%%capture

!pip install -q  llama-index-llms-nebius  python-dotenv

import os, sys

## Recommended way of getting configuration
if os.getenv("COLAB_RELEASE_TAG"):
   print("Running in Colab")
   from google.colab import userdata
   NEBIUS_API_KEY = userdata.get('NEBIUS_API_KEY')
else:
   print("NOT running in Colab")
   from dotenv import load_dotenv
   this_dir = os.path.abspath('')
   parent_dir = os.path.dirname(this_dir)
   sys.path.append (os.path.abspath (parent_dir))
   load_dotenv()
   NEBIUS_API_KEY = os.getenv('NEBIUS_API_KEY')

## quick hack (not recommended) - you can hardcode the config key here
# NEBIUS_API_KEY = "your_key_here"

if NEBIUS_API_KEY:
  print ('✅ NEBIUS_API_KEY found')
  os.environ['NEBIUS_API_KEY'] = NEBIUS_API_KEY
else:
  raise RuntimeError ('❌ NEBIUS_API_KEY NOT found')

NOT running in Colab
✅ NEBIUS_API_KEY found

%%time

from llama_index.llms.nebius import NebiusLLM

llm = NebiusLLM(
    model="openai/gpt-oss-20b-Instruct-2507", 
    api_key=NEBIUS_API_KEY,
    temperature=0.1,  # either set temperature or `top_p`
)

response = llm.complete("What is the capital of Netherlands?")


print ('----model answer -----')
print (response)
print ('---------')

/Users/sujee/my-stuff/nebius/ai-studio-cookbook/upstream-2-tf-launch/.venv/lib/python3.12/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
  from .autonotebook import tqdm as notebook_tqdm
None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.

----model answer -----
The capital of the Netherlands is Amsterdam.
---------
CPU times: user 2.42 s, sys: 677 ms, total: 3.1 s
Wall time: 11.7 s

Run models on Nebius Token Factory (via LlamaIndex API)¶

References and Acknowledgements¶

Pre requisites¶

1 - Install Dependencies¶

2 - Load Configuration¶

3 - Pick a Model¶

4 - Run the Model¶

5 - Try Your Queries¶