Skip to content
DocumentationTry Hanzo
45+ Zen Models

Zen Models
Language · Code · Vision · Audio

45+ open-weight models from 0.6B to 1T+, built by Zoo Labs Foundation and served on the Hanzo API. Zen MoDE (Mixture of Diverse Experts) architecture. All models on HuggingFace.

zen-models
45+
Models
1.04T
Max Params
2M
Max Context
From
Language, code, vision, audio, video
Zen MoDE — Mixture of Diverse Experts
One endpoint, one key
Weights published for most of them

Full Model Catalog

45+ models · Available via API and HuggingFace

Browse on HuggingFace
EdgeProMaxUltraVisionMultimodal
zen5
Pro35B3B active1M ctx1m context
zen5-mini
ProTBA10B active1M ctx1m context
zen5-coder
Pro80B3B active1M ctx1m context
zen5-pro
ProTBA1M ctx1m context
zen5-max
ProTBA1M ctx1m context
zen3-omni
Pro30B3B active131K ctx131k context
zen3-vl
Pro8B128K ctx128k context
zen3-guard
Pro5B128K ctx128k context
zen5-embeddingCloud API
ProTBA33K ctx32k context
zen3-embeddingCloud API
ProTBA33K ctx32k context
zen-rerankCloud API
ProTBAcross-encoder rerank
zen-imageCloud API
VisionTBAtext-to-image
zen-voiceCloud API
ProTBAtext-to-speech
zen-musicCloud API
ProTBAtext-to-music
zen-foleyCloud API
ProTBAtext-to-sound-effect
zen-videoCloud API
ProTBAtext-to-video
zen3-nano
Pro8B41K ctx40k context
zen-nano
Pro0.6B41K ctx40k context
zen-eco
Pro4B262K ctx262k context
zen-embedding-8b
Pro8B41K ctx40k context
zen-embedding-4b
Pro4B41K ctx40k context
zen-embedding-0.6b
Pro0.6B33K ctx32k context
zen-reranker-8b
Pro8B41K ctx40k context
zen-reranker-4b
Pro4B41K ctx40k context
zen-reranker-0.6b
Pro0.6B41K ctx40k context
zen3-image
VisionTBAtext-to-image
zen3-tts
Pro1.7B12 hz codec
zen3-asr
Pro1.7B30 languages
zen-musician
Pro7Btext-to-music
zen-agent-4b
Pro4B262K ctx262k context
zen-router
Pro0.6B32K ctxencoder-pooled route
zen-medical
Pro32B41K ctx40k context
zen-legal
Pro32B41K ctx40k context
zen-finance
Pro32B41K ctx40k context
zen-sql
Pro32B41K ctx40k context
zen-translate
Pro32B41K ctx40k context
zen-multilingual
Pro32B41K ctx40k context
zen-world
Pro14Btext-to-video
zen-director
Vision5Btext + image to vide
zen-image-edit
VisionTBAimage editing
zen-3d
VisionTBAimage-to-3d
zen-dub-live
ProTBAlive dubbing
zen-designer-235b-a22b-instruct
Pro235B22B active131K ctx131k context
zen-designer-235b-a22b-thinking
Pro235B22B active131K ctx131k context
zen-designer-gguf
Pro235B22B active131K ctxgguf weights

What you get by using ours

Same request shape

Change the model name in a call you already wrote. Nothing else about the request changes.

Weights you can take

Most Zen models are published on HuggingFace, so you can serve them yourself. A few are API-only; the catalog above marks which.

0.6B to frontier

Small enough to run on a laptop, or large enough to reason. Text, code, vision, audio, image and video, one API.

Sparse where it counts

The Mixture-of-Diverse-Experts models hold a large parameter count but activate a small slice of it per token, so capacity is not what you pay for.

Pick by what you are doing

Different models, one endpoint. The name in the request is the only thing that changes

Language

Chat, reasoning, retrieval

zen5
zen5-pro
zen5-max

Code

A million tokens of it

zen5-coder
zen5-mini
zen-sql

Vision

Read a screen, draw a thing

zen3-vl
zen3-omni
zen3-image

Audio

Listen, speak, compose

zen3-asr
zen3-tts
zen-music
In Training
Next Generation

Zen 5 Ultra

A 2T-parameter MoDE, training now inside NVIDIA TEE confidential compute on hanzo.network. The point of doing it that way is that the run attests to itself: what data went in and what came out is checkable afterwards rather than taken on our word.

2T+
Parameters
MoDE
Mixture of Diverse Experts
TEE
On-Chain Verifiable Training
䷀ ䷸ ䷹ ䷺ ䷻ ䷼ ䷽ ䷾ ䷿ ䷡

Why they are named this way

These models are built on eight engineering principles drawn from the 64 hexagrams of the I-Ching — orthogonality, smallness, completeness, clarity and composability among them. Ancient pattern language for systems that last.

易經 · Explore the Full Philosophy

Call one and see

Start with zen5-mini because it is fast and cheap, and move up only where a harder question needs it.

Read the specs, or read the code

Open source

License: Apache-2.0zenlm/zen

Get Zen Models

Open-weight frontier models