⚡ Zen LM
Models

zen3-nano

Ultra-lightweight 4B dense model for edge deployment. 40K context.

zen3-nano

Edge

Ultra-lightweight model for edge deployment and low-latency tasks. 4B dense transformer -- the smallest model in the Zen lineup.

Specifications

PropertyValue
Model IDzen3-nano
Parameters4B
ArchitectureDense
Context Window40K tokens
Tierpro
Input Price$0.30 / 1M tokens
Output Price$0.30 / 1M tokens

Capabilities

  • Ultra-low latency inference
  • Edge and IoT deployment
  • Mobile applications
  • High-volume classification tasks
  • Basic chat and instruction following
  • 40K context window

API Usage

curl https://api.hanzo.ai/v1/chat/completions \
  -H "Authorization: Bearer $HANZO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zen3-nano",
    "messages": [{"role": "user", "content": "Classify this text as positive or negative: Great product!"}]
  }'
from hanzoai import Hanzo

client = Hanzo(api_key="hk-your-api-key")

response = client.chat.completions.create(
    model="zen3-nano",
    messages=[{"role": "user", "content": "Classify this text as positive or negative: Great product!"}],
)
print(response.choices[0].message.content)

See Also

zen3-guard

Content safety classifier with 4B dense architecture. 40K context.

zen3-omni

Hypermodal ~200B dense model supporting text, vision, and audio. 202K context.

On this page

zen3-nanoSpecificationsCapabilitiesAPI UsageSee Also