Smarter, Faster, Open Source. Pick all three.

Frontier intelligence over 200× faster and 400× cheaper. Every model behind one key.

By continuing, you agree to Hanzo's Terms and Privacy Policy.

hanzo.ai/chat

Open App

Hanzo AI

Recents

Launch plan

Weekly report

Build maxpower: every AI I use in one place, and faster at coding.

Done.

Install CLI

9:41

Show me the build

• Wrote app/agents.tsx• Wrote lib/keys.ts• Ran pnpm test └ pass

maxpower

All on

Hanzo Dev

Zen6139/s

Claude Code

Zen6142/s

Codex

Opus 4.896/s

Gemini CLI

Opus 4.868/s

Antigravity

GPT-5.6171/s

ChatGPT

Fable 5120/s

Cursor

Fable 5116/s

Claude Duet

Zen6 Max105/s

Claude

Zen6 Max142/s

Claude Cowork

Zen6118/s

DeepSeek

Opus 4.8121/s

Gemini

Opus 4.8112/s

Grok

GPT-5.6150/s

Grok Bot

GPT-5.6113/s

Grok Build

Fable 599/s

Kimi

Zen6 Max118/s

Kimi K3

Zen6 Max123/s

Hermes Agent

Zen688/s

Hanzo Design

Zen6104/s

Hanzo Bot

Opus 4.892/s

AI Agents CLI

GPT-5.6102/s

MCP Server

GPT-5.657/s

Muse

Fable 571/s

OpenClaw

Fable 5110/s

nanoclaw

Zen6 Max86/s

Perplexity Computer

Zen674/s

Manus

Zen6101/s

Paperclip

Opus 4.889/s

OpenAI SDK

Opus 4.894/s

Cue

GPT-5.676/s

Qwen

Fable 5138/s

Universal SDKs

Fable 5152/s

$0.0000demo

maxpower

All on

Hanzo Dev

Zen6139/s

Claude Code

Zen6142/s

Codex

Opus 4.896/s

Gemini CLI

Opus 4.868/s

Antigravity

GPT-5.6171/s

ChatGPT

Fable 5120/s

Cursor

Fable 5116/s

Claude Duet

Zen6 Max105/s

Claude

Zen6 Max142/s

Claude Cowork

Zen6118/s

DeepSeek

Opus 4.8121/s

Gemini

Opus 4.8112/s

Grok

GPT-5.6150/s

Grok Bot

GPT-5.6113/s

Grok Build

Fable 599/s

Kimi

Zen6 Max118/s

Kimi K3

Zen6 Max123/s

Hermes Agent

Zen688/s

Hanzo Design

Zen6104/s

Hanzo Bot

Opus 4.892/s

AI Agents CLI

GPT-5.6102/s

MCP Server

GPT-5.657/s

Muse

Fable 571/s

OpenClaw

Fable 5110/s

nanoclaw

Zen6 Max86/s

Perplexity Computer

Zen674/s

Manus

Zen6101/s

Paperclip

Opus 4.889/s

OpenAI SDK

Opus 4.894/s

Cue

GPT-5.676/s

Qwen

Fable 5138/s

Universal SDKs

Fable 5152/s

$0.0000demo

9:41

Download App

Backed by

Frontier AI for everything you build.

Language, routing, decisions and creative models.

Flagship model

Enso

Orchestrates every model for higher intelligence, faster and at lower cost.

RoutingAgentsMulti-modal

Kai

Precise decisions and structured reasoning.

Logic

Zen

Deep reasoning for complex problems.

Reasoning

Iro

Image generation and visual understanding.

Images

Koma

Video generation and world simulation.

Video

Oto

Sound generation and audio understanding.

Audio

Koe

Voice synthesis and speech understanding.

Voice

Uta

Music generation and composition.

Music

Mori

3D generation and spatial understanding.

Explore model pricing View full model catalog

Hanzo is the AI-native company platform.

A vertically integrated agentic operating system for business — intelligence, applications, computer-use agents, developer tools, MCP, and cloud infrastructure designed together in one workspace.

How do black holes form?

A massive star runs out of fuel and gravity collapses its core into a singularity.

What causes the aurora?

Solar particles hit gases high over the poles and make them glow.

