Skip to main content

Bring your own key (BYOK)

On Plus and Pro, you can point the SnoutData assistant at your own OpenAI, OpenRouter, or Anthropic key. The assistant's chat and edits go straight from your machine to that provider, and the key and those prompts never pass through SnoutData's servers. AI auto-completion is the exception: see below.

The BYOK provider settings: pick a provider, paste a key, add a model, optional base URL

How it works​

By default the assistant runs on SnoutData's managed gateway: we serve the models, meter usage, and bill it to your plan. BYOK swaps that out for your own provider account. You paste an API key, pick a model, and the assistant talks to that provider directly. You pay the provider for what you use, at their rates.

AI auto-completion stays on SnoutData's model​

Your key is used for the assistant's chat and its inline edits. AI auto-completion, the ghost text in the editor, is not moved to it. Completion needs a fill-in-the-middle model, and we cannot count on your provider or model offering one, so it always uses SnoutData's completion model through our gateway, even with your own key set. It is off by default. When it is on, each completion sends the text around your cursor, the relevant part of the schema and some of your earlier queries on that connection. If prompts must go only to your provider, leave AI auto-completion off.

Set it up​

  1. Make sure you are on Plus or Pro (plans).
  2. In Studio, open Settings, AI.
  3. Add a key for OpenAI, OpenRouter, or Anthropic, then pick a model.

Each provider also has an optional base URL field, so you can point at a proxy, Azure OpenAI, or a self-hosted gateway that speaks the same API.

Where your key lives​

Your key is stored in your operating system's keychain and is never written to a config file, a log, or our servers. See Security.

For the full explainer, see the BYOK page on snoutdata.com.