This page contains different examples on how you can use the LLMs.

More examples (e.g. for vLLM or Ollama) can be found in our Example Collection.

• Querying model list
• Simple completions
• Chat completions

Querying model list 

The following example shows how to query available models with curl:

curl https://llm.hpc.itc.rwth-aachen.de/v1/models \
    -H "Authorization: Bearer YOUR-API-KEY"

Simple completions

The following examples show how to perform a simple completion.

Example for curl:

curl https://llm.hpc.itc.rwth-aachen.de/v1/completions \
    -H "Authorization: Bearer YOUR-API-KEY" \
    -H "Content-Type: application/json" \
    -d '{
          "model": "mistralai/Mistral-Small-3.2-24B-Instruct-2506", 
          "prompt": "San Francisco is a", 
          "max_tokens": 300
        }'

Example for OpenAI Python SDK:

import openai

client = openai.OpenAI(
    base_url="https://llm.hpc.itc.rwth-aachen.de",
    api_key="YOUR-API-KEY"
)

response = client.completions.create(
    model="mistralai/Mistral-Small-3.2-24B-Instruct-2506",
    prompt="San Francisco is a",
    max_tokens=300
)

print(response)

Example for Langchain Py:

from langchain_openai import ChatOpenAI, OpenAI

llm = OpenAI(
    base_url="https://llm.hpc.itc.rwth-aachen.de",
    api_key="YOUR-API-KEY",
    model="mistralai/Mistral-Small-3.2-24B-Instruct-2506",
    max_tokens=300
)

prompt = "San Francisco is a"
result = llm.invoke(prompt)
print(result)

Chat completions 

The following examples show how to perform a chat completion.

Example for curl:

curl -X POST https://llm.hpc.itc.rwth-aachen.de/v1/chat/completions \
    -H "Authorization: Bearer YOUR-API-KEY" \
    -H "Content-Type: application/json" \
    -d '{
          "model": "mistralai/Mistral-Small-3.2-24B-Instruct-2506",
          "messages": [
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "San Francisco is a"}
          ],
          "max_tokens": 300
        }'

Example for OpenAI Python SDK:

import openai

client = openai.OpenAI(
    base_url="https://llm.hpc.itc.rwth-aachen.de",
    api_key="YOUR-API-KEY"
)

response = client.chat.completions.create(
    model="mistralai/Mistral-Small-3.2-24B-Instruct-2506",
    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "San Francisco is a"}
    ],
    max_tokens=300
)

print(response)

Example for Langchain Py:

from langchain_openai import ChatOpenAI, OpenAI

llm = ChatOpenAI(
    base_url="https://llm.hpc.itc.rwth-aachen.de",
    api_key="YOUR-API-KEY",
    model="mistralai/Mistral-Small-3.2-24B-Instruct-2506",
    max_tokens=300
)

messages = [
    ("system", "You are a helpful assistant."),
    ("human", "San Francisco is a"),
]

result = llm.invoke(messages)
print(result.content)