# 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.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.computex.ai/pricing.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.