Privacy has always been core to PayPerQ. We store your conversations locally by default, account are optional, and anonymous crypto payments are preferred. Today, we're taking privacy even further with Trusted Execution Environment (TEE) models — AI inference where your prompts and responses are encrypted end-to-end, and not even PayPerQ or its AI provider can see what you're asking.

What Are TEE Models?

TEE models run inside secure hardware enclaves — isolated environments on NVIDIA confidential computing GPUs where data is encrypted during processing, not just in transit. When you use a TEE model on PayPerQ, your query is encrypted in your browser before it ever leaves your device. It stays encrypted through our servers and is only decrypted inside the secure enclave where the AI model runs. The response follows the same path back.

This means:

• PayPerQ never sees your prompts or responses — we physically cannot access them
• No one between you and the enclave can read your data — not us, not your ISP, not any intermediary
• The enclave's integrity is cryptographically verified — you can confirm exactly what code is running

How It Works

The encryption is powered by Tinfoil, which runs AI models inside NVIDIA confidential computing GPUs using a protocol called EHBP (Encrypted HTTP Body Protocol). Here's what happens when you send a message:

1. Browser-side encryption — The Tinfoil SDK encrypts your prompt in the browser using hybrid public key encryption (HPKE)
2. Secure transit — The encrypted payload passes through PayPerQ's servers, but we can only see routing metadata — never the content
3. Enclave processing — Your message is decrypted only inside the hardware-attested secure enclave where the model runs
4. Encrypted response — The model's response is encrypted inside the enclave and sent back to your browser for decryption

Every session includes cryptographic attestation — a mathematical proof that the enclave is running the exact code it claims to be running, on genuine secure hardware.

Verification Badge

When using a TEE model, you'll see a shield icon next to the model name. Hover over it to view the enclave verification status, including:

• Enclave host — which secure environment is processing your request
• Code fingerprint — a hash of the exact code running in the enclave
• Enclave fingerprint — a hash of the enclave's configuration
• Source code link — view the open-source enclave code on GitHub

Available TEE Models

We're launching with five models covering a range of capabilities:

Model	Parameters	Context Window	Strengths
Kimi K2.5	—	262K	Native multimodal, strong coding
DeepSeek R1	671B (37B active)	128K	State-of-the-art reasoning
GPT-OSS 120B	120B	128K	Reasoning, function calling
Llama 3.3 70B	70B	128K	Fast, multilingual
Qwen3-VL 30B	30B	256K	Vision-language, multilingual OCR

These models are the same weights as their standard counterparts — the only difference is they run inside a secure enclave with end-to-end encryption.

What is PayPerQ?

PayPerQ is a pay-per-query AI service that gives you instant access to hundreds of chat, image, video, and audio AI models in one place. Unlike traditional ChatGPT subscription that charges $20+ per month, PPQ users pay only for what they use—averaging just $4 a month.

Account registration optional. No monthly commitments. Privacy focused. Credit cards and all major cryptos accepted. Just top up with as little as 10 cents and start using premium AI immediately.

Why Use PayPerQ?

• Access hundreds of AI models from all major providers in one place
• Pay per use - no subscriptions, no wasted money on unused credits
• No registration required - start using AI in seconds
• Start small - top up with as little as 10 cents
• Privacy-first - conversational data stored locally by default
• Average cost: ~1 cent per query

Getting Started

1. Visit ppq.ai
2. Top up your balance (crypto or credit card, as little as 10 cents)
3. Select a TEE model (look for "Private via TEE" in the model name) and start chatting

No account creation needed—just fund and go.