API Access¶

uniGPT provides an OpenAI-compatible API that allows researchers and developers to integrate AI models into their own applications, scripts, and workflows.

The API is available at:

https://gpt.uni-muenster.de/v1

Getting an API Key¶

To use the API, you need an API key (starting with sk-...). API keys are currently available for two use cases:

Research Projects¶

API keys for research projects are issued upon request. Contact the uniGPT team via our support channel:

uniGPT Support on Mattermost

Please briefly describe your project and intended usage so we can set appropriate quotas.

AI-Assisted Coding (OpenCode, Roo Code, etc.)¶

API keys for use with coding assistants are available through a self-service portal, where you can generate your own key without manual approval.

Using the Python OpenAI Client¶

Install the OpenAI Python library:

pip install openai

Basic Example¶

from openai import OpenAI

client = OpenAI(
    api_key="sk-YOUR_API_KEY",
    base_url="https://gpt.uni-muenster.de/v1"
)

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

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

Streaming Example¶

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

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

Using curl¶

curl https://gpt.uni-muenster.de/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-YOUR_API_KEY" \
  -d '{
    "model": "gemma-3-27b-it",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Available Models via API¶

You can use any of the internal models listed on the Available Models page by specifying their name in the model parameter, including specialized models such as medgemma-1.5-4b-it for medical text and image tasks.