AI Server OpenAI-Compatible
Model: Loading...
AI Playground
✓ Saved
Hello! I'm your AI assistant running on your own server. Try asking me anything!

API Endpoint

POST /v1/chat/completions

API Key

Your API key is your personal 42helv account key. Find it in your account settings under API Keys.

Enter it in the chat panel above or use it in your code — same key works across all your AI Servers.

Python
from openai import OpenAI

client = OpenAI(
    base_url="https://your-server.42helv.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="llama3.2",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

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

Clone & Develop Locally

Fork or clone the repository to customize your AI server.

git clone https://github.com/dannysimfukwe/ai-server-docker.git

Environment Variables

MODEL llama3.2

Deploy on 42helv

One-click deploy your AI server with your preferred model and configuration.

Deploy on 42helv