Is my NVIDIA NIM API key safe in Pluely?

Yes. Keys are encrypted and stored locally on your device — they never leave your computer except in requests to NVIDIA NIM itself. Pluely's servers never see them.

Does Pluely charge for using NVIDIA NIM?

No. Custom providers are unmetered and fully covered by the free plan — you pay only NVIDIA NIM for your own usage.

Which NVIDIA NIM models can I use?

Any model the endpoint serves — for example meta/llama-4-maverick, qwen/qwen3-235b-a22b, deepseek-ai/deepseek-v3. You choose which ones appear in the overlay's picker.

Can I use NVIDIA NIM alongside Pluely's bundled models?

Yes. On Pro plans the picker shows your custom providers next to the 200+ bundled models; on the free plan your own providers and CLIs power everything.

NVIDIA NIM, in an invisible overlay.

NVIDIA's build.nvidia.com serves optimized open models over standard APIs with generous free credits for developers — another zero-cost key that drops straight into Pluely.

Download free Read the setup guide

Your key, encrypted on-deviceUnmetered — free plan covers itOpenAI-compatible

All custom providers

Why NVIDIA NIM?

NVIDIA-hosted open models with free credits.

Free credits, real models

Developer accounts get thousands of free inference credits on frontier open models — realistically weeks of Pluely use before any payment conversation.

NVIDIA-optimized serving

These are the reference deployments NVIDIA tunes on its own hardware — dependable latency on the models everyone else also serves, often faster.

A catalog that tracks the ecosystem

New open models appear on build.nvidia.com quickly after release, each behind the same compatible endpoint you've already configured.

Connection details

Base URL: https://integrate.api.nvidia.com/v1
Get a key: build.nvidia.com
Example models: meta/llama-4-maverickqwen/qwen3-235b-a22bdeepseek-ai/deepseek-v3

Connect NVIDIA NIM in three steps

Any OpenAI-compatible endpoint works the same way.

Get your NVIDIA NIM API key

Create a key at build.nvidia.com. It stays on your device — Pluely encrypts it locally and never sends it anywhere except NVIDIA NIM itself.

Add it as a custom provider

Open Pluely's dashboard → AI Providers → Add Custom Provider. Paste the base URL (https://integrate.api.nvidia.com/v1) and your key, and pick the models you want available.

Pick it and ask

Your NVIDIA NIM models now appear in the overlay's model picker. Select one and every Ask, screenshot, and meeting answer runs on your key — unmetered by Pluely.

Everything Pluely does, on NVIDIA NIM

Connecting a provider doesn't limit the product — every mode routes through it.

Ask NVIDIA NIM about your screen

Capture the full screen, drag-select just the error or the clause that matters, attach PDFs and documents with built-in OCR, or turn on Use image so every message carries a fresh screenshot. NVIDIA NIM answers with the actual context in front of you.

NVIDIA NIM answers your meetings live

Listen mode transcribes your mic and system audio in real time with speaker labels, and NVIDIA NIM drafts the suggested answer before the question finishes — automatically on every question, after each pause, or only when you tap Suggest.

Summaries, transforms, and notes

One tap turns any answer, transcript, or document into a summary, key points with action items, a translation, or a longer draft — and meeting notes build themselves as you go. All of it runs on NVIDIA NIM.