Noviqi Documentation

Integrate the multi-provider LLM gateway in minutes.

1. Quickstart

Noviqi allows you to access models from various providers (OpenAI, Anthropic, Gemini, etc.) using a single endpoint. Simply update your API client base URL and pass your Noviqi Gateway Key.

Install SDK

npm install openai

Initialize Client

import OpenAI from 'openai';

const openai = new OpenAI({
  baseURL: 'http://localhost:8766/v1', // Point to your Noviqi gateway
  apiKey: 'pk_live_your_gateway_key'   // Use your Gateway secret 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. Intelligent Cache

Our gateway automatically caches request contexts. When repeated system messages or conversational histories are detected, Noviqi matches the cached context and avoids resending redundant tokens, saving up to 60% on API costs.

Need Help?

Can\'t find what you need? Visit the FAQ Page or reach out to us.