Models
zen4-coder-flash
Fast 30B (3B active) MoE code model with 262K context.
zen4-coder-flash
Fast Code
Lightweight code model optimized for speed and inline completions. 30B total parameters with only 3B active per token for ultra-fast code generation.
Specifications
| Property | Value |
|---|---|
| Model ID | zen4-coder-flash |
| Parameters | 30B (3B active) |
| Architecture | MoE |
| Context Window | 262K tokens |
| Tier | pro max |
| Input Price | $1.50 / 1M tokens |
| Output Price | $1.50 / 1M tokens |
Capabilities
- Fast code generation for rapid iteration
- 262K context for codebase-level understanding
- Inline completions and code review
- Efficient MoE inference with only 3B active parameters
- All major programming languages
API Usage
curl https://api.hanzo.ai/v1/chat/completions \
-H "Authorization: Bearer $HANZO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "zen4-coder-flash",
"messages": [{"role": "user", "content": "Write a Python function for binary search."}]
}'from hanzoai import Hanzo
client = Hanzo(api_key="hk-your-api-key")
response = client.chat.completions.create(
model="zen4-coder-flash",
messages=[{"role": "user", "content": "Write a Python function for binary search."}],
)
print(response.choices[0].message.content)See Also
- zen4-coder -- Larger 480B MoE code model
- zen4-coder-pro -- Full BF16 precision
- Pricing -- Full pricing table