> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tinfoil.sh/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

> Overview of Tinfoil SDKs and their use cases

The Tinfoil SDKs are drop-in replacements for OpenAI clients with automatic security verification on every connection. Available for Python, TypeScript/Node, Go, Rust, and Swift. The CLI can also act as a reverse proxy.

## Available SDKs

Read the full documentation for your SDK:

<CardGroup cols={3}>
  <Card title="Python" icon="python" href="/sdk/python-sdk" />

  <Card title="JavaScript" icon="js" href="/sdk/javascript-sdk" />

  <Card title="Go" icon="golang" href="/sdk/go-sdk" />

  <Card title="Rust" icon="rust" href="/sdk/rust-sdk" />

  <Card title="Swift" icon="swift" href="/sdk/swift-sdk" />

  <Card title="CLI" icon="terminal" href="/sdk/cli-sdk" />
</CardGroup>

If you'd like to see an SDK for a different language or runtime, please reach out at [contact@tinfoil.sh](mailto:contact@tinfoil.sh) and we'll prioritize adding support for it.

## Why you should use the SDKs

The SDKs make it easy to integrate Tinfoil into your applications without having to
worry about encryption, attestation verification, or other security pitfalls.
All the privacy and integrity features offered by Tinfoil are automatically verified
for you and all connections are blocked in case of verification failure.

Each SDK is designed to be a **drop-in replacement** for OpenAI clients.
This means you can continue to use the chat completions or responses API formats
with Tinfoil models. However, not all backend features are supported or enabled
for all models. If you experience issues, please don't hesitate to contact us.

For accessing the inference endpoint directly via HTTPS without an SDK (which we discourage for production workloads), see [Direct API Access](/sdk/direct-api-access).

## Guides

<CardGroup cols={2}>
  <Card title="Prompt Caching" icon="bolt" href="/sdk/prompt-caching">
    Reuse prompt prefixes with automatic per-user cache scoping.
  </Card>

  <Card title="Web Search" icon="magnifying-glass" href="/guides/web-search">
    Enable AI models to search the web with optional PII protection.
  </Card>

  <Card title="Tool Calling" icon="wrench" href="/guides/tool-calling">
    Learn how to use function calling capabilities with AI models.
  </Card>

  <Card title="Structured Outputs" icon="code" href="/guides/structured-outputs">
    Use JSON schema validation for reliable data extraction.
  </Card>

  <Card title="Image Processing" icon="image" href="/guides/image-processing">
    Process images with multimodal AI models.
  </Card>

  <Card title="Document Processing" icon="file" href="/guides/document-processing">
    Upload and process documents securely.
  </Card>

  <Card title="Proxy Server" icon="server" href="/guides/proxy-server">
    Keep your API key server-side while preserving end-to-end encryption.
  </Card>
</CardGroup>