Overview - Nebius AI Studio documentation

This cookbook respository is a collection of guides and examples for working with open models using Nebius AI Studio. Use these recipes to build and deploy intelligent applications faster.

Getting Started

Prerequisites:
- You’ll need a Nebius AI Studio account and API key. Sign up for free here.
- Python runtime (local, Google Colab etc.)
Follow the setup guide below:

Setup Guide

Clone the Repo

git   clone    https://github.com/nebius/ai-studio-cookbook/
cd    ai-studio-cookbook

Get Nebius API Key

To run most of the examples in this repo, you will need a Nebius API Key. Here is how to get it.

Go to studio.nebius.com.
Click on your profile and go to API Keys section.
Click on ‘Get API Key’
Give a name for the key (e.g. ‘examples1’)
Be sure to save the key before closing the dialog window

Goolge Colab

If you are using Google Colab environment no need to setup a python environment.Add NEBIUS API KEY as follows (one time setup).

**Go to **Google Colab
Click on Secrets tab on left
Add a new secret NEBIUS_API_KEY and set the value
Toggle ‘Notebook access’ button

Local Python Development Environment Setup

Follow the steps below for setting up a local python environment.Option 1 (Recommended): using UVIf the project is a ‘native’ uv project - it has files like uv.lock and pyproject.toml :

uv sync

# run notebooks like
uv run jupyter lab notebook.ipynb

# run python scripts
uv run python code.py

If the project only has requirements.txt file (not a native UV project):

uv venv --python 3.11
source .venv/bin/activate

uv pip install -r requirements.txt

# run notebooks like
uv run jupyter lab notebook.ipynb

# run python scripts
uv run python code.py

Option 2: Using Anaconda / mini-forge

conda create -n studio-1 python=3.11
conda activate studio-1
pip install -r requirements.txt

# run notebooks like
jupyter lab notebook.ipynb

# run python scripts
python code.py

Option 3: Using Python venv

python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

# run notebooks like
jupyter lab notebook.ipynb

# run python scripts
python code.py