ENGINE: worm-chat | LATENCY: <500ms

Next-Gen Autonomous AI Backend

High-performance AI chat completions endpoint with instant Server-Sent Events (SSE) streaming, multi-turn session persistence, defensive security analysis, and fine-tuned persona presets.

Status

99.9% Online

Architecture

Serverless Edge

Protocol

SSE & JSON

Security

Token Throttled

Interactive Live Playground

Test real-time chat completions directly on the production endpoint

Method: POST /api/v1/gpt/chat

Client API Key (Header: heang-API-Key) Use Default

Persona Mode

Session ID

Prompt Message

Stream SSE (Live Chunking)

Console Response

Idle

// Click "SEND QUERY" to dispatch a request to: // POST https://heangblackcyberfree.online/api/v1/gpt/chat // // Ready to receive stream or JSON payload...

API Integration Cookbook

Ready-to-use production snippets in cURL, Python, JavaScript, and Telegram Bot

curl -X POST https://heangblackcyberfree.online/api/v1/gpt/chat \
  -H "Content-Type: application/json" \
  -H "heang-API-Key: e5af7b18d6c35aee93d710b6f92c8bb4dafdc1c339b0be02ffd065574c361a90" \
  -d '{
    "prompt": "Hello HeaNg! Tell me how worm-chat engine works.",
    "session_id": "test-user-1",
    "mode": "default",
    "stream": false
  }'

import requests

API_URL = "https://heangblackcyberfree.online/api/v1/gpt/chat"
API_KEY = "e5af7b18d6c35aee93d710b6f92c8bb4dafdc1c339b0be02ffd065574c361a90"

headers = {
    "Content-Type": "application/json",
    "heang-API-Key": API_KEY
}

payload = {
    "prompt": "Write a secure AES-256 encryption helper in Python",
    "session_id": "py-client-101",
    "mode": "coder"   # Options: default | cyber_security | coder | teacher
    "stream": True 
}

response = requests.post(API_URL, headers=headers, json=payload, timeout=60)
data = response.json()

if response.status_code == 200:
    print(f"[{data['data']['model']} - {data['data']['latency_ms']}ms]:")
    print(data['data']['reply'])
else:
    print("Error:", data)

// Standard Fetch (Node.js 18+ or Browser)
async function chatWithHeang(userPrompt) {
  const response = await fetch("https://heangblackcyberfree.online/api/v1/gpt/chat", {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "heang-API-Key": "e5af7b18d6c35aee93d710b6f92c8bb4dafdc1c339b0be02ffd065574c361a90"
    },
    body: JSON.stringify({
      prompt: userPrompt,
      session_id: "web-session-01",
      mode: "default"
    })
  });

  const json = await response.json();
  if (json.status === "success") {
    console.log("AI:", json.data.reply);
    return json.data.reply;
  } else {
    throw new Error(json.message);
  }
}

# pip install python-telegram-bot requests
import requests
from telegram import Update
from telegram.ext import ApplicationBuilder, MessageHandler, filters, ContextTypes

API_URL = "https://heangblackcyberfree.online/api/v1/gpt/chat"
API_KEY = "e5af7b18d6c35aee93d710b6f92c8bb4dafdc1c339b0be02ffd065574c361a90"

async def reply_handler(update: Update, context: ContextTypes.DEFAULT_TYPE):
    user_id = str(update.effective_user.id)
    await context.bot.send_chat_action(chat_id=update.effective_chat.id, action="typing")

    res = requests.post(API_URL, headers={"Content-Type": "application/json", "heang-API-Key": API_KEY}, json={
        "prompt": update.message.text,
        "session_id": f"tg_{user_id}",
        "mode": "default"
    })
    if res.status_code == 200:
        await update.message.reply_text(res.json()["data"]["reply"])

if __name__ == "__main__":
    app = ApplicationBuilder().token("YOUR_TELEGRAM_BOT_TOKEN").build()
    app.add_handler(MessageHandler(filters.TEXT & ~filters.COMMAND, reply_handler))
    app.run_polling()

Full HTTP Endpoints Specification

Method	Endpoint Path	Auth Header	Description
POST	/api/v1/gpt/chat	heang-API-Key: <key>	Primary AI completions with session history & optional streaming
GET	/api/v1/gpt/chat?prompt=...	heang-API-Key: <key>	Quick URL query testing (text/plain or JSON output)
GET	/api/v1/health	None	Liveness probe and deployment health status
GET	/api/v1/metrics	None	Observability metrics: uptime, total requests, latency