Is this the same as ChatGPT?

Same models, different billing. ChatGPT is OpenAI's subscription app; the API key is pay-per-token. Light overlay use often costs less than a subscription — and if you already pay for ChatGPT Plus, connect the OpenAI Codex CLI to Pluely instead and reuse that plan at no extra cost.

Is my OpenAI API key safe in Pluely?

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

Does Pluely charge for using OpenAI?

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

Which OpenAI models can I use?

Any model the endpoint serves — for example gpt-5.2, gpt-5.2-mini, gpt-4o, o4-mini. You choose which ones appear in the overlay's picker.

Can I use OpenAI 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.

OpenAI, in an invisible overlay.

Connect your OpenAI API key and run GPT models directly in Pluely's overlay — your billing, your rate limits, no middleman. Every screenshot question, live meeting answer, and document summary goes straight from your machine to OpenAI and back.

Download free Read the setup guide

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

All custom providers

Why OpenAI?

GPT models on your own key.

The models everyone benchmarks against

GPT-5-class models are the default answer to "which AI should I use?" — strong at everything, exceptional at instruction-following. In Pluely that means answers that actually match what you asked, whether it's a contract clause or a live interview question.

First-party beats resold

Your key talks to api.openai.com directly — no aggregator in the middle adding latency or a markup. You get OpenAI's real rate limits, real uptime, and usage visible in your own dashboard.

Scale the model to the moment

Keep gpt-5.2-mini as your fast default for meeting answers, and switch to the full model or a reasoning model for the hard questions — one tap in the picker, mid-conversation, context intact.

Connection details

Base URL: https://api.openai.com/v1
Get a key: platform.openai.com
Example models: gpt-5.2gpt-5.2-minigpt-4oo4-mini

Connect OpenAI in three steps

Any OpenAI-compatible endpoint works the same way.

Get your OpenAI API key

Create a key at platform.openai.com. It stays on your device — Pluely encrypts it locally and never sends it anywhere except OpenAI itself.

Add it as a custom provider

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

Pick it and ask

Your OpenAI 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 OpenAI

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

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

OpenAI answers your meetings live

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