Deploy Application
Select Application
All Models
LLM
Image
Audio
Video
No Data
Select Deploy Type
Instance
Dedicated GPU instance with full control. Best for long-running workloads.
SSH access
Persistent storage
Pay per hour
Serverless
Coming soon
Auto-scaling GPU endpoints. Best for API services with variable traffic.
Auto-scaling
No idle costs
Pay per request
Serverless
Coming soon
Your serverless application is launching soon.
Go toDeploy Serverlessto view and manage it.
Currently selected
Based on the current selection, a random selection has been made for you to an available
Commitment
--/hr
