AI models and providers

Three ways to analyse your cameras

Every check sends a short series of frames from your Station to the AI model you choose, together with your Events. The model answers whether each Event is happening, and your workspace turns the answer into Messages and alerts.

You choose the model per Station, and you can override it for a single camera. Changing it never changes your Events, schedules or alerts.

Local model

The model runs on the computer with your Station, so camera frames are analysed there and never go to a cloud AI provider. There is no token bill; the cost is your hardware and electricity. It needs a desktop Station (Windows, macOS or Linux) with enough memory, ideally with an NVIDIA GPU or Apple Silicon.

LiquidAI d1-2B runs locally on desktop Stations. Setup downloads verified files and checks readiness before monitoring starts.

TypeSafe AI

For cloud detection, Station sends frames directly to TypeSafe AI using your API key. TypeSafe bills usage to your account.

OpenAI

A cloud provider with its own API key and pricing. Stations set up with an OpenAI key keep using it, and Camera Chat always uses one.

How to choose

1. Start with local d1 on a desktop Station. Check its measured analysis time to see whether the computer can keep up.
2. Use cloud AI on mobile Stations or when a desktop is too slow for your cameras.
3. Mix them: keep a cloud provider as the Station default and switch only the cameras that need it to a local model, or the other way round.
4. Camera Chat, where you ask a camera a question, always uses your OpenAI key, whichever model watches for Events.

Explore guides