Does Ollama have a free tier?
Free throughout — there is no API bill. The cost is your own machine's VRAM, disk, and electricity; how large a model you can run depends on the hardware.
Ollama: get an API key and write fiction with it on your phone
Fully local: the model runs on your own computer, not one word of your draft leaves the LAN, and the API bill is zero — the ceiling option on both the privacy and cost axes. This page is the BYOK quick answer for Ollama: 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 2 modality flags for Ollama. 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 |
| Image | Scene illustration · moment cards · comics |
How do I install Ollama and reach it from my phone?
- Install Ollama on your computer from ollama.com/download (macOS / Windows / Linux builds available).
- Run ollama pull qwen3 (or another model) to fetch weights, then ollama serve to start the server.
- By default it listens on 127.0.0.1 only, so your phone can't reach it: set OLLAMA_HOST=0.0.0.0:11434 and restart the service.
- Allow port 11434 through the firewall and note the computer's LAN IP (like 192.168.1.100).
- With phone and computer on the same Wi-Fi, change the Ollama API host in the app to http://<computer-IP>:11434/v1.
Key in hand: three steps to connect
- Open the app's Settings → AI models & services and find Ollama 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.
Ollama-specific notes
The preset host is http://localhost:11434/v1 — on a real phone, replace localhost with the computer's LAN or Tailscale IP. Ollama itself has no auth, but the app's key field must be non-empty, so any placeholder (like ollama) passes the connectivity test; for the same reason, never expose port 11434 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.