Quickstart

Get up and running with AI Foundation Services in minutes. This guide walks you through installing the SDK, setting up authentication, and making your first API call.

---

Step 1: Install the OpenAI Package

AI Foundation Services uses an OpenAI-compatible API, so you can use the official OpenAI SDKs.

Python

pip install openai

Node.js

npm install openai

---

Step 2: Get an API Key

1. Go to the API Key Portal and create a free trial key.
2. Or purchase via the T-Cloud Marketplace for production use.

---

Step 3: Set Environment Variables

macOS / Linux

export OPENAI_API_KEY="your_api_key_here"
export OPENAI_BASE_URL="https://llm-server.llmhub.t-systems.net/v2"

Windows (PowerShell)

$env:OPENAI_API_KEY = "your_api_key_here"
$env:OPENAI_BASE_URL = "https://llm-server.llmhub.t-systems.net/v2"

Windows (CMD)

setx OPENAI_API_KEY "your_api_key_here"
setx OPENAI_BASE_URL "https://llm-server.llmhub.t-systems.net/v2"

---

Step 4: Make Your First API Call

curl

curl -X POST "$OPENAI_BASE_URL/chat/completions" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Llama-3.3-70B-Instruct",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is quantum computing in simple terms?"}
    ],
    "temperature": 0.5,
    "max_tokens": 150
  }'

Python

from openai import OpenAI

client = OpenAI()  # Reads OPENAI_API_KEY and OPENAI_BASE_URL from env

response = client.chat.completions.create(
    model="Llama-3.3-70B-Instruct",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is quantum computing in simple terms?"},
    ],
    temperature=0.5,
    max_tokens=150,
)

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

Node.js

import OpenAI from "openai";

const client = new OpenAI(); // Reads OPENAI_API_KEY and OPENAI_BASE_URL from env

const response = await client.chat.completions.create({
  model: "Llama-3.3-70B-Instruct",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "What is quantum computing in simple terms?" },
  ],
  temperature: 0.5,
  max_tokens: 150,
});

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

---

More Examples

Create Embeddings

from openai import OpenAI

client = OpenAI()

texts = ["The quick brown fox jumps over the lazy dog", "Data science is fun!"]
result = client.embeddings.create(input=texts, model="jina-embeddings-v2-base-de")

print(f"Embedding dimension: {len(result.data[0].embedding)}")
print(f"Token usage: {result.usage}")

Vision / Multimodal

from openai import OpenAI

client = OpenAI()

response = client.chat.completions.create(
    model="Qwen3-VL-30B-A3B-Instruct-FP8",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's in this image?"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://images.unsplash.com/photo-1546069901-ba9599a7e63c?w=400"
                    },
                },
            ],
        }
    ],
    max_tokens=300,
)

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

---

Next Steps

• Authentication — API key management and best practices
• Available Models — Browse all supported models
• Chat Completions Guide — Detailed guide with streaming, parameters, and more
• LangChain Integration — Use AIFS with LangChain for RAG
• LlamaIndex Integration — Use AIFS with LlamaIndex for RAG