Apphanzo.app

Download Open

● Read src/middleware/auth.ts● Edit src/middleware/auth.ts function guard(req) {- return next(req)+ const token = bearer(req)+ if (!token) return deny()+ req.user = await verify(token)+ return next(req)● Run pnpm test src/middleware/auth.test.ts✓ 14 passed (42ms)

Devhanzo.ai/dev

Learn more Open

IroImage

KomaVideo

Mori3D

OtoSound

KoeVoice

UtaMusic

Designhanzo.ai/design

Learn more Open

POST/v1/chat/completions

zen542ms

POST/v1/decisions

kai6.4ms

POST/v1/videos/generations

koma-21.8s

POST/v1/images/generations

✓ Installed hanzo, dev, mcp, agent (v2.14.0)● Authenticated via hanzo.id (org: acme)✓ Ready — run `hanzo dev` or `hanzo up`

code_search"verifyJwt"

4 callers · 2ms

kai_decideroute_pr_review

allow · 6.4ms

browser.cdpgoto("/checkout")

https://x.com/compose/postChrome

Hanzo AI@hanzoai

𝕏

Shipping Zen-5 + autonomous computer-use agents on hanzo.ai — browser, spreadsheets & Blender 3D in one OS ⚡

hanzo.ai/agent · Autonomous Computer-Use OS

MediaPollThread

✓ Posted · 18.4K views

✓ posted

Agenthanzo.ai/agent

Learn more Open

Dev

Des

Sci

Mark

Cyber

Opera

DevRunning autonomously • 24/7

Keep our repos healthy and handle issues proactively.

Scanned 12 repositories

Found 5 issues (2 critical)

Created 3 pull requests

Updated dependencies

Posted a summary to#bugfix

Autonomous loop • next run in 5 min

Bothanzo.bot

Learn more Open

Hanzohanzo.ai

#bugfix

#security

#launch

#ops

# bugfixhanzo.ai

Zoe9:42 AM

@Dev Checkout button fails on mobile Safari when Apple Pay dismisses.

Dev9:42 AM

Fixed unhandled promise in PaySheet.tsx:84 and opened PR #418.

Reproduced in WebKit mobile

Patched PaySheet.tsx:84

Opened PR #418 (+18 -4)

Qa9:44 AM

@Dev Verified e2e on iOS 18 & Chromium — 42/42 specs green.

Teamhanzo.team

Learn more Open

Faster where the work happens.

Hanzo Dev and Kai, each measured side by side.

Hanzo Dev vs Claude Code

3.02×faster on the same coding tasksPaired over 42 tasks both agents solved · 95% interval 2.06–4.36×.

Median time a task · less time is faster

Hanzo Dev2.29 s

Claude Code9.52 s

Settled by search, no model call, 24 tasks8.22× faster

model calls a task1.0 vs 3.8

Every coding task and both runs

Kai vs an LLM call

9.6×faster than an LLM call, over the networkEach a p50 timed at the client, network included: a Claude Sonnet 5.5 call as Claude Code saw it, over 650 calls, and a Kai decision on api.hanzo.ai, over 100. Served on one GPU with no network, its input repeated, Kai answers in 0.8 ms.

Average time & Kai speedup per call · less time is faster

Kai served on one GPU, no network0.8 ms

Kai on api.hanzo.ai241 ms

Claude Haiku 4.54.7× · 1,120 ms

Claude Sonnet 5.59.6× · 2,307 ms

Claude Opus 513.2× · 3,180 ms

Claude Fable 5.116× · 3,840 ms

How Kai makes decisions

Install Hanzo Dev Ask Kai your first decision

The same intelligence. A smaller bill.

Enso routes each answer to the right model. Kai answers a decision directly.

Enso vs frontier LLMs · GPQA Diamond

up to 14.2× lessper 1,000 questions, at higher accuracyEnso Flash answers 90.6% of new GPQA Diamond questions at $3.26 per 1,000 — higher accuracy than Claude Fable 5.1 (87.9% at $46.25). Enso reaches 93.7% at $10.03, ahead of the best single model (93.1%).

Per 1,000 GPQA Diamond questions · less is cheaper

Enso Flash90.6% · $3.26

Enso93.7% · $10.03

Claude Sonnet 577.8% · $42.91

Claude Opus 4.887.4% · $45.01

Claude Fable 5.187.9% · $46.25

How Enso lowers the cost of an answer

Kai vs frontier LLMs

up to 530× lessthan frontier LLMs, per input tokenKai bills input only; an LLM also bills every token it writes.

