: JSON.stringify({
            model: "gpt-3.5-turbo",
            messages: [
              {
                role: "system",
                content:
                  "You are a skilled ....",
              },
              {
                role: "user",
                content: `Please produce two unique recipe for the following ingredients: ${formatStringArray(
                  ingredients
                )}`,
              },
            ],
          }),
        }
      );

      const fetchedRecipes = await response.json();
      const recipesArray = Object.values(
        JSON.parse(
          removeTrailingCommas(fetchedRecipes.choices[0].message.content)
        )
      );
      setIngredientsHandler(ingredients);
      setRecipesHandler(recipesArray as Recipe[]);

      // console.log(recipesArray);
      setLoading(false);
      toggleLoadingRecipes();
    } catch (error) {
      setLoading(false);
      // console.log(error);

      router.push("/");
    }
  };

It is like you discover, not the application, but your account and the gpt-3.5-turbo models.

Maybe they bought new datacenter services for “special” users made of gamer GPUs now capable of running a vastly reduced gpt-3.5-turbo? Nobody knows.

Thank you for reply.

I am making request from Asia (Pakistan). The account was created by a team member in USA. When he made the request, response time was same 2 to 3 minutes as I am getting in Asia (Pakistan).

Can you give me any guide for how I can mention “Open AI” team on my post?

Thanks for helping out !