Is my Cerebras API key safe in Pluely?

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

Does Pluely charge for using Cerebras?

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

Which Cerebras models can I use?

Any model the endpoint serves — for example llama-4-maverick, qwen3-32b, gpt-oss-120b. You choose which ones appear in the overlay's picker.

Can I use Cerebras 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.

Cerebras, in an invisible overlay.

Cerebras inference runs on dinner-plate-sized chips and it shows — thousands of tokens per second on frontier open models. Connected to Pluely, even long answers land in a blink. Free tier available.

Download free Read the setup guide

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

All custom providers

Why Cerebras?

Wafer-scale speed, thousands of tokens per second.

The speed record holder

Cerebras regularly posts the fastest inference numbers in the industry — 2,000+ tokens per second on some models. Long summaries that take other providers fifteen seconds appear instantly.

Reasoning models you'll actually wait for

Thinking models are great until you're staring at a spinner mid-meeting. At Cerebras speeds, even chain-of-thought models respond in conversational time.

Free tier to feel the difference

The free tier is enough to run Pluely daily — try one meeting on it and normal-speed providers feel broken afterward.

Connection details

Base URL: https://api.cerebras.ai/v1
Get a key: cloud.cerebras.ai
Example models: llama-4-maverickqwen3-32bgpt-oss-120b

Connect Cerebras in three steps

Any OpenAI-compatible endpoint works the same way.

Get your Cerebras API key

Create a key at cloud.cerebras.ai. It stays on your device — Pluely encrypts it locally and never sends it anywhere except Cerebras itself.

Add it as a custom provider

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

Pick it and ask

Your Cerebras 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 Cerebras

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

Ask Cerebras 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. Cerebras answers with the actual context in front of you.

Cerebras answers your meetings live

Listen mode transcribes your mic and system audio in real time with speaker labels, and Cerebras 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 Cerebras.