KellyIQ

KellyIQ examples

Working examples for the KellyIQ API: size a whole sports betting slate as one portfolio from your own scripts, models, spreadsheets and AI assistants.

You send your bankroll and the bets you have chosen, with your view of each. KellyIQ removes the bookmaker's margin from each price, applies your view, and returns a dollar stake for every bet, sized across the slate together under per-bet and total-exposure limits.

Get a key

Create an API key in the KellyIQ app under Settings → API. Every plan includes API access, Free included, each with its own daily allowance. Then:

export KELLYIQ_API_KEY="kiqa_..."

Recipes

Each recipe is a complete script in Python (requests) and JavaScript (Node 18+, no packages).

Recipe	What it shows
first-optimize	Size a three-bet slate and read every part of the result
slate-from-csv	Keep your slate in a spreadsheet: CSV in, CSV of stakes out (slate.csv)
reproducible-results	Get exactly the same answer again with the returned seed
handling-limits	Back off and retry on rate limits and a busy server

cd recipes
python first-optimize.py        # or: node first-optimize.mjs

Each recipe has a walkthrough in the docs: Recipes.

Python package

pip install kellyiq (kellyiq-python): the same API with specific exceptions for each error and automatic retries when the server is busy.

Example	What it shows
python/size-a-slate.ipynb	A notebook: stakes, the probabilities behind them, and the risk at each Kelly fraction, as tables
python/slate_from_csv.py	CSV in, CSV of stakes out, with each error handled (slate.csv)
python/size_from_model.py	Your model's probabilities in, stakes merged back into the DataFrame (model_output.csv); needs pandas
python/nba_home_teams.py	A real NBA slate (DraftKings prices, Oct 30, 2026) sized with every home team at the same assumed Moderate Edge (nba_2026-10-30.csv); needs pandas

Guide: Python SDK.

Excel

spreadsheets/kellyiq-slate.xlsx: enter your bankroll and your bets, press Ctrl+Alt+F5, and get a stake for every bet with a summary of the slate. No macros, and your API key stays in a file on your computer, never in the workbook. Excel for Windows. Setup: spreadsheets/.

Benchmark

benchmarks/slate-sizing: three NBA slates sized by cap-then-scale, by the exact constrained optimum and by KellyIQ, scored by exact expected log growth. The slates, the scoring script and every stake are included so you can rerun it.

AI assistants (MCP)

KellyIQ runs a hosted MCP server at https://api.kellyiq.com/mcp, so your assistant can size a slate as one of its tools. Claude connects by signing in; coding tools use an API key, with ready-to-use configs in mcp/:

Assistant	Setup
Claude (web, desktop, mobile)	Settings, Connectors, Add custom connector, paste the URL, then Connect and sign in
Claude Code	mcp/claude-code.md
Cursor	mcp/cursor.json
VS Code (GitHub Copilot)	mcp/vscode.json
Gemini CLI	mcp/gemini-cli.md

Full guide: AI assistants (MCP).

Skills

skills/analyze-my-slate teaches the assistant to collect your slate in one message, confirm before using an optimize, and explain the stakes and the risk. Install steps for Claude and Claude Code: skills/.

Docs and support

• Quickstart, API reference, OpenAPI spec
• [email protected] (include the requestId from any error)

Keep your key out of code you commit or share; every example here reads it from the environment.

KellyIQ sizes the bets you choose; it does not choose bets or predict outcomes. Results are calculations, not betting advice. 21+, where legal.

The examples are MIT licensed. The KellyIQ optimizer itself runs as a hosted service.