Skip to main content

Using the API

AI Model Endpoints​

AI model endpoints are compatible with the OpenAI API format, so you can use the official OpenAI SDK or any compatible HTTP client.

Authentication​

Include your API key in every request using the apikey header:

apikey: <your-api-key>

Finding Your Endpoint​

Open Platform → AI Catalog, click on a granted model to see its endpoint URL and model name.

Chat Completions​

curl https://aifactory-dev.ai-factory.datalab.tuwien.ac.at/<model-path>/v1/chat/completions \
  -H "apikey: <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<model-name>",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Explain transformers in one sentence."}
    ]
  }'

Python Example​

from openai import OpenAI

client = OpenAI(
    base_url="https://aifactory-dev.ai-factory.datalab.tuwien.ac.at/<model-path>/v1",
    api_key="<your-api-key>",
)

response = client.chat.completions.create(
    model="<model-name>",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

Replace <model-path> and <model-name> with the values shown in the catalog for your model.

Infrastructure Services​

Infrastructure services (such as the Compute API) have their own REST interface. The full API reference is available via Swagger at aifactory-dev.ai-factory.datalab.tuwien.ac.at/docs. Authentication is the same: use the apikey header.