Does LM Studio have a free tier?
Free throughout, with no API bill — the cost is your own machine's VRAM, disk, and electricity; the LM Studio app itself is free to use.
LM Studio: get an API key and write fiction with it on your phone
The most point-and-click way to run models locally: a few GUI clicks get you a model plus an OpenAI-compatible server with zero command line — the smoothest first step toward keeping every word of your draft inside the LAN. This page is the BYOK quick answer for LM Studio: key steps, direct console and pricing links, and the app-side notes that matter. Verified 2026-07-18.
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 LM Studio. 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.
| Modality | Used for |
|---|---|
| Text | Continuation · roleplay chat · agent |
How do I install LM Studio and reach it from my phone?
- Install LM Studio from lmstudio.ai/download (macOS / Windows / Linux).
- Search for and download a model inside the app (GGUF/MLX, with recommendations matched to your hardware).
- Open the Developer tab and start the local server, which listens on http://127.0.0.1:1234 by default.
- In Server Settings, enable "Serve on Local Network" (equivalent to binding 0.0.0.0) so your phone can reach it, and allow port 1234 through the firewall.
- With phone and computer on the same Wi-Fi, set the LM Studio host in the app to http://<computer-IP>:1234/v1.
Key in hand: three steps to connect
- Open the app's Settings → AI models & services and find LM Studio in the list (one of 62 presets, with logo and search).
- 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.
- 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.
LM Studio-specific notes
The preset host is http://localhost:1234/v1 — on a real phone, replace localhost with the computer's LAN or Tailscale IP. There is no auth by default, so any placeholder (like lmstudio) satisfies the app's key field and connectivity test; LM Studio itself recommends enabling authentication once you serve on the network — if you do, paste the generated key into the app. Never expose port 1234 to the public internet.
FAQ
Where does the key live once I paste it into the app?
It's stored on your device only, under system-level encryption — never uploaded or synced to any Foreverse server. Requests go straight from your phone to the provider's official endpoint with zero markup. To revoke access, delete the key in the provider's console.