Models
zen4-thinking
Deep reasoning model with 80B (3B active) MoE + chain-of-thought. 131K context.
zen4-thinking
Deep Reasoning
Dedicated reasoning model with explicit chain-of-thought. Same MoE architecture as zen4-pro with CoT reasoning enabled for step-by-step problem solving.
Specifications
| Property | Value |
|---|---|
| Model ID | zen4-thinking |
| Parameters | 80B (3B active) |
| Architecture | MoE + CoT |
| Context Window | 131K tokens |
| Tier | pro max |
| Input Price | $2.70 / 1M tokens |
| Output Price | $2.70 / 1M tokens |
Capabilities
- Explicit chain-of-thought reasoning
- Mathematical and logical problem solving
- Step-by-step analysis and deduction
- Complex multi-step planning
- 131K 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": "zen4-thinking",
"messages": [{"role": "user", "content": "Solve: If 2^x = 1024, what is x?"}]
}'from hanzoai import Hanzo
client = Hanzo(api_key="hk-your-api-key")
response = client.chat.completions.create(
model="zen4-thinking",
messages=[{"role": "user", "content": "Solve: If 2^x = 1024, what is x?"}],
)
print(response.choices[0].message.content)See Also
- zen4-pro -- Same architecture without thinking mode
- zen4-ultra -- 744B maximum reasoning
- Pricing -- Full pricing table