Noviqi Documentation

1. Quickstart Guide

Noviqi allows you to target any model (OpenAI, Anthropic, Gemini, etc.) using a single unified API endpoint. Simply replace your model API endpoint with Noviqi, and pass your gateway key.

Install SDK

npm install openai

Initialize Client

import OpenAI from 'openai';

const openai = new OpenAI({
  baseURL: 'http://localhost:8766/v1',
  apiKey: 'pk_live_your_gateway_key'
});

async function main() {
  const completion = await openai.chat.completions.create({
    model: 'gpt-4o',
    messages: [{ role: 'user', content: 'Hello!' }]
  });
  console.log(completion.choices[0].message);
}
main();

2. Token Optimization Cache

Our gateway automatically caches prompt contexts. When duplicate system messages or long history headers are detected, Noviqi matches client caches and avoids resending redundant tokens, saving up to 60% on billing.