Hanzo Zen Models
Language · Code · Vision · Audio
41+ open-weight models from 0.6B to 1T+. Zen MoDE (Mixture of Distilled Experts) architecture. All models on HuggingFace.
Full Model Catalog
41+ models · Available via API and HuggingFace
Why Zen Models?
OpenAI-Compatible API
Drop-in replacement for GPT/Claude. Same SDK, same format, lower cost.
Open Weight
All Zen models are open-weight on HuggingFace. Run them yourself.
Full Spectrum
82M edge to 1T+ frontier. Text, code, vision, audio, image — one API.
MoE Efficiency
Mixture-of-Experts activates only a fraction of params per token.
Every Modality
Text, vision, code, speech — all through a single unified API
Language
Chat, reasoning, RAG
Code
Generation, review, debug
Vision
Image, video, OCR
Audio
Speech-to-speech <300ms
Zen 5 Ultra
2T+ parameter MoDE. Trained on-chain via NVIDIA TEE confidential compute on hanzo.network. The largest open-weight model in history.
The Philosophy Behind the Models
These models are built on ten engineering principles drawn from the 64 hexagrams of the I-Ching. Orthogonality. Smallness. Completeness. Clarity. Composability. Ancient pattern language for systems that last.
易經 · Explore the Full PhilosophyReady to build with Zen?
41+ models, full spectrum of modalities, one API. Start building today.