Quick Start

maKI provides an OpenAI-compatible API. If you’ve used the OpenAI SDK before, you already know how to use it — just point it at our endpoint.

Base URL & Authentication

Base URL	https://maki.uni-mannheim.de/v1
Auth	Bearer token (API key)

To get an API key, contact your maKI administrator.

Python (OpenAI SDK)

pip install openai

from openai import OpenAI

client = OpenAI(
    base_url="https://maki.uni-mannheim.de/v1",
    api_key="your-api-key",
)

response = client.chat.completions.create(
    model="gemma4-26b",
    messages=[{"role": "user", "content": "What is the capital of France?"}],
)

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

curl

curl https://maki.uni-mannheim.de/v1/chat/completions \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemma4-26b",
    "messages": [{"role": "user", "content": "What is the capital of France?"}]
  }'

Streaming

Pass stream=True for token-by-token responses:

stream = client.chat.completions.create(
    model="gemma4-26b",
    messages=[{"role": "user", "content": "Explain quantum computing"}],
    stream=True,
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Embeddings

response = client.embeddings.create(
    model="jina-embeddings-v2-base-de",
    input="Ein Beispielsatz auf Deutsch",
)

print(response.data[0].embedding[:5])  # First 5 dimensions

Transcription

Transcribe audio files (WAV, MP3, FLAC, OGG):

audio_file = open("recording.wav", "rb")

transcription = client.audio.transcriptions.create(
    model="parakeet-v3",
    file=audio_file,
)

print(transcription.text)

curl https://maki.uni-mannheim.de/v1/audio/transcriptions \
  -H "Authorization: Bearer your-api-key" \
  -F model="parakeet-v3" \
  -F file="@recording.wav"

Health Check

curl https://maki.uni-mannheim.de/health
# OK

Further API documentation

maKI is built on LiteLLM. The API is OpenAI-compatible — for detailed descriptions of all endpoints, parameters, and SDK examples see the LiteLLM proxy documentation and the OpenAI API reference. Always use https://maki.uni-mannheim.de/v1 as the base_url.