Quickstart

JoyToken is an OpenAI-compatible model gateway. Your application sends model requests to JoyToken, and JoyToken handles API keys, routing, policies, wallet limits, usage, and billing attribution.

Required Values

Step 1: Set the Environment

$
export JOY_TOKEN_API_KEY="jt_xxx"
$
export JOY_TOKEN_OPENAI_BASE_URL="https://api-dev.joytokens.ai/openai/v1"

Keep API keys in server-side environment variables, secret managers, or CI/CD secrets. Do not put them in browsers, mobile apps, public repositories, or logs.

Step 2: Send a Request

$
curl "$JOY_TOKEN_OPENAI_BASE_URL/chat/completions" \
>
  -H "Content-Type: application/json" \
>
  -H "Authorization: Bearer $JOY_TOKEN_API_KEY" \
>
  -H "X-Request-ID: quickstart-001" \
>
  -d '{
>
    "model": "auto",
>
    "messages": [
>
      { "role": "user", "content": "Reply with exactly: pong" }
>
    ],
>
    "stream": false
>
  }'

A successful response includes model output in choices[0].message.content.

Step 3: Use the OpenAI SDK

1
import OpenAI from "openai";
2
3
const client = new OpenAI({
4
  apiKey: process.env.JOY_TOKEN_API_KEY,
5
  baseURL: process.env.JOY_TOKEN_OPENAI_BASE_URL,
6
});
7
8
const response = await client.chat.completions.create({
9
  model: "auto",
10
  messages: [{ role: "user", content: "Reply with exactly: pong" }],
11
});
12
13
console.log(response.choices[0]?.message?.content);

Step 4: Check the Integration

Choose a Next Step