Compute rental
Rent compute resources for your models, with configurations based on location, scale and duration.
AI COMPUTING
AI compute and model services
Compute rental, inference APIs and private model deployment for running models and integrating AI into your applications.
Contact sales
SERVICE OVERVIEW
Choose how to use AI
Inference APIs
Integrate model inference into existing applications through APIs to build AI-powered features.
Private deployment
Deploy models in your chosen environment, with model versions, resources and acceptance criteria agreed for the project.
ENQUIRY CHECKLIST
What to share with us
Share what you know. We can discuss the remaining details together.
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