Getting Started
Get up and running with VoltageGPU in under 5 minutes.
Create an Account
Sign up at voltagegpu.com/register. Get $5 referral credit instantly.
Get Your API Key
Go to voltagegpu.com/api-keys and click Generate New Key.
Save your key securely -- you will not be able to see it again after creation.
Deploy a Confidential Pod
~60 seconds
List confidential inventory
curl https://api.voltagegpu.com/api/volt/machines \ -H "X-API-Key: YOUR_KEY"
Returns Intel TDX tiers only, non-confidential hardware is filtered out server-side. Grab a resource_name (e.g. h200-small).
Pick a resource and deploy
curl -X POST https://api.voltagegpu.com/api/volt/pods \
-H "X-API-Key: YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"provider": "confidential",
"name": "my-first-vm",
"resource_name": "rtx6000b-small"
}'This boots a full Confidential VM (Ubuntu 24.04, NVIDIA driver and CUDA preinstalled, 320 GB encrypted disk on single-GPU tiers). Pricing is resolved server-side and the 1h upfront charge is debited atomically, no client-side cost_per_hour needed. Confidential container tiers were retired by our provider in October 2026.
Connect via SSH
The VM is ready in about two minutes. Poll the list until ssh_ready is true, then run the ssh_command it returns.
curl https://api.voltagegpu.com/api/volt/pods -H "X-API-Key: YOUR_KEY" # then, with the ssh_user / ssh_host / ssh_port it returns: ssh -p SSH_PORT ubuntu@SSH_HOST
Release when done
Stop = destroy for confidential VMs: billing ends immediately and the VM disk is erased, so copy out anything you want to keep first.
curl -X POST https://api.voltagegpu.com/api/volt/pods/POD_ID/stop \ -H "X-API-Key: YOUR_KEY"
Make Your First API Call
~30 seconds
Chat completion (OpenAI-compatible)
curl https://api.voltagegpu.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "Qwen/Qwen3-32B-TEE",
"messages": [
{"role": "user", "content": "Hello!"}
]
}'Python
pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://api.voltagegpu.com/v1",
api_key="YOUR_KEY"
)
response = client.chat.completions.create(
model="Qwen/Qwen3-32B-TEE",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)JavaScript
const response = await fetch(
"https://api.voltagegpu.com/v1/chat/completions",
{
method: "POST",
headers: {
"Authorization": "Bearer YOUR_KEY",
"Content-Type": "application/json"
},
body: JSON.stringify({
model: "Qwen/Qwen3-32B-TEE",
messages: [
{ role: "user", content: "Hello!" }
]
})
}
);
const data = await response.json();
console.log(data.choices[0].message.content);