Billing
This section provides an overview of how billing works for Ori's serverless computing resources, including details on GPU, vCPU, and memory usage costs. Understanding this billing model will help you manage and optimize your resource utilization and associated costs effectively.
Overview of Billing Components
Our serverless platform bills you based on the resources your pods use. Here are the key components of our billing model (refer to the Resource Pricing table below):
- GPU: Each GPU used in your pods is billed at a fixed rate. This includes the associated vCPU and memory that the pod utilizes.
- vCPU: Every vCPU used by your pods is billed. If your pods use CPU resources without a GPU, these are billed separately.
- Memory: Memory usage is billed per MB. This allows for granular control over the memory allocation and cost.
- Load Balancer: Running Load balancer on the cluster.
Billing Rates
- GPU: The billing for GPU usage encompasses the cost of the GPU along with the vCPU and memory resources allocated to it. This is billed per minute of actual usage.
- CPU: CPU usage is billed at 1/100th the cost of a vCPU per minute. This rate applies to all pods.
- Memory: Memory is billed for each MB used per minute. This ensures that you pay only for the memory you actually use.
- Load Balancer: When a load balancer is started on the cluster, this is billed per minute. Only one LB per cluster is the default quota.
Billing Calculation
Billing is calculated per minute, allowing you to scale resources up or down according to your needs without being locked into hourly or daily rates. This per-minute calculation ensures that you are billed only for the time your pods are actively running.
Billing for Suspended/Stopped/Idle Resources
Pods are only billed when they are actively running. If a pod is stopped, suspended, or idle, you will not be charged for those resources during that time. When a cluster is Suspended, all pods are stopped and stop being billed for. The exception to this are load balancers, as the IP address is persisted during the time the cluster is suspended.
Resource Pricing
The following tables outlines the pricing per hour/per minute for:
1. GPU Resources:
| Resource | SKU | Price (minute) | Price (hour) |
|---|---|---|---|
| NVIDIA H100 80GB | ogx-k8s-h100 | 0.069408 | 4.16448 |
| NVIDIA L4 24GB | ogx-k8s-l4 | 0.019044 | 1.14261 |
| NVIDIA L40S 48GB | ogx-k8s-l40s | 0.036000 | 2.16000 |
2. Other Resources:
| Resource | SKU | Price (minute) | Price (hour) |
|---|---|---|---|
| Memory (MB) | ogx-k8s-mem | 0.00000008 | 0.000005 |
| CPU (1/100) | ogx-k8s-vcpu | 0.00000167 | 0.0001 |
| Load Balancer | ogx-k8s-lb | 0.0003015 | 0.01809 |
Support and Contact Information
For any billing issues or queries, please do not hesitate to contact our support team at support@ori.co. Our team is available to help resolve any concerns and provide further clarification on your billing invoices.