One familiar API shape.

Send your Tok0n API key as a Bearer token. Create and revoke keys from the dashboard. The full key is shown only once.

curl https://tok0n.com/v1/chat/completions \
  -H "Authorization: Bearer $TOK0N_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "messages": [
      { "role": "user", "content": "Write a short headline for Tok0n" }
    ]
  }'

OpenAI JavaScript SDK

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.TOK0N_API_KEY,
  baseURL: "https://tok0n.com/v1",
});

const response = await client.chat.completions.create({
  model: "gpt-5.5",
  messages: [
    { role: "user", content: "Write a short headline for Tok0n" },
  ],
});

console.log(response.choices[0].message.content);

• 60 requests per minute per active Tok0n API key.
• 10 concurrent requests per user.
• A 55 RPM global upstream safety limit during private beta.

Tok0n reserves tokens before calling the upstream provider, then charges the actual successful usage and releases the remainder. Upstream timeouts, network failures, invalid responses, and missing usage are not billed.

One purchased Tok0n token equals one token reported by the successful upstream response. Token packs are one-time USD purchases; subscriptions and automatic top-ups are not available.