Blablador endpoint#

In this notebook we will use the blablador infrastructure at the Research Center Jülich. Before you can access it, you need to create an API key as explained on this page. You will see that also this method uses the OpenAI API and we change the base_url.

import os
import openai
openai.__version__
'3.31.0'
def prompt_blablador(message:str, model="01 - GPT-OSS-120b - an open model released by OpenAI in August 2025"):
    """A prompt helper function that sends a message to Blablador (FZ Jülich)
    and returns only the text response.
    """
    import os
    
    # convert message in the right format if necessary
    if isinstance(message, str):
        message = [{"role": "user", "content": message}]
    
    # setup connection to the LLM
    client = openai.OpenAI()
    client.base_url = "https://api.blablador.fz-juelich.de/v1/"
    
    # todo: enter your API key here:
    # client.api_key = ""
    client.api_key = os.environ.get('BLABLADOR_API_KEY')
    response = client.chat.completions.create(
        model=model,
        messages=message
    )
    
    # extract answer
    return response.choices[0].message.content
prompt_blablador("Hi!")
'Hey there! 👋 How’s it going? Let me know if there’s anything you’d like to chat about or need help with today.'

Exercise#

List the models available in the blablador endpoint and try them out by specifying them when calling prompt_blablador().

client = openai.OpenAI()
client.base_url = "https://api.blablador.fz-juelich.de/v1/"
client.api_key = os.environ.get('BLABLADOR_API_KEY')

print("\n".join([model.id for model in client.models.list().data]))
70 - EVE-Instruct - Expert Earth Observation and Earth Science (ES) domains
alias-eve
01 - GPT-OSS-120b - an open model released by OpenAI in August 2025
alias-fast
02 - Qwen3.8-Flash-Next-NVFP4, general purpose large model
alias-large
alias-qwen3.8-flash-next
alias-embeddings
gpt-3.5-turbo
text-davinci-003
text-embedding-ada-002
alias-qwen3-8b-embeddings
07 - Qwen3.8-27B-FP8 - Multimodal model from Aug 2026
alias-qwen38-27b
alias-code
alias-default
00 - Aleph Kolibri
15 - DeepSeek-V4.1-Flash on JUWELS Booster
20 - EVE-Instruct - Expert Earth Observation and Earth Science (ES) domains
30 - Swiss AI: Apertus-v1.5-70B
80 - MiMo-V2.6-Flash-RL on Juwels Booster
80 - MiMo-V2.6-Pro-RL on Juwels Booster
90 - Glm-5.3-Flash on Juwels Booster
90 - Kimi-K3 1M on Juwels Booster
90 - Qwen 3.8-27B on Juwels Booster
90 - Qwen 3.8-Flash-Next-125B-AWQ-W4A16 on Juwels Booster - An excellent model from September 2026
999 - FLUX.2-dev - An image generator (Black Forest Labs)
999 - Qwen-Image-2.1 on JUWELS Booster (generation + editing)
Anonymizer: M-size ShinrAI PII 1.3
Muse-Spark-Open-816B-A42B - Built with Muse Spark Open
Swift-Qwen3.8-27b
alias-aleph-kolibri-1
alias-anonymizer
alias-apertus
alias-apertus-70b
alias-clef
alias-deepseek-v41-flash-booster
alias-flux2
alias-glm-5.3-flash
alias-huge
alias-hyperqwen-27b
alias-image
alias-kimi-k3-1m
alias-mimo-v2.6-flash
alias-mimo-v2.6-pro
alias-muse-spark
alias-ocr
alias-qwen3-4b-embeddings
alias-qwen3-4b-reranker
alias-qwen3-4b-reranking
alias-qwen3-8b-reranking
alias-qwen3.8-27b
alias-qwen38-quick
alias-video
alias-voice-drama3
deepseek-v4.1-flash-at-hzdr
faster-whisper-large-v3
qwen3.8-27b
trustllm-v2-8b-sft
trustllm-v2-8b-sft-8k
trustllm-v2-8b-sft-mixb2-exp