VoltageGPUDocsConsole
Documentation

VoltageGPU Documentation

Confidential AI Infrastructure.
Deploy hardware-sealed Intel TDX GPU pods and run confidential LLM inference, all via REST API.

Base URL: https://api.voltagegpu.com
QuickstartQuickstart: your first Confidential VM in 5 minutesCreate an account, get your API key, deploy a Confidential VM and make your first API call.Start the quickstart

Deploy a Confidential VM

Hardware-sealed Intel TDX VMs with the GPU inside the trust domain. Encrypted memory, hardware attestation.

Standard GPUs

GPU pods with SSH access and per-second billing. No enclave, for data that is not sensitive.

API reference

Every endpoint, parameter, and response documented.

CLI

Manage confidential pods and inference from your terminal.

Inference API

OpenAI-compatible API for TEE LLMs running in Intel TDX enclaves.

Verify an attestation

Check the attestation proof of a Confidential VM yourself.

Quick Start

Deploy a Confidential Pod

curl https://api.voltagegpu.com/api/volt/machines      # Browse TDX GPUs
curl -X POST .../api/volt/pods -H "X-API-Key: ..."    # Deploy (TDX-sealed)
ssh root@<pod-ip>                                      # Connect
Full tutorial →

Run Confidential Inference

curl https://api.voltagegpu.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_KEY" \
  -d '{"model":"Qwen/Qwen3-32B-TEE","messages":[...]}'
Full tutorial →

Authentication

VoltageGPU uses two API styles depending on the product:

Volt API Confidential Pods, SSH Keys

X-API-Key: YOUR_KEY

Inference API TEE Chat Completions

Authorization: Bearer YOUR_KEY

API Overview

APIBaseEndpointsAuth
Volt (Confidential Infrastructure)/api/volt/*Confidential pods, SSH keys, templates, volumesX-API-Key
Inference (OpenAI-compat)/v1/*TEE chat completions + models listBearer
Full API Reference →

Help and community