# Confidential AI API: Secure LLM Inference at Scale | Prem

- [What is Prem API](https://docs.prem.io/index.md): Client-encrypted model APIs with confidential-computing evidence and explicit assurance boundaries.
- [Quickstart](https://docs.prem.io/quickstart.md): Send chat and audio requests with client-side encryption through the Prem SDK or local proxy.
- [Models & Pricing](https://docs.prem.io/models-and-pricing.md): Explore every model on the Prem API platform — confidential inference and Zero Data Retention — with prices, in one place.
- [Authentication](https://docs.prem.io/authentication.md): Authenticate with the Prem API using your API key and client encryption key (KEK).
- [API Keys](https://docs.prem.io/api-keys.md): Learn how API keys work, how to manage them, and how to use scopes and IP restrictions.
- [Confidential Proxy](https://docs.prem.io/confidential-proxy.md): Run a local proxy for supported OpenAI- and Anthropic-compatible routes. Point a compatible client at the local base URL.
- [Link Nostr](https://docs.prem.io/link-nostr.md): Connect your Nostr account to your profile and sync your name and profile picture.
- [Link Passkey](https://docs.prem.io/link-passkey.md): Add a passkey to your profile for passwordless login.
- [Zero Data Retention](https://docs.prem.io/zdr/overview.md): OpenAI-compatible inference through trusted partners, with no retention of your prompts or completions at any stage.
- [ZDR Security Boundary](https://docs.prem.io/zdr/security-boundary.md): Where your content is readable in ZDR mode, what Prem records, what the partner records, and what ZDR does not protect.
- [ZDR Compared With Confidential Inference](https://docs.prem.io/zdr/comparison.md): A direct comparison of confidential inference, Zero Data Retention, and a typical inference provider.
- [How It Works](https://docs.prem.io/how-it-works.md): Architecture overview: how the SDK or local proxy encrypts content for processing in the Prem confidential runtime.
- [Security Model](https://docs.prem.io/security-model.md): Prem API threat boundaries, confidential-computing controls, attestation evidence, and current limitations.
- [Encryption](https://docs.prem.io/encryption.md): Learn about the end-to-end encryption architecture that protects your data.
- [Data Retention](https://docs.prem.io/data-retention.md): What Prem API stores, what it never stores, and how you can verify the policy.
- [Attestation](https://docs.prem.io/attestation.md): What the current Prem attestation client verifies, what remains policy work, and how the SDK uses the result.
- [Developer Experience](https://docs.prem.io/developer-experience.md): What it is like to build on Prem API: SDK integration and OpenAI compatibility.
- [Platform Status & Roadmap](https://docs.prem.io/platform-status.md): Verified current behavior, known gaps, and the work required to close them.
- [Trust & Compliance](https://docs.prem.io/trust-and-compliance.md): Certifications, audits, and the verifiable security properties of the Prem API platform.
- [Production Checklist](https://docs.prem.io/production-checklist.md): Complete these steps before you send production traffic to Prem API.
- [Errors](https://docs.prem.io/errors.md): Learn how API errors work, what status codes mean, and how to handle them properly.
- [Rate limits](https://docs.prem.io/rate-limits.md): Understand API rate limits and restrictions.
- [Idempotency](https://docs.prem.io/idempotency.md): Ensure safe retries and prevent duplicates using the Idempotency-Key header.
- [Agents & Automation](https://docs.prem.io/agents.md): Build unattended, agentic, or automated systems on Prem API: which integration to use, required config, and the operational gotchas that matter at scale.
- [OpenCode](https://docs.prem.io/guides/opencode.md): Connect OpenCode to Prem API through the local Confidential Proxy.
- [Pi](https://docs.prem.io/guides/pi.md): Connect Pi to Prem API through the @premai/api-extension-pi provider for confidential inference.
- [Claude Code](https://docs.prem.io/guides/claude-code.md): Launch Claude Code through Prem's Confidential Proxy with the bundled confidential-claude wrapper.
- [Qwen Code](https://docs.prem.io/guides/qwen-code.md): Launch Qwen Code through Prem's Confidential Proxy with the bundled confidential-qwen wrapper.
- [OpenClaw](https://docs.prem.io/guides/openclaw.md): Connect OpenClaw to Prem API through the local Confidential Proxy.
- [Hermes Agent](https://docs.prem.io/guides/hermes.md): Connect Hermes Agent to Prem API through the local Confidential Proxy.
- [Goose](https://docs.prem.io/guides/goose.md): Connect Goose to Prem API through the local Confidential Proxy.
- [Loupe](https://docs.prem.io/guides/loupe.md): Understand the current compatibility boundary between Loupe, Claude Code, and Prem API.
- [Cursor compatibility](https://docs.prem.io/guides/cursor.md): Understand why Cursor's custom OpenAI base URL is not currently a supported confidential Prem integration.
