Is my Fireworks AI API key safe in Pluely?

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

Does Pluely charge for using Fireworks AI?

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

Which Fireworks AI models can I use?

Any model the endpoint serves — for example llama4-maverick-instruct, deepseek-v3, qwen3-235b-a22b. You choose which ones appear in the overlay's picker.

Can I use Fireworks AI 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.

Fireworks AI, in an invisible overlay.

Fireworks serves open models with enterprise speed, compliance, and reliability — the choice when Pluely is part of how you work, not an experiment, and the endpoint simply has to be up.

Download free Read the setup guide

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

All custom providers

Why Fireworks AI?

Production-grade open-model serving.

Built for uptime

Fireworks runs open models on infrastructure with SOC 2 and HIPAA compliance options and enterprise SLAs — the boring, dependable qualities you want from something answering your client calls.

FireAttention speed

Their custom serving stack is consistently among the fastest GPU-based options — long answers stream smoothly into the overlay instead of stuttering.

Sensible pay-as-you-go

Per-token pricing with no minimums: connect the key, use what you use, and the bill matches your actual Pluely habits.

Connection details

Base URL: https://api.fireworks.ai/inference/v1
Get a key: app.fireworks.ai
Example models: llama4-maverick-instructdeepseek-v3qwen3-235b-a22b

Connect Fireworks AI in three steps

Any OpenAI-compatible endpoint works the same way.

Get your Fireworks AI API key

Create a key at app.fireworks.ai. It stays on your device — Pluely encrypts it locally and never sends it anywhere except Fireworks AI itself.

Add it as a custom provider

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

Pick it and ask

Your Fireworks AI 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 Fireworks AI

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

Ask Fireworks AI 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. Fireworks AI answers with the actual context in front of you.

Fireworks AI answers your meetings live

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