Is my DeepInfra API key safe in Pluely?

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

Does Pluely charge for using DeepInfra?

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

Which DeepInfra models can I use?

Any model the endpoint serves — for example meta-llama/Llama-4-Maverick, deepseek-ai/DeepSeek-V3, Qwen/Qwen3-235B-A22B. You choose which ones appear in the overlay's picker.

Can I use DeepInfra 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.

DeepInfra, in an invisible overlay.

DeepInfra serves the big open models at some of the lowest per-token prices anywhere, with per-request billing and no minimums — the budget key for making Pluely your all-day habit.

Download free Read the setup guide

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

All custom providers

Why DeepInfra?

Open models at rock-bottom prices.

Prices that change your usage habits

When a day of heavy overlay use costs a few cents, you stop rationing questions. DeepInfra's pricing makes 'ask about everything' economically rational.

The full open-model roster

Llama, DeepSeek, Qwen, Gemma, Mistral — the popular open models are all deployed, so your picker in Pluely stays interesting without juggling providers.

Pay only for what streams

No subscriptions, no reserved capacity, no idle costs — per-token billing that matches the bursty way an overlay actually gets used.

Connection details

Base URL: https://api.deepinfra.com/v1/openai
Get a key: deepinfra.com
Example models: meta-llama/Llama-4-Maverickdeepseek-ai/DeepSeek-V3Qwen/Qwen3-235B-A22B

Connect DeepInfra in three steps

Any OpenAI-compatible endpoint works the same way.

Get your DeepInfra API key

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

Add it as a custom provider

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

Pick it and ask

Your DeepInfra 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 DeepInfra

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

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

DeepInfra answers your meetings live

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