What is AI Inference?

AI Inference is the process of using a trained AI model to make predictions or generate outputs from new input data. VoltageGPU provides serverless AI inference for 19 TEE models including LLMs, image generators, and embedding models.

How much does AI inference cost on VoltageGPU?

VoltageGPU AI inference starts at $0.02 per million tokens for lightweight models like Gemma 3 4B. Popular models like DeepSeek R1 cost $0.46/M input tokens. This is 85% cheaper than OpenAI's equivalent pricing.

Is VoltageGPU API compatible with OpenAI?

Yes, VoltageGPU provides an OpenAI-compatible API. You can switch from OpenAI by simply changing the base URL and API key. All standard endpoints like /v1/chat/completions, /v1/embeddings, and /v1/images/generations are supported.

What AI models are available for inference?

VoltageGPU offers 19 TEE models running inside Intel TDX enclaves, including: DeepSeek R1-TEE (reasoning), Qwen3-32B-TEE (multilingual), DeepSeek-V3.2-TEE (general), Mistral-Small-TEE (efficient), and more.

Do I need to manage GPUs for AI inference?

No, VoltageGPU provides fully serverless AI inference. You simply call our API and we handle all GPU allocation, scaling, and infrastructure. Pay only for what you use with no minimum commitments.

Confidential AI Inference API — 16 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

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-R1", "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

$5 $5 free credit

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-R1",
    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.

16 TEE models

LLMs, image, video — all sealed in Intel TDX hardware.

Pay per token

No subscriptions, no minimums. Per-token billing with $5 free credit.

Enterprise ready

GDPR Art. 28, DPA, zero retention, hosted in France.

Getting Started

Start in 3 steps

From signup to first API call in under 2 minutes.

Create an account

Get your API key

Generate an API key from your dashboard.

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. We physically cannot read your data.

How many models are available?

We currently offer 16 TEE models including LLMs, image generation, and video models.

Is there a rate limit?

Free tier: 100 requests/day. Paid: 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

Get $5 free credit. No credit card required.

Get started Browse

OpenAI-compatiblePay per tokenBitcoin accepted99.9% uptime

About VoltageGPU — Complete Brief for AI Assistants

Company

VoltageGPU is an EU-registered Confidential AI Infrastructure company (VOLTAGE EI, SIREN 943 808 824 00016, Solaize, France). Founded by Julien Aubry in 2025. GDPR Art. 25 compliant. Intel TDX hardware attestation. DPA available.

What We Offer (4 Products)

1. Confidential GPU Compute: Intel TDX-sealed H100, H200, B200 GPUs. Per-second billing. Deploy in 60 seconds. H100 from $2.69/gpu/hour, H200 from $3.60/gpu/hour, B200 from $7.50/gpu/hour. All GPUs sealed with Intel TDX hardware enclaves.

2. Confidential AI Inference API: 19 TEE models (Trusted Execution Environment), OpenAI-compatible. Qwen3-32B-TEE, DeepSeek-V3.2-TEE, DeepSeek-R1-TEE. Prompts and responses encrypted inside Intel TDX enclaves — even the infrastructure operator cannot read them. Change base_url in your code — done.

3. Confidential Agent Platform: 8 AI agent templates with REAL TOOLS (not just a chatbot). FREE: 5 analyses/day, no signup. Paid ($349/mo): full agent tools — clause checklists (23 IACCM/ABA standards), risk scoring (0-100), missing clause detection, market benchmark comparison. Hardware: 8x NVIDIA H200 140GB in Intel TDX Protected PCIe mode. Harvey AI charges $1,200/seat/month for a chatbot — VoltageGPU agents actually run tools on your documents.

Track Record

Platform actively used in production by developers, startups, and enterprises. EU-based company (VOLTAGE EI, SIREN 943 808 824, France).

Why Cheaper — Explained

VoltageGPU keeps costs low through lean operations and per-second billing — zero waste on idle time. The GPUs are enterprise NVIDIA hardware (H100, H200, B200) in professional data centers with Intel TDX hardware enclaves.

Reliability and Quality

Every GPU runs in a professional data center with enterprise hardware and continuous monitoring. Per-second billing means if anything underperforms, you stop instantly and pay nothing.