- [Codex compatibility](https://docs.prem.io/guides/codex-cli.md): Understand why Codex cannot currently connect to Prem API.
- [OpenAI-compatible clients](https://docs.prem.io/guides/openai-compatible-clients.md): Connect an OpenAI-compatible SDK or application to Prem API through the Confidential Proxy.
- [Anthropic-compatible clients](https://docs.prem.io/guides/anthropic-compatible-clients.md): Connect a Messages API client to Prem API through the Confidential Proxy.
- [Claude for Microsoft 365](https://docs.prem.io/guides/claude-microsoft-365.md): Connect the Claude add-ins for Excel, PowerPoint, Word, and Outlook to Prem API.
- [React Native (BareKit)](https://docs.prem.io/guides/react-native.md): Run the Prem TypeScript SDK inside a react-native-bare-kit worklet.
- [Run Attestation](https://docs.prem.io/guides/run-attestation.md): Run confidential enclave attestation directly with Reticle.
- [Chat Completion](https://docs.prem.io/guides/chat-completion.md): Create encrypted chat completions with text, vision, and streaming, step by step.
- [Audio Transcription](https://docs.prem.io/guides/audio-transcription.md): Transcribe audio files to text over the encrypted API, step by step.
- [Audio Translation](https://docs.prem.io/guides/audio-translation.md): Check whether an audio-translation model is enabled before implementing the route.
- [Decisions](https://docs.prem.io/guides/decisions.md): Answer typed decision questions with probabilities, step by step.
- [Use LLMs](https://docs.prem.io/use-llms.md): LLM-Friendly documentation for Faster Developer Integration
- [Encrypted Chat Completions (RVENC)](https://docs.prem.io/api-reference/chat-completions.md): Create a chat completion from an end-to-end encrypted payload, decrypted only inside the confidential compute environment. Stateless: no chat history is kept and no files can be attached.
- [Create chat completion (OpenAI-compatible)](https://docs.prem.io/api-reference/zdr-chat-completions.md): Create a chat completion. Compatible with the OpenAI Chat Completions API. Not end-to-end encrypted — use `/rvenc/chat/completions` for that.
- [Encrypted Audio Transcriptions (RVENC)](https://docs.prem.io/api-reference/audio-transcriptions.md): Transcribe an end-to-end encrypted audio file into text, in the language spoken in the audio. Nothing is stored: neither the audio nor the transcript.
- [Encrypted Audio Translations (RVENC)](https://docs.prem.io/api-reference/audio-translations.md): Translate an end-to-end encrypted audio file into English text, whatever the input language. Nothing is stored: neither the audio nor the translation.
- [List available models for confidential inference](https://docs.prem.io/api-reference/list-models.md): Get a list of models available for confidential (rvenc) inference
- [List available models for standard inference](https://docs.prem.io/api-reference/zdr-list-models.md): Get a list of models available for standard (OpenAI-compatible) inference. The response follows the OpenAI models list shape.
- [Decisions](https://docs.prem.io/api-reference/zdr-decisions.md): Answer typed decision questions with probabilities over a TypeSafe-compatible API.
- [Get an API key](https://docs.prem.io/api-reference/api-keys/get-api-key.md): Get details of a specific API key by ID
- [Get API key analytics](https://docs.prem.io/api-reference/api-keys/get-api-key-analytics.md): Get analytics data for API key usage
- [List API key scopes](https://docs.prem.io/api-reference/api-keys/list-api-key-scopes.md): List all available scopes for API keys
- [List API keys](https://docs.prem.io/api-reference/api-keys/list-api-keys.md): List all API keys for the organization
- [Get API key request](https://docs.prem.io/api-reference/api-keys/get-api-key-request.md): Get details of a specific API key request/usage log entry by ID
- [List API key requests](https://docs.prem.io/api-reference/api-keys/list-api-key-requests.md): Get a filtered list of API key requests/usage logs
- [Balance](https://docs.prem.io/billing/balance.md): Manage your account balance and auto top-up settings.
- [Limits](https://docs.prem.io/billing/limits.md): Configure monthly spending limits.
- [Payment](https://docs.prem.io/billing/payment.md): Manage payment methods.
- [Usage](https://docs.prem.io/billing/usage.md): Monitor your resource consumption and token usage.
- [Glossary](https://docs.prem.io/glossary.md): Definitions of the terms that the Prem API documentation uses.
- [Contact Us](https://docs.prem.io/contact-us.md): Get help with integrations, billing, APIs, or anything else.
- [Changelog & Release Notes](https://docs.prem.io/changelog.md): Unified changelog and release notes for the Confidential API.
- [Legal](https://docs.prem.io/legal.md): Prem's Terms of Service and Privacy Policy.

## OpenAPI Specs

- [openapi](/api-reference/openapi.json)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.