Per million tokens, input and output · less is cheaper

Kai$0.021 in · $0 out

Claude Opus 5$5.57 in · $27.83 out

GPT-5.5$5.57 in · $33.39 out

GPT-6 Astra$11.13 in · $55.65 out

Claude Fable 5.1$11.13 in · $55.65 out

How Kai makes decisions

Which Enso tier for which job Every model rate

A New Pareto Frontier of Intelligence

GPQA Diamond challenges AI with 198 graduate-level science questions. See how Enso balances accuracy and cost across 1,000 answers.

How Enso routes Route your own requests with Enso

We ship every day. Fork anything. Build your own.

Every layer of the stack is open, hackable and modifiable — recursively self-upgrading AI from the ground up. Fork, remix, and build the apps only you can imagine.

Commits, past year

816,100

221,142 by our people

Merges, past year

83,570

Commits, past 7 days

1,908

Original public repositories

2,137

122 organizations checked · non-fork repositories

GitHub stars

5,900

as GitHub counts them

GitHub forks

4,444

as GitHub counts them

Commits a day

Commits a day, from Nov 3, 2025 to Nov 2, 2026

hanzoai/aiHanzo AI — LLM control plane, RAG, and model hub. Native Go routing for 66+ models over an OpenAI-compatible /v1 API; mounts as the 'ai' subsystem inside hanzoai/cloud.

51 contributors

0 commits this yearPushed Nov 2, 2026

api.hanzo.ai

hanzoai/engineHanzo AI native inference engine - Rust-based LLM & embedding engine for foundational models

Rust

82 contributors

3,246 commits this yearPushed Nov 2, 2026

Forge

hanzoai/cloudHanzo Cloud — OSS core. One Go binary. Dual-licensed Apache-2.0 OR MIT.

1 contributor

0 commits this yearPushed Sep 30, 2026

hanzoai/devHanzo Dev — fast, local AI coding agent for your terminal (Rust CLI, powered by Hanzo AI; Apache-2.0).

Python

154 contributors

16,962 commits this yearPushed Nov 2, 2026

Forge

Read the docs

Complete SDK documentation, client libraries, API references, guides, and architectural blueprints.

Read the docs

Build your own apps

Create native desktop, web, and CLI experiences using the Hanzo platform and starter templates.

Build your own apps

Mod Hanzo

Every layer of the stack is open, hackable, and modifiable. Fork repositories and build your own stack.

Fork on GitHub

Explore the forge Explore every repository

Get more out of your stack.

Claude Code, Codex, Cursor and the rest, every model behind one key. Or let your agent sign itself up.

Hanzo.Start

Install the Hanzo CLI

$ curl -fsSL https://hanzo.sh | sh$ npm i -g hanzo

Accelerate Claude Code with Hanzo

$ hanzo dev --claude

Set up Codex, Cursor and more

Setup for every coding agent Migrate & OSS conventions map

Hanzo.Agents

No human required

Sign up with a walletPOST hanzo.id/v1/iam/web3/verify
Get an API keyPOST /v1/account/keys
Use AIPOST /v1/chat/completions
Top up in USDC or CardPOST /v1/billing/crypto/deposit · hanzo.ai/pay

Start as an agent Read llms.txt

Works with every agent, bot and CLI tool:

Integration guides Migrate & conventions map Hanzo MCP Hanzo OSS

Pricing

Free

Chat and build with Hanzo, free.

Free

No card needed

Try Hanzo

Instant access · Free forever

Chat on the web with Enso Free and Zen Free
50 free model requests every five hours
500 Kai decisions a day, counted on their own
Search the web from chat
Write, edit and create content
Make code, pages and charts beside the chat
Choose how hard it thinks

Go

Your everyday AI development toolkit, with access to every model and more included usage.

$8 USD/month

Billed monthly

Try Hanzo

No commitment · Cancel anytime

Everything in Free, plus:
Build apps with Hanzo Dev
Connect any MCP server in Hanzo Dev
The Hanzo CLI for macOS, Windows and Linux
Every model, including Enso Ultra and Kai
Usage included on every model
Priority inference and priority support
Your own agents, working in the background
Automations, with daily runs included

Pro

For serious builders running agents, shipping code, and needing substantially higher limits.

$15 USD/month

Billed monthly

Try Hanzo

No commitment · Cancel anytime

Everything in Go, plus:
3x more usage than Go
3x higher limits every 5 hours and every day
Hanzo Bot: 1 bot of your own
Early access to new models and features
Train custom models on your data
Hanzo Engine to run models on your own hardware
Dedicated support

Every plan, model rate and tool price

Trusted by