CTS Router Quickstart

CTS Model Router provides an OpenAI-compatible API interface. You can use standard official client libraries by pointing the base URL to our gateway.

---

1. Obtain an API Key

Generate an API key from the CTS Router Developer Console. Store your key in an environment variable:

export CTS_API_KEY="cts_live_..."

---

2. Make Your First Request

cURL

curl -X POST https://api.creativetechstudios.org/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $CTS_API_KEY" \
  -d '{
    "model": "deepseek-r1-distill",
    "messages": [
      {"role": "system", "content": "You are a concise technical assistant."},
      {"role": "user", "content": "Explain the difference between on-device and edge routing."}
    ],
    "temperature": 0.2
  }'

Python

from openai import OpenAI
import os

client = OpenAI(
    api_key=os.environ.get("CTS_API_KEY"),
    base_url="https://api.creativetechstudios.org/v1"
)

response = client.chat.completions.create(
    model="deepseek-r1-distill",
    messages=[
        {"role": "system", "content": "You are a concise technical assistant."},
        {"role": "user", "content": "Explain the difference between on-device and edge routing."}
    ],
    temperature=0.2
)

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

TypeScript / Node

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: process.env.CTS_API_KEY,
  baseURL: 'https://api.creativetechstudios.org/v1',
});

async function main() {
  const completion = await client.chat.completions.create({
    model: 'deepseek-r1-distill',
    messages: [
      { role: 'system', content: 'You are a concise technical assistant.' },
      { role: 'user', content: 'Explain the difference between on-device and edge routing.' },
    ],
    temperature: 0.2,
  });

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

main();

---

3. Streaming Responses

To stream tokens in real-time with sub-second time-to-first-token (TTFT), pass "stream": true:

stream = client.chat.completions.create(
    model="claude-3-7-sonnet",
    messages=[{"role": "user", "content": "Synthesize a 3-point edge deployment strategy."}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="", flush=True)