Pricing

At CX, we offer two flexible pricing strategies to give you the best value for your investment.

Choose from our Always-on Deployments for constant, reliable performance, or opt for our flexible Serverless Deployments to scale with your dynamic requirements.

Always-on Deployments: Fastest Processing

Leverage fully configurable GPU Servers at a fraction of the cost.

GPU Model	VRAM (GB)	Max vCPUs	Max RAM (GB)	GPU Cost Per Hour	GPU Cost Per Second
NVIDIA H100 PCIe	80	48	256	$4.68	$0.07792
A100 80GB NVLINK	80	48	256	$2.54	$0.04236
A100 80GB PCIe	80	48	256	$2.54	$0.04236
A100 40GB NVLINK	40	48	256	$2.47	$0.04120
A100 40GB PCIe	40	48	256	$2.47	$0.04120
A40	48	48	256	$1.66	$0.02773
RTX A6000	48	48	256	$1.66	$0.02773
RTX A5000	24	36	128	$1.00	$0.01668
RTX A4000	16	36	128	$0.79	$0.01322
Quadro RTX 5000	16	36	128	$0.74	$0.01235
Quadro RTX 4000	8	36	128	$0.31	$0.00520
Tesla V100 NVLINK	16	36	128	$1.04	$0.01733

Cost per vCPU: $0.02 per hour (0.000333 per second)

Cost per GB RAM: $0.01 per hour (0.000166 per second)

Serverless Deployments: Pay Per Request

For those with fluctuating requirements, Serverless is the most cost effective approach. Pay only for request execution time.

Benchmark your model and receive a personalized quote per inference.

Storage Pricing

CX offers NVMe storage for all AI models for the fastest inference processing times. Each deployment benefits from a dedicated storage volume.

Storage Cost Details: Each model hosted on CX accrues a monthly storage cost of $8.10.