Quickstart

So you want to call some models. Good news: if you’ve ever used the OpenAI SDK, you already know how to use Token Router. The only thing that changes is the base URL and the key.

The whole trick

Point your OpenAI client at https://beta.token-router.org/v1 and authenticate with a vk_live_… key. That’s it. Everything else is the API you already know.

Get set up

1. Sign in. Head to the dashboard and sign in with GitHub. You’ll land with $5 in free credits — enough to try things before you spend a cent.

2. Mint an API key. In the dashboard, open Keys and create one. You’ll get a vk_live_… token. Copy it now — like any good secret, we only show it once.

3. Make a request. Use it as a bearer token against /v1. See below.

Your first request

curl

curl https://beta.token-router.org/v1/chat/completions \
  -H "Authorization: Bearer vk_live_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.6-27b",
    "messages": [
      {"role": "user", "content": "Explain Token Router in one sentence."}
    ]
  }'

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://beta.token-router.org/v1",
    api_key="vk_live_your_key_here",
)

resp = client.chat.completions.create(
    model="qwen3.6-27b",
    messages=[{"role": "user", "content": "Explain Token Router in one sentence."}],
)
print(resp.choices[0].message.content)

JavaScript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://beta.token-router.org/v1",
  apiKey: "vk_live_your_key_here",
});

const resp = await client.chat.completions.create({
  model: "qwen3.6-27b",
  messages: [{ role: "user", content: "Explain Token Router in one sentence." }],
});
console.log(resp.choices[0].message.content);

What can I call?

Ask the gateway directly — it speaks the OpenAI model-list format:

curl https://beta.token-router.org/v1/models \
  -H "Authorization: Bearer vk_live_your_key_here"

The catalog reflects whatever the network is actively serving right now. Pick a model id from that list and drop it into your request.

How billing works

You pay for what you use, metered per request. Behind the scenes, 70% of every dollar goes to the provider whose node answered you, and 30% goes to the treasury (which, neatly, funds bonuses that pull more providers online). Your $5 starter credit spends just like topped-up credit.

Next steps

• Curious where your tokens actually go? Read The Fair Ecosystem.
• Want to be on the earning side? Start with Contribute Compute.
• Need every parameter and endpoint? See the Developer API.