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 14 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 14 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, 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

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

$5 $5 referral 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-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 with $5 referral credit.

Enterprise ready

GDPR Art. 28, DPA, no prompt/output retention by design, 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. 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?

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

$5 referral credit available. No credit card required.

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 $5.00/gpu/hour and H200 from $6.58/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.