Getting Started

Four steps: create an account, add a provider key you already own, mint a FreeRouter key, and send your first request. Budget about five minutes.

Prerequisites

  • An account with at least one supported gateway and an API key for it — for example OpenRouter, Vercel AI Gateway, or Cloudflare AI Gateway. FreeRouter is bring-your-own-keys (BYOK); it forwards requests using the keys you provide.
  • A terminal with curl, or a project using the OpenAI SDK for Python or Node.
BYOK, by design FreeRouter never resells inference. You pay your providers directly — often cheaper than a single gateway's markup — and keep full control of your keys.

Step 1 — Create your account

1
Sign up with email + OTP
Go to app.freerouter.com/app/signup and enter your email. We send a one-time passcode — no password to manage. Enter the code to land in your personal workspace.
2
(Optional) Create a team workspace
Working with others? Create a team workspace and invite members. The creator is the owner; every team keeps at least one owner. Keys, providers, and routing rules live inside a workspace.

Step 2 — Add a provider key (BYOK)

3
Open Providers → Add provider
In the dashboard, go to Providers, choose a gateway (e.g. OpenRouter), and paste the API key you already hold for it. FreeRouter encrypts it at rest and uses it only to forward your traffic. Add as many providers as you like — you'll route across them next.
Add two providers now Routing is more useful with more than one gateway. Adding a second provider up front lets you try %-split and failover on the Routing Rules page without coming back.

Step 3 — Create a FreeRouter API key

4
Keys → Create key
Go to API Keys and create a key. Pick its API shape (default openai) and attach a routing rule. Copy the key — it looks like fr_live_... and is shown only once.

You can create multiple FreeRouter keys — for example a openai-shaped key for production and an anthropic-shaped key for a service that speaks the Messages API. Each key carries its own shape and routing rule.

Step 4 — Make your first request

Point any OpenAI-compatible client at FreeRouter's base URL and pass your fr_live_... key. Here it is with curl:

# Set your FreeRouter key
export FREEROUTER_API_KEY="fr_live_your_key_here"

curl https://api.freerouter.com/v1/chat/completions \
  -H "Authorization: Bearer $FREEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o-mini",
    "messages": [
      { "role": "user", "content": "Hello from FreeRouter!" }
    ]
  }'

A successful response is a standard OpenAI chat completion object:

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "openai/gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "Hello! How can I help?" },
      "finish_reason": "stop"
    }
  ],
  "usage": { "prompt_tokens": 12, "completion_tokens": 9, "total_tokens": 21 }
}
Which gateway answered? FreeRouter adds an X-FreeRouter-Provider response header naming the gateway that served the request, so you can confirm your routing rule is doing what you expect.

Next steps

  • Quickstart — the full drop-in migration with Python and Node examples.
  • API Reference — endpoints, auth, and the per-key API shapes.
  • Routing Rules — configure %-split and priority failover.
  • Providers — supported gateways and how BYOK keys are used.
Next Quickstart — drop-in migration