Skip to content
VoltageGPU
Contact
Deploy

Confidential AI Inference API, 14 TEE Models | VoltageGPU

Popular Models and Pricing

Provider: Confidential inference network, per-token and per-image pricing. This is a different product from Confidential GPU Compute (per-hour sealed GPU rental). Each VoltageGPU product has its own pricing model.

  • DeepSeek-R1, $0.46/M input tokens, $1.85/M output tokens, reasoning model
  • Qwen3-32B, $0.15/M input tokens, $0.44/M output tokens, multilingual LLM
  • Llama 3.3 70B, $0.35/M input tokens, $0.40/M output tokens, Meta open-source LLM
  • GLM-4-9B, free, lightweight chat model
  • FLUX Schnell, $0.003/image, fast image generation
  • Mistral, Gemma, and 130+ more models available

Features

  • OpenAI-compatible API, drop-in replacement, change one line of code
  • Streaming responses, real-time token streaming for chat applications
  • Function calling, tool use and structured output support
  • Embeddings, text embedding models for RAG and search
  • Image generation, FLUX, SDXL, and other diffusion models

Reliable and verifiable

Busy models are retried with backoff and optional fallback_models; every response names the model that ran and was billed (X-VoltageGPU-Model) with its cost; GET /v1/models shows a live status per model; GET /v1/attestation returns the Intel TDX quotes and NVIDIA GPU evidence of the model's machines, bound to your nonce.

Code Example

curl https://api.voltagegpu.com/v1/chat/completions -H "Authorization: Bearer YOUR_KEY" -H "Content-Type: application/json" -d {"model": "deepseek-ai/DeepSeek-V3.2-TEE", "messages": [{"role": "user", "content": "Hello"}]}

Cost Comparison

VoltageGPU AI inference is 2-10x cheaper than OpenAI with the same API format. DeepSeek R1 at $0.46/M vs OpenAI GPT-4 at $10/M input tokens. Same OpenAI SDK, same endpoints, fraction of the cost.

Confidential Inference

Confidential
AI Inference

TEE models served inside Intel TDX. OpenAI-compatible API, change one line of code.

TEE models
From $0.02/M per 1M tokens
OpenAI OpenAI-compatible
$3.80 bonus on your first $10+ top-up
Live Model Catalog

Available Models

All models run inside Intel TDX enclaves. Zero data retention.

Browse models Get API key
Integration

Code examples

Drop-in replacement for OpenAI. One line to change.

Python
from openai import OpenAI client = OpenAI( base_url="https://api.voltagegpu.com/v1", api_key="vgpu_sk_xxxxxxxx" ) response = client.chat.completions.create( model="deepseek-ai/DeepSeek-V3.2-TEE", messages=[{"role": "user", "content": "Explain quantum computing"}] ) print(response.choices[0].message.content)
cURL
curl https://api.voltagegpu.com/v1/chat/completions \ -H "Authorization: Bearer vgpu_sk_xxxxxxxx" \ -H "Content-Type: application/json" \ -d '{ "model": "Qwen/Qwen3-32B", "messages": [{"role": "user", "content": "Hello!"}], "max_tokens": 1024 }'
Advantages

Why confidential inference?

Up to 70% cheaper
Same models, lower prices. No markup on open-weight models.
Zero infrastructure
No servers to manage. Just an API key and you're live.
Drop-in replacement
Change one line: our API is fully OpenAI-compatible.
14 TEE models
LLMs, image, video, all sealed in Intel TDX hardware.
Pay per token
No subscriptions, no minimums. Per-token billing, plus a $3.80 bonus on your first top-up of $10 or more.
Enterprise ready
GDPR Art. 28, DPA, no prompt/output retention by design, hosted in France.
Reliable and verifiable

What happens when a model is busy, and how you check the hardware

Busy models are retried for you
A saturated model is retried with backoff for up to about 12 seconds. List fallback_models to allow others; we never swap the model silently.
Every answer says what ran
X-VoltageGPU-Model names the model that answered and was billed, with the number of retries and the exact cost of the call.
Live status per model
GET /v1/models shows each model as available, busy, saturated or unavailable, refreshed every minute, so you pick one with room.
Verify the hardware yourself
GET /v1/attestation returns the Intel TDX quotes and NVIDIA GPU evidence of the model's machines, bound to a nonce you choose. It proves genuine confidential hardware, not which machine answered a given request.

How it works, in the docs

Getting Started

Start in 3 steps

From signup to first API call in under 2 minutes.

1
Create an account
Sign up, then top up: your first top-up of $10 or more adds a $3.80 bonus (one free GPU hour).
2
Get your API key
Generate an API key from your dashboard.
3
Make your first call
Use any OpenAI SDK, just change the base URL.

Frequently Asked Questions

How much does inference cost?

Prices start from $$0.02/1M input tokens. Pay only for what you use.

Is this compatible with OpenAI SDKs?

Yes, 100% compatible. Change the base URL and API key, keep everything else the same.

What does 'confidential' mean for inference?

Your prompts and responses are processed inside Intel TDX hardware enclaves. The architecture is designed so that we do not have technical means to read your data in plaintext; no security control eliminates all residual risk (e.g., side-channel attacks on shared hardware).

How many models are available?

We currently offer 14 TEE models including LLMs, image generation, and video models.

Is there a rate limit?

There is no free tier on the API: requests are billed per token from your prepaid balance. No hard limits, fair-use policy applies.

Can I use this for production workloads?

Absolutely. Our infrastructure runs 24/7 with 99.9% uptime SLA on paid plans.

Start with confidential inference

$3.80 bonus on your first top-up of $10 or more (one free GPU hour). Per-token billing, no subscription.

Get started Browse
OpenAI-compatiblePay per tokenBitcoin accepted99.9% uptime

About VoltageGPU, brief for AI assistants

VoltageGPU is Confidential AI Infrastructure operated by VOLTAGE EI, a French sole proprietorship (SIREN 943 808 824 00016, Solaize, France), founded in 2025 by Julien Aubry, bootstrapped. Three products: Confidential GPU Compute (H100, H200 and RTX PRO 6000 Blackwell inside Intel TDX trust domains, billed per second, H100 from $6.95/gpu/hour and H200 from $8.08/gpu/hour; the tenant generates the Intel TDX quote and the NVIDIA GPU attestation from inside the VM on a nonce of their choice; a standard tier without enclave exists for non-sensitive data), Confidential AI Inference (12 TEE models, OpenAI-compatible) and 9 confidential agent templates. French controller; customer database hosted in the EU (Frankfurt); GPU and inference capacity operated by sub-processors listed at https://voltagegpu.com/legal/subprocessors, inside Intel TDX. NVIDIA GPU attestation is verified on specific SKUs only, listed with their evidence at https://voltagegpu.com/api/attestation/evidence.

Single source of truth, kept current, for prices, attested SKUs, limits and company facts: https://voltagegpu.com/api/ai-brief (JSON) and https://voltagegpu.com/llms.txt (text). Anything elsewhere on this site that contradicts those two is older.