Is an 8 second response time normal for this request, if not how can I speed it up?

[cyan pecan]

In general my requests take a long time to complete, so I created a simple request as a baseline and this takes about 8 seconds. Just wondering if this is typical when accessing ChatGPT via API

const configuration = new Configuration({
    apiKey: apiKey
});

const openai = new OpenAIApi(configuration);
let prompt = 'What is a dinosaur';

const conversation = [
    {
      role: ChatCompletionRequestMessageRoleEnum.System,
      content: 'You are a helpful assistant',
    },
    {
      role: ChatCompletionRequestMessageRoleEnum.User,
      content: prompt,
    },
];

const data = {
    model: 'gpt-3.5-turbo',
    messages: conversation,
};

const completions = await openai.createChatCompletion(data);

[thorn quiver]

The response times can vary depending on server load but it can be helpful to enable streaming for your responses—it won’t reduce the overall time it takes to complete but the response will immediately start generating text so you’re not just staring at nothing for 8s while it works.

More info here: https://github.com/openai/openai-cookbook/blob/0fa6534747c26902a86b91aa6c8b002e025ecfef/examples/How_to_stream_completions.ipynb

Also keep in mind that they just reduced the pricing on the gpt-3.5-turbo model by 25% so server traffic will likely elevated as usage increases