Models
zen4-coder-pro
Premium 480B full-precision BF16 code model with 262K context.
zen4-coder-pro
Premium Code
Full-precision code model for maximum accuracy. The entire 480B parameter model running in BF16 without MoE sparsity, for the highest code quality on complex codebases.
Specifications
| Property | Value |
|---|---|
| Model ID | zen4-coder-pro |
| Parameters | 480B |
| Architecture | Dense BF16 |
| Context Window | 262K tokens |
| Tier | ultra max |
| Input Price | $4.50 / 1M tokens |
| Output Price | $4.50 / 1M tokens |
Capabilities
- Maximum code accuracy with full BF16 precision
- 262K context for entire repository understanding
- Complex multi-file refactoring and architecture generation
- Difficult debugging and performance optimization
- 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-pro",
"messages": [{"role": "user", "content": "Refactor this codebase to use dependency injection..."}]
}'from hanzoai import Hanzo
client = Hanzo(api_key="hk-your-api-key")
response = client.chat.completions.create(
model="zen4-coder-pro",
messages=[{"role": "user", "content": "Refactor this codebase to use dependency injection..."}],
)
print(response.choices[0].message.content)See Also
- zen4-coder -- MoE variant, lower cost
- zen4-coder-flash -- Fastest code model
- Pricing -- Full pricing table