Does NVIDIA NIM have a free tier?
Yes, for dev and testing: sign-up grants roughly 1,000 inference credits (expandable to about 5,000 on request) at around 40 requests/minute, no card required; production use needs a separate enterprise license.
NVIDIA NIM: get an API key and write fiction with it on your phone
The zero-cost sandbox for NVIDIA-optimized inference: 100+ open models (Nemotron, DeepSeek, Llama, Qwen) on a free prototyping allowance with no credit card — positioned as a dev/test playground, not a production channel. This page is the BYOK quick answer for NVIDIA NIM: 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 NVIDIA NIM. 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 NVIDIA NIM and reach it from my phone?
- Sign in to build.nvidia.com with a free NVIDIA Developer Program account — no card needed.
- Open any model page and click Get API Key (or go straight to Settings → API Keys) to mint an nvapi- key.
- The key is shown once — copy it. New accounts carry roughly 1,000 inference credits, expandable to about 5,000 on request from your profile.
Key in hand: three steps to connect
- Open the app's Settings → AI models & services and find NVIDIA NIM 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.
NVIDIA NIM-specific notes
The preset host is https://integrate.api.nvidia.com/v1. Keys carry the nvapi- prefix. The free tier throttles at roughly 40 requests/minute and NVIDIA explicitly does not grant increases; the catalog and limits shift over time. Officially this covers prototyping and R&D only — production requires an NVIDIA AI Enterprise license, which is why no public per-token price list exists.
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.