# Hosted or self-run

> Where your agent's logic runs, from a worker on your machines to a flow with nothing to host, and which key each one uses.

Source: https://docs.vlayers.ai/get-started/concepts/hosted-vs-self-run

Kind: Concept

VoiceLayer runs every call: the voice, the phone line, the safety checks, billing and the transcript. What differs is where **your** logic runs, if you have any.

![Four boxes side by side, all feeding one wide box that reads VoiceLayer runs every call. Your worker: code runs on your machines, dials out to VoiceLayer, uses a worker key. Hosted room: code runs on VoiceLayer, sleeps when idle or stays always on. Brain connector: your model answers while VoiceLayer keeps the voice, uses a connector token. Flow on the canvas: no code to run, nothing to host.](https://docs.vlayers.ai/portal-media/concepts/hosted-vs-self-run.svg)

*Four places your logic can run. Every call still runs on VoiceLayer.*

## The four ways

**Your worker.** You write an agent with the SDK and run its worker on your own machines. It opens one outbound connection to VoiceLayer, so you open no inbound port. It holds a worker key for one environment, never a provider key.

**A hosted room.** You write the same agent, but run `voicelayer deploy --hosted`. VoiceLayer runs your code in a sealed room, so there is no worker to operate. The room can only call hosts you list. Deploying uses your API key.

**A brain connector.** Your own model or text agent writes the replies; VoiceLayer keeps the voice. In **tunnel** mode a small daemon dials out with a connector token; in **direct** mode VoiceLayer calls your public endpoint.

**A flow on the canvas.** You build the steps in the dashboard. Nothing to write and nothing to host. Tool steps can call an API you host.

## Which should I pick?

| | Your worker | Hosted room | Brain connector | Flow |
|---|---|---|---|---|
| Where your logic runs | Your machines | VoiceLayer | Your endpoint | Nowhere, the canvas runs it |
| You operate | A worker process | Nothing | The daemon, or a public URL | Nothing |
| Key it uses | Worker key | API key to deploy | Connector token | Dashboard sign-in |
| Provider keys (voice and model) | Saved in **Settings → Provider accounts** | Same | Same, for the voice | Same |
| Best for | Code that must stay on your network | Code without servers; schedules, saved data, endpoints | An LLM app you already have | Most agents |

Whichever you pick, speech and model provider keys stay with VoiceLayer, never in your process. The exception is a framework brain, which calls its own model from your process with its own key.

## Sleep and always on

A hosted agent sleeps after 30 minutes with no call, text, request or schedule run, and is not billed for a room while asleep. The next call wakes it, and the first answer takes a few seconds longer. **Always on** keeps rooms up every hour at the room's hourly price, and you turn it on knowing that price. Your plan limits how many always-on rooms you can have.

## Next

- [How agents run](https://docs.vlayers.ai/build/deploy)
- [Run your agent on VoiceLayer](https://docs.vlayers.ai/developers/sdks/hosting)
- [Brain connectors](https://docs.vlayers.ai/build/brain-connectors)
- [Voice agents in code](https://docs.vlayers.ai/developers/sdks/voice-agents)
