Log in Try Hanzo

Learn

Learn Hanzo

Start with a working request, then go as deep as you need. Everything here is part of the documentation — this page is the map.

Get started Hanzo University

Start here

Install, authenticate, and make your first call. The shortest path from nothing to a working request.

Hanzo University

Hanzo University

Courses and certifications live on Hanzo University.

Start here

Getting started

Install, authenticate, and make your first call. The shortest path from nothing to a working request.

Drive the platform from your terminal — projects, deploys, keys and logs.

Every endpoint, parameter and response shape.

Pick what to try

One thread with every model, your MCP tools, your files and a code sandbox.

Every model in every mode, with each run’s tokens and cost beside the answer.

A coding agent that opens the files, makes the change, runs the tests and shows you the diff.

Open-weight frontier models you can self-host anywhere, served on the Hanzo API.

Thirteen tools — shell, files, code, git, HTTP — behind one server.

A Python SDK where an agent is a model, instructions and tools, and several can sit behind one router.

Go further

Define an agent once and run it from chat, the API, or your own application.

Connect tools and data to models over the Model Context Protocol.

A starter for each Hanzo product. Browse, fork, deploy.

Open-source, accessible React components built on @hanzo/gui primitives.

The cross-platform UI kit and design system behind every Hanzo app.

From the blog

Optimizing for Headless Commerce in the Era of Agentic LLMs2026-10-26

Buyers are becoming agents. What it takes to be readable, signable and payable by an LLM with no human in the loop, and what Hanzo ships for it today.

Your AI is Planning To Kill You2026-10-25

Why frontier models fail when real lives are on the line, and how Hanzo Kai 1.9 enforces deterministic safety.

Kai 1: Decisions, Not Completions2026-10-07

Kai is Hanzo's decision model, served by the Hanzo API. Give it explicit state and a listed question, and it returns a typed, calibrated answer — a choice, a score, a yes/no, or a reasoned deferral.

Read the thinking

Product launches, architecture deep dives, and research essays.

Research papers

The reasoning behind the architecture, published in full.

The platform is open source — read it, run it, change it.

Questions

What is Hanzo and how does it work?

Hanzo is an AI cloud on one account. Chat with frontier models, build and ship with Hanzo Dev, and call the same models from one API: Enso, our frontier model, and Kai, which makes a decision in one call. How the platform fits together.

Can I keep using Claude Code?

Yes. Install the Hanzo CLI and sign in, then run Claude Code with its model calls going through api.hanzo.ai, or point your own Claude Code install at Hanzo. The commands, ready to copy.

Where do the numbers on hanzo.ai come from?

Each one is read when the page opens: the race and the boards from Hanzo's research runs, the prices from our price list, and the plans from our plan list. A figure whose source does not answer is left out, never replaced with an older one. Every board and its runs.

How much does it cost to use?

Free needs no card. Paid plans are sold by the month for one person and by the member for a team, and every paid plan can be cancelled any time. Enterprise is priced with our team. See every plan and model rate.

Can Hanzo run in our own cloud or on our own GPUs?

Yes, with Enterprise: in your cloud, on your own servers or fully offline, with dedicated compute and your own models. Hanzo Enterprise.

Build what’s next.

Try Hanzo Read the docs