Node.js integration (fetch)

This is the most version-proof way: plain HTTP with fetch.

Requirements:

• OPENAI_API_KEY env var (your SU8 Codes key)
• Node.js 18+ (built-in fetch)

Minimal runnable example

node.mjs

const baseURL = 'https://www.su8.codes/codex/v1';
const apiKey = process.env.OPENAI_API_KEY;

if (!apiKey) throw new Error('Missing OPENAI_API_KEY');

async function main() {
  const resp = await fetch(`${baseURL}/responses`, {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',
      Authorization: `Bearer ${apiKey}`
    },
    body: JSON.stringify({
      model: 'gpt-5.2',
      reasoning_effort: 'high', // Optional: low / medium / high / xhigh (for reasoning models)
      instructions: 'You are a professional coding assistant', // Equivalent to System Prompt
      stream: true, // Recommended: use streaming to avoid Cloudflare 502 timeouts on long requests
      input: [
        {
          type: 'message',
          role: 'user',
          content: [{ type: 'input_text', text: 'Hello' }]
        }
      ]
    })
  });

  if (!resp.ok) {
    const text = await resp.text();
    throw new Error(`${resp.status} ${resp.statusText}\n${text}`);
  }

  const reader = resp.body.getReader();
  const decoder = new TextDecoder();
  while (true) {
    const { done, value } = await reader.read();
    if (done) break;
    process.stdout.write(decoder.decode(value, { stream: true }));
  }
  console.log('\n');
}

main();

Not sure about model ids? Copy from:

• Models

---

title: Python integration (requests)

Stable and straightforward: plain HTTP.

Minimal runnable example

main.py

import os
import requests

base_url = "https://www.su8.codes/codex/v1"
api_key = os.environ.get("OPENAI_API_KEY")
if not api_key:
    raise RuntimeError("Missing OPENAI_API_KEY")

resp = requests.post(
    f"{base_url}/responses",
    headers={
        "Content-Type": "application/json",
        "Authorization": f"Bearer {api_key}",
    },
    json={
        "model": "gpt-5.2",
        "reasoning_effort": "high", # Optional: low / medium / high / xhigh (for reasoning models)
        "instructions": "You are a professional coding assistant", # Equivalent to System Prompt
        "stream": True, # Recommended: use streaming to avoid Cloudflare 502 timeouts
        "input": [
            {
                "type": "message",
                "role": "user",
                "content": [{"type": "input_text", "text": "Hello"}],
            }
        ],
    },
    stream=True,
    timeout=60,
)

resp.raise_for_status()
for line in resp.iter_lines():
    if line:
        print(line.decode('utf-8'))

Model ids: copy from:

• Models