Jupyter AI Integration

Jupyter AI is an extension for JupyterLab that adds AI-powered features including a chat interface, magic commands for inline AI assistance, and support for multiple model providers.

Jupyter AI supports custom OpenAI-compatible endpoints through its provider settings.

Prerequisites

An LLM API account with an API key
Jupyter AI installed or accessible

Setup

Get Your LLM API Key

Log in to your LLM API dashboard
Click Create Key to Start
Copy your new API key immediately — it will only be shown once
Store the key securely (e.g., in a password manager or .env file)

LLM API is an OpenAI-compatible gateway that gives you access to dozens of AI models through a single API key and endpoint.

Configure LLM API in Jupyter AI

Install Jupyter AI:

pip install jupyter-ai

In JupyterLab, open the AI chat panel and navigate to Settings.
Select "OpenAI" as the provider.
Set environment variables:

export OPENAI_API_KEY="your-llm-api-key-here"
export OPENAI_API_BASE="https://api.llmapi.ai/v1"

Select the model in the Jupyter AI settings panel.

Test the Integration

Verify that Jupyter AI can successfully communicate with LLM API by sending a test request. All requests will now be routed through LLM API.

Jupyter AI's %%ai magic command works with LLM API models for inline AI assistance in notebooks.

Benefits of Using LLM API with Jupyter AI

Multi-Provider Access: Use models from OpenAI, Anthropic, Google, and more through a single API
Cost Control: Track and limit your AI spending with detailed usage analytics
Unified Billing: One account for all providers instead of managing multiple API keys
Caching: Reduce costs with response caching for repeated requests

View all available models on the models page.