Drop-in OpenAI replacement where every LLM call runs inside Intel TDX hardware enclaves. Full TEE catalog from $0.15/M input tokens. Python, Node.js, Go SDKs. $3.80 bonus on your first top-up of $10 or more (one free GPU hour). Change one line of code, the base URL, and your users data is hardware-sealed. French company, GDPR Art. 28, DPA included, 99.99% uptime, no vendor lock-in.
Drop-in OpenAI replacement where every LLM call runs inside Intel TDX hardware enclaves. TEE models from $0.15/M input tokens. Change the base URL: your users' data is hardware-sealed.
Your users' data deserves better than a privacy policy
Standard AI APIs see everything you send. Self-hosting costs a fortune. You need a third option.
Standard APIs expose data
OpenAI, Anthropic, and Google see every prompt and response. One subpoena, one breach, and your users' data is exposed. A policy promise is not a hardware guarantee.
Self-hosting is a money pit
Running your own GPU cluster means $15K+/month, a DevOps team, and months of setup. Most startups can't justify the cost or the distraction.
Compliance is a moving target
GDPR, HIPAA, SOC 2: regulators want proof of data protection, not promises. Hardware attestation is the only answer that satisfies auditors.
Integration
Change one line. Ship confidential AI.
Same OpenAI SDK, same code, same workflow. Replace the base URL and your data is hardware-encrypted. Python, Node.js, curl, works everywhere.
from openai import OpenAI
client = OpenAI(
base_url="https://api.voltagegpu.com/v1", # <-- only change
api_key="your-voltagegpu-key"
)
response = client.chat.completions.create(
model="Qwen/Qwen3-32B-TEE",
messages=[{"role": "user", "content": "Analyze this contract..."}]
)
print(response.choices[0].message.content)
Models
TEE models, from $0.15/M tokens
Every model runs inside Intel TDX enclaves with AES memory encryption and trust-domain GPU isolation. No fallback to unencrypted infrastructure, ever.
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 (14 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.