Get instant access to intelligent routing for 100+ LLM providers with zero infrastructure setup. Our cloud-hosted AI Gateway handles scaling, monitoring, and reliability automatically.
1

Sign up for Helicone

Create your free account at helicone.ai.
2

Add your LLM Provider keys to Helicone

Go to the Provider page in Helicone to add your provider API keys for all the providers you wish to use.
3

Create a Helicone API Key

Go to the API Key page in Helicone to create a Helicone API key.You will be required to include a valid Helicone API Key as an authorization header in every request.
4

Configure your AI client

Simply point your existing AI SDK to the Helicone gateway’s unified API endpoint. No other changes needed!
import { OpenAI } from "openai";

const openai = new OpenAI({
  baseURL: "https://ai-gateway.helicone.ai/ai",
  apiKey: process.env.HELICONE_API_KEY,
});

const response = await openai.chat.completions.create({
  model: "openai/gpt-4o-mini",
  messages: [{ role: "user", content: "Hello, world!" }],
});
Works with any model! Simply prefix the model with the provider name. You may find the full list of supported providers here
5

View your requests

Head to your Helicone dashboard to see:
  • Real-time request logs
  • Cost tracking across all providers
  • Latency metrics and performance insights
  • Token usage analytics
Everything is automatically tracked - no additional setup needed!

​
Next Steps

Routers in depth

Learn about routers, load balancing, and advanced features

Configuration Reference

Detailed configuration options and API documentation