Quickstart

This guide gets you from zero to a working API call. By the end you’ll have:

A RouterLink account and API key
A successful chat completion against any supported model
A budget set on your key so you can’t overspend

1. Create an API key

Visit routerlink.ai and sign in with email or Google.

Top up credits

Open Billing → Recharge and add credits. New accounts ship with a small free balance to test with.

Generate a key

Go to API Keys → Create key. Copy the key (it starts with rl- and is shown only once).

Set a monthly budget on the key while you’re here. If you hit the cap, RouterLink returns 429 instead of letting spend run away.

2. Make your first request

curl
Python (OpenAI SDK)
Node (OpenAI SDK)

curl https://router-link.world3.ai/v1/chat/completions \
  -H "Authorization: Bearer $ROUTERLINK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {"role": "user", "content": "Say hello in one short sentence."}
    ]
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://router-link.world3.ai/v1",
    api_key="<your-routerlink-key>",
)

resp = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Say hello in one short sentence."}],
)
print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://router-link.world3.ai/v1",
  apiKey: process.env.ROUTERLINK_API_KEY,
});

const resp = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [{ role: "user", content: "Say hello in one short sentence." }],
});
console.log(resp.choices[0].message.content);

3. Try a different provider

Same endpoint, different model — RouterLink figures out the upstream:

# Anthropic via OpenAI-compatible API
-d '{ "model": "claude-sonnet-4-6", "messages": [...] }'

# Google
-d '{ "model": "gemini-2.5-pro", "messages": [...] }'

For native Anthropic SDK usage, see the Integration Guide.

4. Watch your spend

Open the Dashboard to see request volume, latency, and cost broken down by model and key. Per-key budgets and email alerts at 70 / 90 / 100% are configured in API Keys → Edit.

Basics

API

1. Create an API key

2. Make your first request

3. Try a different provider

4. Watch your spend

Next steps

Use Claude Code

Full Integration Guide

Basics

API

​1. Create an API key

​2. Make your first request

​3. Try a different provider

​4. Watch your spend

​Next steps

Use Claude Code

Full Integration Guide

1. Create an API key

2. Make your first request

3. Try a different provider

4. Watch your spend

Next steps