Quick Start

This page helps you complete your first DDTokens API call. DDTokens is compatible with the OpenAI Chat Completions protocol, so most OpenAI SDK projects only need a different API key and base_url.

Prerequisites

Before you begin, make sure you have:

• A DDTokens account.
• A working API key. If you do not have one, read Create API Key first.
• A terminal that can run commands.

Configure Environment Variables

Set the API key and endpoint in your terminal:

export DDDT_API_KEY="sk-your-key-here"
export DDDT_BASE_URL="https://apiddt.com/v1"

Do not put the API key in your code repository. In production, inject it with CI/CD secrets, environment variables, or a secret management system.

Call the API with cURL

Run the following command to send your first message:

curl "$DDDT_BASE_URL/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $DDDT_API_KEY" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }'

On success, you receive a JSON response containing choices and usage. Use the usage field to reconcile token consumption.

Use TypeScript

Install the OpenAI SDK:

npm install openai

Create quickstart.ts:

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.DDDT_API_KEY,
  baseURL: process.env.DDDT_BASE_URL ?? "https://apiddt.com/v1",
});

async function main() {
  const response = await client.chat.completions.create({
    model: "gpt-4o-mini",
    messages: [{ role: "user", content: "Hello!" }],
  });

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

main();

Run it:

npx tsx quickstart.ts

Use Python

Install the OpenAI SDK:

pip install openai

Create quickstart.py:

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["DDDT_API_KEY"],
    base_url=os.environ.get("DDDT_BASE_URL", "https://apiddt.com/v1"),
)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello!"}],
)

print(response.choices[0].message.content)

Run it:

python3 quickstart.py

Use Go

Install an OpenAI-compatible Go SDK:

go get github.com/sashabaranov/go-openai

Create main.go:

package main

import (
	"context"
	"fmt"
	"os"

	openai "github.com/sashabaranov/go-openai"
)

func main() {
	config := openai.DefaultConfig(os.Getenv("DDDT_API_KEY"))
	config.BaseURL = "https://apiddt.com/v1"

	client := openai.NewClientWithConfig(config)
	response, err := client.CreateChatCompletion(
		context.Background(),
		openai.ChatCompletionRequest{
			Model: "gpt-4o-mini",
			Messages: []openai.ChatCompletionMessage{
				{Role: openai.ChatMessageRoleUser, Content: "Hello!"},
			},
		},
	)
	if err != nil {
		panic(err)
	}

	fmt.Println(response.Choices[0].Message.Content)
}

Run it:

go run main.go

Next Steps

• Review Model Pricing and choose a suitable model.
• Read Rate Limits and configure retries and rate limiting for production.
• Open a client integration guide to use DDTokens with common AI coding tools.