Loading...
Together hosts the open-model universe — Llama, Qwen, DeepSeek, Mixtral — behind one OpenAI-compatible API with per-second serverless billing. The practical way to run big open models without owning a GPU.
200+ open models, serverless.
Two hundred plus models, from 1B tinies to 600B frontier MoEs, on one key. Whatever the open-source community shipped this month, it's probably already deployed here.
Together's serverless endpoints keep popular models warm — Pluely gets sub-second first tokens without you renting dedicated capacity.
Running open models means the weights are public and the behavior is reproducible — a real consideration when an AI is reading your screen all day.
Any OpenAI-compatible endpoint works the same way.
Create a key at api.together.ai. It stays on your device — Pluely encrypts it locally and never sends it anywhere except Together AI itself.
Open Pluely's dashboard → AI Providers → Add Custom Provider. Paste the base URL (https://api.together.xyz/v1) and your key, and pick the models you want available.
Your Together 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.
Connecting a provider doesn't limit the product — every mode routes through it.
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. Together AI answers with the actual context in front of you.
Listen mode transcribes your mic and system audio in real time with speaker labels, and Together AI drafts the suggested answer before the question finishes — automatically on every question, after each pause, or only when you tap Suggest.
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 Together AI.
Install Pluely, paste your key once, and Together AI answers for the next error, the next call, the next thing on your screen.
Free plan forever · Invisible on screen shares · No bot joins your calls
Download for your platform, browse release history, or explore our development journey
Apple Silicon & Intel
x64 Architecture
Debian Package
Loading releases...
Latest release downloads
Browse all releases
Development timeline
Download Pluely now and experience the privacy-first AI assistant that works seamlessly in the background.