CLI Generator
×
Model ID (Fuzzy Search)
Model Information
Instance Type
Select instance type...
Engine Type
Select engine type...
Service Type
SageMaker Realtime
SageMaker Async
ECS
Local
Model Tag
Extra Parameters
📦 Model Parameters
Model S3 Path
Download Source
Auto (default)
Hugging Face
ModelScope
Hugging Face Model ID
ModelScope Model ID
Skip model preparation (reduces deployment time)
🔧 Service Parameters
API Key
Max Capacity
Min Capacity
Auto Scaling Target
Custom Endpoint Name
VPC ID
Subnet IDs
Desired Capacity
Max Size
VPC ID
Subnet IDs
Use Spot Instances (cost optimization)
⚙️ Engine Parameters
Environment Variables
Max Model Length
Max Number of Sequences
GPU Memory Utilization
Tool Call Parser
None
Hermes
Pythonic
Reasoning Parser
None
DeepSeek R1
Granite
Chat Template Path
Disable log statistics
Enable automatic tool choice
Enable reasoning capabilities
Max Total Tokens
Max Concurrent Requests
Max Batch Size
Max Input Tokens
🌐 Framework Parameters
Limit Concurrency
Timeout Keep Alive
Uvicorn Log Level
Default
Debug
Info
Warning
Error
Critical
🔧 General Options
Skip confirmation prompts (--skip-confirm)
Select a model from the table to generate deployment command
Background
Click any model to open CLI generator
Loading models...
Model ID
Type
Description
Instances
Engines
Services
China
Loading models...
Commands copied to clipboard!