From a polished AI workspace to a self-hosted engine — pick the deployment that fits how you work.
A full AI workspace where you talk to models from every major provider through one interface. Smart routing, model pinning, web grounding, conversation memory, streaming, themes, and full pipeline transparency — all built on top of the Nyquest optimization engine.
The Nyquest workspace ships with a full theme engine. Swap colors, layouts, backgrounds, and accents with a click. Dark mode, light mode, and everything in between. All themes are included — no upsell, no paywall.
All themes are free. Always included. More themes added regularly.
BYOK is a core feature of the Nyquest App. Plug in your API keys for any supported provider and your requests go directly to that provider under your billing — with Nyquest compression applied first. No token resale. No middleman markup. No surcharge.
Your Prompt
│
├── Nyquest Compression ─── 350+ rules · semantic condensation · 15–37% savings
│
├── Your API Key ──────── decrypted in memory · used once · never stored in plaintext
│
├── Provider API ──────── direct HTTPS call to OpenAI / Anthropic / Google / xAI
│ billed to YOUR account at YOUR rate
│
└── Response streams back ─ through Nyquest → to your workspace| Scenario | Tokens (unoptimized) | Tokens (with Nyquest) | Reduction |
|---|---|---|---|
| GPT-5.4 request | 1,000 | ~730 | ~27% |
| Claude Sonnet 4.6 request | 1,000 | ~730 | ~27% |
| Large system prompt | 4,000 | ~1,760 | ~56% |
| 10-turn conversation history | 8,000 | ~2,000 | ~75% |
Same model prices apply. You use fewer tokens per request — so your budget goes further. This is efficiency, not a discount.
Change one URL in your code. Every LLM call gets compressed automatically. Works with any OpenAI or Anthropic-compatible client. Optimization engine, metrics dashboard, multi-provider routing.
The same optimization engine deployed on your infrastructure. Single package, zero cloud dependency. Prompts never leave your network. Built for privacy-sensitive and air-gapped environments.
Chrome extension that intercepts prompts on Claude, ChatGPT, Gemini, and Grok. Applies 281 compression rules locally before send — no proxy, no server, no account required.
The Chrome extension ships 281 rules — a curated subset optimized for browser-side execution. The full proxy engine runs 350+ rules plus code minification, format optimization, and advanced compression stages.
| Product | Where It Runs | Data Path | Setup | Status |
|---|---|---|---|---|
| Nyquest App | app.nyquest.ai (web) | Browser → Nyquest → Provider | Open free | ✅ Live |
| Cloud Proxy | Nyquest infrastructure | Client → Proxy → Provider | Change base_url | ✅ Live |
| Self-Hosted | Your machine / VM | Client → localhost → Provider | Install binary | ✅ v3.1.1 |
| Chrome Extension | User's browser | Client → Provider (direct) | Chrome Web Store | ✅ v1.2.0 |
Open the app free, add the Chrome extension, or contact us for enterprise deployment.