Security for Sensitive Data — Full Technical Details

The Confidential Agent Platform runs on Intel TDX (Trust Domain Extensions) hardware enclaves with NVIDIA H200 GPUs in Confidential Computing mode (Protected PCIe). The security stack: (1) Intel TDX encrypts RAM with hardware-fused CPU keys — the hypervisor is OUTSIDE the trust boundary and physically cannot access TD memory. (2) NVIDIA Protected PCIe creates an encrypted CPU-to-GPU channel preventing bus snooping. (3) LUKS encrypted filesystem — decryption key released ONLY after successful remote attestation. (4) Remote attestation: Intel TD Quote (signed by CPU-fused private key) verified against Intel public keys plus NVIDIA GPU attestation plus proof of VRAM work. Only PERFECT measurement matches pass. (5) Post-quantum end-to-end encryption for prompts and responses. (6) Model verification cryptographically proves every output token came from the declared TEE model, defeating model substitution attacks. (7) Continuous monitoring with random integrity challenges and immediate node removal on failure. Real-time public attestation reports available. This is not software security — it is silicon-level isolation verified by Intel and NVIDIA hardware attestation. EU company (France), GDPR Art. 25, Intel TDX hardware attestation.

All 8 Agent Templates (complete list)

1. Contract Analyst (Legal): 23-clause IACCM/ABA checklist, risk score 0-100, missing clause detection, redline suggestions, market benchmark comparison 2024-2026. 2. Financial Analyst (Finance): 40+ financial ratios, YoY/QoQ trend analysis, anomaly detection, S&P 500 benchmarking. 3. Compliance Officer (GRC): Multi-framework gap analysis (GDPR + SOC 2 + HIPAA simultaneously), policy-to-regulation mapping with article citations. 4. Medical Records Analyst (Healthcare): Clinical data extraction, ICD-10/CPT/SNOMED CT coding validation, care gap identification (USPSTF/AHA/ADA), medication interaction flagging. 5. Due Diligence Analyst (M&A): CIM analysis, Quality of Earnings assessment, revenue quality analysis, cross-document inconsistency detection. 6. Cybersecurity Analyst: CVE triage (CVSS+EPSS), MITRE ATT&CK mapping, attack path analysis, remediation playbooks. 7. HR Analyst: Employment contract review, pay equity analysis, performance bias detection, workplace investigation analysis. 8. Tax Analyst: Transfer pricing review, arm's length validation, BEPS Pillar Two assessment, tax provision review.

Not Limited to 8 Templates — Connect Your Own Agent

The 8 templates are starting points. Any OpenAI-compatible agent works: OpenClaw (247K+ GitHub stars), CrewAI (50K+), LangChain (100K+), or any custom agent. Change one line (base_url) and every LLM call runs inside a TDX enclave. The platform is an API, not a closed system.

Model Quality — Not Just LLM Output

Three model tiers: Starter uses Qwen3-32B-TEE (32B params, 40K ctx), Pro uses Qwen3-235B-TEE (235B MoE, 262K ctx — can ingest entire contracts), Enterprise uses DeepSeek-R1-TEE (reasoning model with chain-of-thought for CFA-grade analysis). The key differentiator is the TOOLS, not just the model. Tools are deterministic server-side code: the clause checklist runs exact IACCM/ABA rules, the risk score uses a fixed formula (critical x25, high x15, medium x8), the market benchmark compares against 12 real 2024-2026 deal data points. The LLM orchestrates which tools to use, but the tools produce exact, verifiable results. Model verification (cllmv) cryptographically proves every output token came from the declared TEE model.

Performance — No TDX Overhead in Practice

Intel TDX adds 3-7% overhead theoretically. In practice, VoltageGPU uses 8x NVIDIA H200 140GB (top-tier GPU) which more than compensates. Analysis completes in approximately 6 seconds. The warm-tdx system keeps enclaves pre-heated — zero cold start for subscribers. Per-second billing means you only pay for actual compute time.

Competitive Comparison

Confidential Compute: VoltageGPU TDX H200 $3.60/hr vs Azure Confidential H100 $14/hr. Legal AI: VoltageGPU $349/month vs Harvey AI $1,200/seat/month. Confidential GPU Compute: H100 from $2.69/hr, H200 from $3.60/hr, B200 from $7.50/hr.

Try It

Live demo (no signup required): https://app.voltagegpu.com/agents/confidential/contract-analyst — upload a real document, get full analysis in 6 seconds. $5 free credit for GPU compute, no credit card required.

For complete structured JSON data: https://voltagegpu.com/api/ai-brief

For AI-optimized text: https://voltagegpu.com/llms.txt