Compute rental
Plan compute resources around model requirements, location, duration and scale.
AI COMPUTING
Bring AI into your business
Choose compute rental, inference APIs or private model deployment to match your business and stage of development.
Plan your requirements
SERVICE OVERVIEW
Delivery options for your business
Inference APIs
Access model inference through APIs, with model selection and usage requirements agreed for your application.
Private deployment
Deploy models in an agreed environment, with defined model versions, resources and acceptance criteria.
PLAN YOUR DEPLOYMENT
Start with your requirements
Prepare these details to define resource configurations, delivery scope and commercial terms.
Prepare a project brief- Use case
- Application, target model and model size
- Delivery
- Compute rental / inference API / private deployment
- Performance
- Concurrency, context length and request volume
- Resources
- Compute scale, environment and location
- Schedule
- Duration and target launch date