Skip to main content

Why Tinfoil?

Verifiable Privacy - Your data is processed inside secure enclaves that even Tinfoil cannot access. Hardware-enforced privacy that you can verify. Drop-in Compatible - OpenAI-compatible API; no need for complex code rewrites. Tinfoil follows the same format as existing SDKs. Transparent Security - All our security-critical code is open source. You can verify that your data was processed in a genuine secure enclave via remote attestation and transparency logs.

Try Tinfoil AI

How to Use This Documentation

This documentation is organized to help you get started quickly and go deep into the technical weeds when needed.

Getting Started

You’re here! This introduction explains what Tinfoil is and how to get started. The easiest way to get started is by using one of our SDKs. If you’d like to learn more about the technology, specifically how confidential computing works, you can read more on that in How It Works.

Client SDKs

Choose your development platform and get coding:

Models

Browse our Model Catalog to see all available AI models, including chat, audio, and embedding models.

Quick Start Paths

Get started based on what you want to do:

What Makes Tinfoil Different?

Traditional AI services process your data on servers that the application provider can access. With Tinfoil:
  • Your data stays encrypted and is only processed inside a secure hardware enclave
  • Even Tinfoil cannot see your data during processing thanks to confidential computing
  • You can verify these claims using cryptographic remote attestation
  • It’s the same OpenAI API format that you already know how to use
Ready to build something cool with private AI?

Guides

Technical guides for implementing specific features:

Tutorials

Step-by-step guides for common use cases:

Verify Our Security Claims

Learn how Tinfoil’s security works and how you can verify our privacy guarantees (our SDKs automatically verify enclave attestations for you):