VoltageGPU is a Confidential AI Infrastructure platform. We provide hardware-sealed GPU pods (Intel TDX, H100 / H200 / B200) and an OpenAI-compatible inference API for confidential TEE LLMs such as DeepSeek-V3.2-TEE, Qwen3-32B-TEE and Qwen3.5-397B-TEE.

Is the VoltageGPU Inference API OpenAI compatible?

Yes. The Inference API is fully OpenAI-compatible. Point any existing OpenAI SDK at https://api.voltagegpu.com/v1 to run prompts against confidential TEE LLMs.

Which models does the Inference API expose?

The Inference API exposes confidential TEE LLMs only: DeepSeek-V3.2-TEE (Enterprise), Qwen3.5-397B-TEE (Plus / Team Starter / Pro) and Qwen3-32B-TEE (Free). All inference runs inside Intel TDX enclaves with hardware attestation.

Documentation

Create Pod

The Create Pod page allows you to configure and deploy a new compute pod with GPU resources. Follow this guide to understand all configuration options.

Pod Configuration

Basic Settings

Pod Name

Default: "Your Pod"
Enter a custom name to identify your pod
Names help you organize multiple pods

Template Selection

The Template Selection section allows you to choose the environment configuration (template) that will be used to create your pod. A template defines the base Docker image, software stack, and environment settings for your GPU container.

How Template Selection Works

Pick one of the curated templates listed on the rent page
Each template pins a Docker image and version
Selecting a template determines the software environment (Python version, CUDA version, pre-installed libraries)

Standard templates

Standard pods start from one of three curated environments:

PyTorch 2.12 · CUDA 13     (default) PyTorch with a built-in Docker daemon
PyTorch 2.11 · CUDA 12.8   for dependencies that need the 12.x toolkit
CUDA 13 (full toolkit)     bare CUDA devel image with nvcc

Only templates published and verified by our provider itself are offered, never one maintained by a third party, so nobody else can change what starts on your pod.

Number of GPUs

A standard machine is rented whole. The price shown is the hourly price of the whole machine, all of its GPUs included, and that is the amount charged per hour. To use fewer GPUs, pick a machine with fewer GPUs.

SSH Access

This section allows you to configure how you will securely connect to your pod using SSH (Secure Shell).

SSH Key Configuration

SSH keys authenticate your access to the pod without needing a password:

Current Selection: Shows the SSH key that will be installed on your pod
Dropdown: Select from your list of previously added SSH keys
Add SSH Key: Upload a new SSH key if needed

Security Note

Only you (or someone with your SSH private key) can access the pod after deployment, providing secure and convenient remote access.

Storage

External Volume Configuration

Volume Selection: Use the "Choose Volume" dropdown to select from available external storage volumes
Add Volume: Click to attach additional external storage volumes to your pod

For more details about how volumes work, see the Volumes documentation.

Restore Options

Restoring a backup at deploy time is turned off for now: a backup id cannot yet be matched to the account that made it, and a deploy that names a backup is refused before anything is charged. Deploy without it.

For more details on restores, see the Restore documentation.

Pod Summary

This section provides an overview of all the key settings and resources you have chosen for your pod before deployment. The summary panel helps you quickly review:

Hardware configuration (CPU, memory, disk, GPU)
Network details
Geographic location
Estimated pricing

Reviewing this summary ensures that your pod will be provisioned exactly as intended and allows you to confirm your selections before finalizing the deployment.

Advanced Options

Agent SSH Key

VoltageGPU automatically adds an agent SSH key to your pod to enable features like the web terminal and to monitor pod health.

Skip agent SSH key: Check this box if you do not want the agent SSH key added

Warning

If you skip the agent SSH key:

The web terminal will be disabled
VoltageGPU cannot check SSH connectivity or monitor your pod
Connection issues cannot be verified or reported to the GPU provider

Recommendation: Keep the agent SSH key enabled unless you have a specific reason to disable it.

Deployment

Once all configurations are set, click the Deploy button to create and start your pod. The pod will be provisioned with the selected hardware, template, and access configurations.

Next Steps After Deployment

Connect to your pod via SSH using your configured key
Access your development environment
Monitor pod performance and costs through the dashboard
Manage volumes and backups as needed

Pro Tip

Make sure your SSH key is properly configured before deployment to ensure secure access to your pod.

Create a standard pod with the API

Everything above can be done with an API key, without the dashboard. The API runs the same deployment as the Deploy button: same price, same prepaid hour, same pod in your account. Send the key in the X-API-Key header; the base URL is https://api.voltagegpu.com. Create a key in the dashboard under API Keys.

1. List the machines you can deploy

curl -H "X-API-Key: $VOLT_API_KEY" \
  "https://api.voltagegpu.com/api/volt/machines?provider=standard"

Each entry has a machine_id, gpu_type, gpu_count, price_per_hour (whole machine, markup included, the amount charged), price_per_gpu_hour, location and available_gpu_count. Only machines whose GPUs are all free are listed.

2. Register an SSH key (once)

curl -X POST https://api.voltagegpu.com/api/volt/ssh-keys \
  -H "X-API-Key: $VOLT_API_KEY" -H "Content-Type: application/json" \
  -d '{"name": "laptop", "public_key": "ssh-ed25519 AAAA... you@laptop"}'

3. Deploy

curl -X POST https://api.voltagegpu.com/api/volt/pods \
  -H "X-API-Key: $VOLT_API_KEY" -H "Content-Type: application/json" \
  -d '{"provider": "standard", "name": "my-pod", "machine_id": "<machine_id>"}'

provider is required: a request without it is refused with 400, it never defaults to the tier without an enclave. Optional fields: template_id (from GET /api/volt/templates?provider=standard, default PyTorch 2.12), ssh_key_id (required only if your account has several keys), jupyter, port_count (1 to 31) and auto_terminate_hours (1 to 720), and, to run your own public image instead of a template, image with an optional start_command, ports and env (see the API reference). The answer is 201 with the pod id and the hourly_price charged.

4. Wait for SSH, then connect

curl -H "X-API-Key: $VOLT_API_KEY" https://api.voltagegpu.com/api/volt/pods/<id>
# repeat every 10 to 15 seconds until "ssh_command" is set, then run it

5. Release

curl -X DELETE -H "X-API-Key: $VOLT_API_KEY" https://api.voltagegpu.com/api/volt/pods/<id>

Billing

Per second, from your prepaid balance. One hour is charged when the deploy succeeds; per-second billing starts after that hour. Releasing within the first hour refunds the unused seconds. A failed deploy is not charged, and a pod that never starts gets the full prepaid hour back. Errors come back as JSON with a plain English error: 402 when the balance is below one hour, 404 or 409 when the machine was taken in the meantime (list again and pick another one).

Full contract, every field and every error: API reference, Standard Pods.

Ready to Create Your Pod?

Browse available GPUs and deploy in under 60 seconds.

Browse Available GPUs View Templates

PreviousPods Overview

NextConfidential Compute