Zen LM by Hanzo AI -- 14 frontier models for code, reasoning, vision, multimodal, embeddings, and safety

Zen LM

Zen LM by Hanzo AI is a frontier model family of 14 specialized models spanning code, reasoning, vision, multimodal, embeddings, and safety. From the 4B zen3-nano for edge deployment to the 1T+ zen4-max for frontier-scale reasoning, Zen MoDE (Mixture of Distilled Experts) delivers state-of-the-art performance across every major AI task.

Model Lineup

Zen4 Generation

9 models -- flagship, reasoning, and code. From 8B zen4-mini to ~400B zen4-ultra.

Zen3 Generation

5 models -- multimodal, vision, edge, safety, and embeddings.

API Reference

OpenAI-compatible API at api.hanzo.ai with all 14 models.

Pricing

Transparent pricing at 3x upstream inference cost. From $0.30/MTok.

Quick Start

API (OpenAI-compatible)

from openai import OpenAI

client = OpenAI(
    base_url="https://api.hanzo.ai/v1",
    api_key="hk-your-api-key",
)

response = client.chat.completions.create(
    model="zen4",
    messages=[{"role": "user", "content": "Hello, who are you?"}],
)
print(response.choices[0].message.content)

curl

curl https://api.hanzo.ai/v1/chat/completions \
  -H "Authorization: Bearer hk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{"model": "zen4", "messages": [{"role": "user", "content": "Hello, Zen."}]}'

Key Facts

14 models covering all major AI tasks
OpenAI-compatible API -- works with every SDK that supports the OpenAI format
Zen MoDE (Mixture of Distilled Experts) architecture
Transparent pricing from $0.30/MTok
API key prefix: hk-
Endpoints: api.hanzo.ai/v1 and api.zen.hanzo.ai/v1

All 14 Models

Model	Type	Architecture	Input $/1M	Output $/1M
zen4	Flagship	~400B Dense	$3.00	$9.60
zen4-ultra	Max Reasoning	~400B Dense + CoT	$3.00	$9.60
zen4-pro	High Capability	80B (3B active) MoE	$2.70	$2.70
zen4-max	Frontier Scale	1.04T (32B active) MoE	$3.60	$3.60
zen4-mini	Fast & Efficient	8B Dense	$0.60	$0.60
zen4-thinking	Deep Reasoning	80B (3B active) MoE + CoT	$2.70	$2.70
zen4-coder	Code Generation	480B (35B active) MoE	$3.60	$3.60
zen4-coder-pro	Premium Code	480B Dense BF16	$4.50	$4.50
zen4-coder-flash	Fast Code	Dense	$1.50	$1.50
zen3-omni	Hypermodal	~200B Dense Multimodal	$1.80	$6.60
zen3-vl	Vision-Language	30B (3B active) MoE VL	$0.45	$1.80
zen3-nano	Edge	4B Dense	$0.30	$0.30
zen3-guard	Content Safety	4B Dense	$0.30	$0.30
zen3-embedding	Text Embeddings	Embedding (3072 dim)	$0.39	$0.39

Introduction