# How to deploy a GPU Container

1. Navigate to the **"Deploy GPU Container"** button(located on upper right in screenshot below) under **GPU Container** page.

<figure><img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXfG4gnteqWNaLD6OQDztE6OWS-P8z5zWcL0D0TA7SLphu35Ss_sLaYNmxuCyKs1Bor7JuoYPQuyKkS-o4wTbt7uoZkvXuAPjcdR5FkYQaJDZsTvxWVQ9SR97SiiSopFVwH5iPD0Ffr73YVtB_hbpDdxWd0?key=UbI8YI3-VF8UhldN54mDkg" alt=""><figcaption></figcaption></figure>

2. **Package Details:** Review the specifications of GPU container such as GPU cores, CPU cores, and memory before deployment.

<figure><img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXcB9fVEPjGXm6-KN9SrbaOXHehVC0-OwzLRnGekbqxemRK027w3BIUiZAovRgDrG9GYsjGnbHiepuvG2p6222R3I43F3Q-beXOjtINS6ZJJvRc3RYzD77xoW0pma8nSqlLILjZERY1-KoYuVfhU2RngV70?key=UbI8YI3-VF8UhldN54mDkg" alt=""><figcaption></figcaption></figure>

3. Customize your deployment by configuring environment variables, exposed ports, and other necessary parameters.

<figure><img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXe3PeVxfx6bKswtpCBDAeILb3olqy31cDUKz5mgUhgPYMQybvmR3-WWpbY-PQuoswHQpypjFIZO_Fdt0fVwrIarsOuulfe6I5ifDc9O9DGxatBm-q6iLFPwdCyPyAC_c3jIPoCGvnbfIsm34ak2wJ1RkE_Y?key=UbI8YI3-VF8UhldN54mDkg" alt=""><figcaption></figcaption></figure>

4. Choose GPU container instance pricing according to your needs. Kaisar offers various pricing models such as on-demand, 1 month, 3 months, 6 months, 12 months, and 24 months with corresponding hourly rates and total costs for reservation.&#x20;

&#x20; *See screenshot below for reference.*

<figure><img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXfvxmLKuotu5r9ysoyLPhe7WnWm0QfuxQgMgLAxFqvlmLLY4ykxS7aO1ZRpDEjVh2RajYXptMp0WgPCaF2-0pkXBiGT1J2fDvgdRc74SgagSaQWBUd5PRn1q5hUb-p0gjDjc6uvUKEZyY6QQ6dH17jmXpo?key=UbI8YI3-VF8UhldN54mDkg" alt=""><figcaption></figcaption></figure>

5. Check all configurations before finalizing the deployment. Ensure all details are correct and meet your requirements:

   **Container Summary:** Provides a summary of the selected GPU instance, including GPU model, VRAM, RAM, vCPU, connectivity speed, and location.\
   \
   **Order Summary:** Shows the total cost for GPU on-demand usage and cloud services fee.\
   \
   **Payment Method:** Options to pay with USDT or credit card (coming soon).\
   \
   **Proceed to Payment Button:** To finalize and proceed with the payment.\
   \
   \&#xNAN;*See Screenshot below for reference.*

<figure><img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXcPfvF8GGItpBEzIr1NfJFq3G8gaiEdF8f-NIMToD0NUge47ux_RXvB3Tbq47P6oOz3JG-CHbhBM_ZfGcXWaYYfp6HLfDtKxkSNOqPnDTfFj5rhjcfS6L2UekBdIXPqYdw5NFDRW-Ydl8w3BxqN9Hg5z9QU?key=UbI8YI3-VF8UhldN54mDkg" alt=""><figcaption></figcaption></figure>

6. After deployment, monitor the container details, including CPU, memory, network traffic, logs, status, uptime, and logs.

<figure><img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXdFEZ_69xOBM9-Pfi_q4AhXN8-Qw-hThlIJFOlFRFC55GChoE95PM3rI2aZTqA2QhyPlUNtzRJAP_WTBfTWLqRC4qp9aZPtxf5g-kbAVoJFRvM_lNgkOnGuDALCeiFXKRW6LROlKQXMvv6eejqrFIN4nzc?key=UbI8YI3-VF8UhldN54mDkg" alt=""><figcaption></figcaption></figure>

7. Click on the **"Connect"** button to view access details for the container.

<figure><img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXfpxjgR7B6AxaBUh2pVdIITQ1-bp-T_0Qf5t5m89jz2KchUadLzDBzxkyNOSiTDPuaR69Ek5b-R2EhDkjpmnkPL5jnuXEHaV75NfwtaPGT_9yFabeq575WUgtgJhMSmpFhkXDB_V8ys54bdqF4l8MQKSMTT?key=UbI8YI3-VF8UhldN54mDkg" alt=""><figcaption></figcaption></figure>

8. Now access the GPU container using the provided credentials and run AI workflows.

<figure><img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXdchIR4fZjnzfMbQr2HqXOpGiHJg6_vQKIMZWZHg06KIovEyjr4YTYLa-jW2IquVsWY54MYmvP2VDyo_qE3cCUxNEu-OQf68h39JKs2yWmbLOzeqYKhuq7iaiFW4boyeQmYZd4fuJZ4tl5-5hfK2a1JUagm?key=UbI8YI3-VF8UhldN54mDkg" alt=""><figcaption></figcaption></figure>


---

# 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.kaisar.io/kaisar-network/kaisar-architecture/products/kaisar-cloud-end-users/how-to-deploy-a-gpu-container.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.