# Gatelit

## Docs

- [POST /v1/chat/completions](https://docs.gatelit.dev/api/chat-completions.md): OpenAI-compatible chat completion endpoint — the core gateway API for sending messages to any supported model.
- [Errors](https://docs.gatelit.dev/api/errors.md): Error codes, HTTP statuses, and error handling patterns for the Gatelit gateway API.
- [POST /v1/prompts/:id/run](https://docs.gatelit.dev/api/run-prompt.md): Execute a published saved prompt by its UUID, with optional variable substitutions and runtime overrides.
- [OIDC Bearer Tokens](https://docs.gatelit.dev/authentication/oidc-bearer.md): If your users already have a session token from Clerk, Supabase Auth, or Auth0, pass it directly to the gateway.
- [Authentication](https://docs.gatelit.dev/authentication/overview.md): Gatelit supports three authentication schemes. Choose the one that fits your app's architecture.
- [Service Keys (GatelitKey)](https://docs.gatelit.dev/authentication/service-keys.md): Long-lived keys for backend services, agents, and automated pipelines where there is no end user.
- [Signed Tokens (GatelitSigned)](https://docs.gatelit.dev/authentication/signed-tokens.md): Your backend issues a short-lived HMAC-signed token per user. The frontend uses it for one request, then fetches a fresh one.
- [Models](https://docs.gatelit.dev/dashboard/models.md): Control which AI models are available to your organization.
- [Dashboard overview](https://docs.gatelit.dev/dashboard/overview.md): A tour of the Gatelit dashboard and its main sections.
- [Request logs](https://docs.gatelit.dev/dashboard/request-logs.md): Browse and filter the audit trail of every request routed through your Gatelit gateway.
- [Bring Your Own Key (BYOK)](https://docs.gatelit.dev/guides/byok.md): Supply your own OpenAI, Anthropic, Google, or Mistral API keys so Gatelit routes your requests through your provider accounts.
- [Your First Request](https://docs.gatelit.dev/guides/first-request.md): Install the Gatelit SDK, issue a signed token from your backend, and send your first chat request end-to-end.
- [Prompt Management](https://docs.gatelit.dev/guides/prompt-management.md): Create, version, and run saved prompts from the Gatelit dashboard, with variable substitution, partials, and fallback model chains.
- [Streaming](https://docs.gatelit.dev/guides/streaming.md): Stream AI responses token-by-token using Server-Sent Events with the Gatelit SDK.
- [Structured Output](https://docs.gatelit.dev/guides/structured-output.md): Get typed JSON responses from any model using Gatelit's normalized structured output API.
- [How it works](https://docs.gatelit.dev/how-it-works.md): A conceptual overview of how Gatelit authenticates requests, routes them to the right LLM provider, and logs the results.
- [Introduction](https://docs.gatelit.dev/introduction.md): Gatelit is an AI gateway that routes authenticated LLM calls from any client through a single endpoint — with provider routing, org-scoped API keys, structured output, and request logging.
- [Quickstart](https://docs.gatelit.dev/quickstart.md): Make your first authenticated LLM request through Gatelit in under five minutes.
- [Installation](https://docs.gatelit.dev/sdk-vue/installation.md): Add the Gatelit Vue SDK to your Vue 3 or Nuxt application.
- [useGatelit](https://docs.gatelit.dev/sdk-vue/use-gatelit.md): Vue 3 composable for streaming AI responses from the Gatelit gateway.
- [Conversation](https://docs.gatelit.dev/sdk/conversation.md): Stateful multi-turn chat helper that accumulates message history and sends it with every request automatically.
- [GatelitClient](https://docs.gatelit.dev/sdk/gatelit-client.md): Full reference for the GatelitClient class — the main entry point for sending AI requests through the Gatelit gateway.
- [Installation](https://docs.gatelit.dev/sdk/installation.md): Install the Gatelit JavaScript SDK and set up your first AI request.
- [signToken](https://docs.gatelit.dev/sdk/sign-token.md): Sign a short-lived HMAC token on your backend to authenticate users against the Gatelit gateway.