What Tinfoil provides
Hardware-enforced Privacy - User request data is processed inside secure enclaves that even Tinfoil cannot access, giving you hardware-enforced privacy that is verifiable via remote attestation. Transparent Security - All our security-critical code is open source. You can verify that your data was processed in a secure enclave running the exact code we’ve open-sourced on GitHub. All our SDKs are configured to verify attestation and supply chain security automatically on each connection. Drop-in Compatibility - An OpenAI-compatible API supporting a variety of open-source models. Tinfoil SDKs are compatible with the OpenAI API, so switching requires minimal code changes.Getting Started
The easiest way to get started is by using one of our SDKs to make some inference requests.Try it now
Try our in-browser private chat with enclave verification center.
Client SDKs
Choose your development platform and get coding:Models
Browse the model catalog to see all available AI models.Learn more about Tinfoil
Read about our security architecture
If you’d like to learn more about the technology, specifically how confidential computing with secure enclaves works, you can read more on that in our primer on secure enclaves. If you’d like to understand the technical components of how Tinfoil works and the design details of our security architecture, you can read about how verification works and our backend infrastructure.Read our technical guides
Learn more about implementing specific features with:Tool Calling
Use function calling to let AI models interact with external tools and APIs.
Structured Outputs
Use JSON schema validation for reliable data extraction and structured responses.
Image Processing
Process images with multi-modal AI models using base64 encoding.
Document Processing
Upload and process documents securely through chat completions.