Sophia's LoreBary proxy with your own key

• You want the model, not the layer. Put the API straight into the app: JanitorAI, Chub, WyvernChat, RisuAI. Nothing in the middle, one bill, every request on the console's Usage page.
• You want LoreBary's layer on top. The key goes through LoreBary; the rest of this page is what that passes on, what it keeps, and what it costs.

• A LoreBary account and the app you already use. The portal is at lorebary.com/connect-proxy.
• A RelaySwitch key from the console. Make it a key of its own with a budget, because it will sit in a third party's configuration. Keys start with sk-relay-.
• A balance. Top-ups start at $10, by card or crypto; the console chat runs 12 free turns a day before the first top-up.

The portal's first card, Connect my current app ("Show me the setup", then Your own key), lists the providers LoreBary has a permanent route for and hands you three values per provider:

This API is not on that list today, so the path for this key is the second card, My Custom Proxy (the older community guide calls the same form "Cheating On Us?"). By what each field asks for:

LoreBary answers with a proxy URL of its own. That URL, not https://api.relayswitch.io/v1, goes into the app's proxy field; the key and the model id go into their own fields as usual. In JanitorAI: Settings, Provider Proxy, + New, the LoreBary URL, your key, the model id, Add, Save, then reload the page. Chub wants a LoreBary URL with no /v1, Wyvern wants it with /v1. The form sits behind a LoreBary sign-in and renames fields between releases; match each by what it asks for.

LoreBary's own guide says its features (commands, plugins, lorebooks) work only when the proxy URL belongs to one of its permanent provider routes. A custom proxy relays the chat and nothing else. So on this route you get your app, the model you named, and the LoreBary account for its library and forums; you do not get the mid-chat commands or the plugin mechanics.

If the layer is the reason you are here, the thing to ask LoreBary for is a permanent route to api.relayswitch.io; its Discord is where that request goes. If the model is the reason, skip the hop: the direct guides take two minutes and nothing is lost on the way.

LoreBary adds no fee of its own ("Bring any provider key, we add no fee", on the portal), so the bill is the app's prompt at this catalog's prices. The ids LoreBary prints for other routes (deepseek-chat and the like) are not on this list; these are, priced per million tokens with one 2K-in / 300-out turn (2,000 in, 300 out):

Give a model that reasons before it writes a response length of 1,000 or more, or the reply arrives empty. The ranked list orders the catalog by use.

With two services in the chain, a failure has to be placed before it can be fixed. One request straight to the API, in the shape an app sends; a 200 here means the key, URL and model id are right, and anything that fails afterwards is the hop.

Each request is one line on the console's Usage page whether it came direct or through LoreBary, with a signed receipt, so the hop never hides the bill.

• 401: the key is wrong, revoked, or pasted into the URL. Paste it again into the key field.
• 404 route_not_found: the endpoint and the appended path do not add up to /v1/chat/completions; re-create the proxy. model_not_found: an id from another provider's list; paste one from the Models page.
• Commands or plugins do nothing: expected on a custom proxy. Ask LoreBary for a permanent route, or go direct.
• JanitorAI still answers with its own model: proxy settings are read when the chat loads. Save, then reload.