GPU cloud
RunPod
A container-oriented GPU Pod API suited to experiments, inference workers, and direct GPU selection.
- API
- REST Pods API · POST /v1/pods
- Auth
- Bearer API token
Source-linked API research · Reviewed August 2, 2026
Know the control plane before choosing the GPU.
Each entry links to official provisioning documentation and summarizes credentials, lifecycle operations, and responsibilities. Run Any AI has no provider integration and does not rank these services.
GPU cloud
Lambda Cloud
A focused REST API for launching and managing GPU instances, images, SSH keys, filesystems, and firewalls.
- API
- Lambda Cloud REST API · instance-operations/launch
- Auth
- Bearer API key
Hyperscaler
AWS EC2
A broad infrastructure API with GPU instance families, networking, IAM, storage, Spot, and mature lifecycle controls.
- API
- EC2 Query API · RunInstances
- Auth
- IAM credentials with Signature Version 4
Hyperscaler
Google Compute Engine
A REST and client-library surface for creating VMs with attached accelerators, IAM, networks, disks, and reservations.
- API
- Compute Engine REST API · instances.insert
- Auth
- OAuth access token through IAM or workload identity
Hyperscaler
Azure Virtual Machines
An Azure Resource Manager API for creating GPU VMs within subscriptions, resource groups, networks, and identity controls.
- API
- Azure Compute REST API · Virtual Machines Create or Update
- Auth
- Microsoft Entra OAuth through a managed identity or service principal
AI infrastructure
CoreWeave
A Kubernetes-first AI cloud whose CKS API creates and manages clusters before GPU node pools and workloads are attached.
- API
- CKS REST API · POST /v1beta1/cks/clusters
- Auth
- Bearer API access token