Skip to main content
Version: Latest

Authentication

AI Foundation Services uses API keys for authentication. All requests must include your API key in the Authorization header.

Get an API Key​

Free Trial Key​

Get started immediately with a free trial key:

  1. Visit the API Key Portal
  2. Create an account and generate your API key
  3. Your trial key gives you access to all available models

Production Key​

For production workloads, purchase via the T-Cloud Marketplace.

Set Up Environment Variables​

Store your API key as an environment variable — never hardcode it in your source code.

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

To persist across sessions, add these lines to your ~/.zshrc or ~/.bashrc file.

Using the API Key​

With OpenAI SDKs​

When OPENAI_API_KEY and OPENAI_BASE_URL are set, the OpenAI SDKs pick them up automatically:

from openai import OpenAI

client = OpenAI()  # No need to pass api_key or base_url

You can also pass them explicitly:

from openai import OpenAI

client = OpenAI(
    api_key="your_api_key_here",
    base_url="https://llm-server.llmhub.t-systems.net/v2",
)

With HTTP Requests​

Include the API key in the Authorization header:

curl -X POST "https://llm-server.llmhub.t-systems.net/v2/chat/completions" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "Llama-3.3-70B-Instruct", "messages": [{"role": "user", "content": "Hello"}]}'

Base URL​

All API requests go to:

https://llm-server.llmhub.t-systems.net/v2

This is the OpenAI-compatible endpoint. For the full API specification, see the API Reference.

Best Practices​

  • Never commit API keys to version control. Use .env files and add them to .gitignore.
  • Use environment variables in production rather than hardcoding keys.
  • Rotate keys regularly via the API Key Portal.
  • Monitor usage through the API Key Portal to track token consumption and costs.
© Deutsche Telekom AG