GPUStack: get an API key and write fiction with it on your phone

Two links up front: get your key at the official download page (it runs locally — there is no pricing page because there is no bill). Prices and free quotas move; the official pages are authoritative.

What does it power inside Foreverse?

The factory preset declares 1 modality flag for GPUStack. The models actually available come from the live catalog fetched in-app — catalogs move fast, and the flag only means the protocol wiring is ready.

How do I install GPUStack and reach it from my phone?

1. Start the server with one docker command on a GPU machine: docker run -d --name gpustack -p 80:80 -v gpustack-data:/var/lib/gpustack gpustack/gpustack.
2. Get the initial password via docker exec gpustack cat /var/lib/gpustack/initial_admin_password, then open http://<host-IP> in a browser and log in as admin.
3. Deploy a model from the console (extra machines can join as workers to form a scheduled cluster).
4. In the console, open Access Control → API Keys → New API Key; the key is shown once at creation, so copy it immediately.
5. In the app, set the host to http://<host-IP>/v1 (port 80 by default; include the port if you mapped a different one) and paste the key.

Key in hand: three steps to connect

1. Open the app's Settings → AI models & services and find GPUStack in the list (one of 62 presets, with logo and search).
2. Paste the key and tap the connectivity test — it fires one real request to verify key and network, and pulls back the model list while it's at it.
3. Enable the models you want, then set per-modality defaults (text, image, speech, and video each get their own); continuation, chat, and listening route through them from then on.

The one universal host pitfall: the API host must include its full version prefix (this provider's exact form is in the notes below) — the app never appends /v1 for you.