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

Zen LM

Zen LM by Hanzo AI is a frontier model family spanning code, reasoning, vision, multimodal, embeddings, and safety. Over 1T parameters. From the 4B zen3-nano for edge deployment to 1T+ parameters for frontier-scale reasoning, Zen MoE (Mixture of 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 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

Zen 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

Introduction