Models
zen4.1
High-performance 1M context model for long-document analysis, large codebase reasoning, and agentic workflows. Best balance of intelligence and cost at million-token scale.
zen4.1
Million-Token Context
High-performance model optimized for long-document analysis, large codebase reasoning, and agentic workflows. Best balance of intelligence and cost at million-token scale.
Specifications
| Property | Value |
|---|---|
| Model ID | zen4.1 |
| Architecture | Dense |
| Context Window | 1M tokens |
| Tier | ultra |
| Status | Available |
Capabilities
- 1M token context window for entire codebase ingestion
- Long-document analysis and summarization
- Agentic workflows with extended reasoning chains
- Large-scale retrieval augmented generation
- Multi-step planning over very large contexts
API Usage
curl https://api.hanzo.ai/v1/chat/completions \
-H "Authorization: Bearer $HANZO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "zen4.1",
"messages": [{"role": "user", "content": "Analyze this entire codebase..."}]
}'from hanzoai import Hanzo
client = Hanzo(api_key="hk-your-api-key")
response = client.chat.completions.create(
model="zen4.1",
messages=[{"role": "user", "content": "Analyze this entire codebase..."}],
)
print(response.choices[0].message.content)Try It
Resources
See Also
- zen4 -- Flagship dense model
- zen4-ultra -- Maximum reasoning
- Pricing -- Full pricing table