Products · app · API · engine · extension

One platform.
Four ways to use it.

The Nyquest App is the primary product. Around it: a public REST API for developers, a self-hosted engine for air-gapped deployments, and a browser extension. Pick what fits how you work.

01 · Primary product · app.nyquest.ai Live

Nyquest App

A full AI workspace. Talk to models from every major provider through one interface. Smart routing across tiers, model pinning, web grounding, persistent memory with vector recall, agent mode, artifacts (14 file types), audio + image generation, and ten distinct visual chassis — all in one place.

Open App
Routing

Tiered Routing

Free has access to BYOK plus whichever models are currently no-cost in the catalog. Pro unlocks every model — Claude Fable 5.1 (batch) · Fable 5.1 · Opus 5, GPT-6 Astra · Astra (batch) · Astra Pro, and the rest. Circuit breakers fail over between tiers automatically; you always know which model handled which request.

Pinning

Model Pinning

Lock any conversation to a specific model. Your pinned model handles every message in that thread — no routing surprises, no model switching mid-conversation.

Keys

BYOK

Bring your own API keys for OpenAI, Anthropic, Google, xAI. Keys are AES-256-GCM encrypted at rest and used for direct provider calls. Your rates, your billing.

Web

Web Grounding

Live web search and full-page fetch injected into context before the model responds. No Tavily key required — built in. Responses cite the URLs they used.

Memory

Memory + Recall

Conversations persist. A separate memory system extracts facts across sessions, sanitizes PII, and recalls relevant ones via vector search at chat time. Confidence-scored.

Agents

Agent Mode

Multi-step planner that decomposes a request, runs tools (search, fetch, artifact creation, memory query), and streams steps over SSE. Per-run guardrails on cost, time, and steps.

02 · Create

Generate images and audio
in chat.

Type a prompt, get an image. Ask for speech, get audio. Nyquest detects creative intent and routes to the right model automatically.

Images

Image Generation

Describe what you want. Nyquest detects image intent and routes automatically. Images appear inline in your conversation and saved to your gallery.

Speech

Text-to-Speech

Generate natural-sounding speech from text. Multiple voices. Long-form inputs are auto-chunked. Audio files saved to your account and playable in the browser.

Studios

Studio Interfaces

Dedicated Image Studio and Audio Studio for focused media work. Choose models, adjust settings, and manage generated files in one place.

03 · Splicer — verify Premium

One prompt.
Every opinion that matters.

The Splicer fans a single prompt out to multiple frontier models in parallel, streams each response as it lands, then runs a consensus engine across them: an agreement score, the dominant position, a synthesized answer, and — just as important — exactly where the models diverge.

Every run comes with receipts: each model's full response, its cost, and its latency, side by side. For high-stakes answers — legal reading, medical literature, architecture decisions — one model's confident voice isn't evidence. Agreement across rivals is.

The number of models per splice scales with your plan. Splicer surfaces a higher-confidence, consensus-backed answer — it does not guarantee correctness, and it shows you the dissent instead of hiding it.

Explore Splicer in depth →

Consensus engine · illustrative run

4models asked
87%agreement
1divergence flagged
claude-opus-5aligned with consensus1.9s
gpt-5.6-luna-proaligned with consensus2.4s
gemini-3.6-flashaligned, adds caveat1.1s
grok-4.5diverges — flagged in answer2.0s

Synthesized consensus + full per-model responses, costs and latencies below every run.

04 · Artifacts

Upload files.
They become context.

Drop a file into a conversation. Nyquest processes it automatically — extracts text, structures data, generates previews — and injects it into the model's context. 14 file types, 50+ extensions accepted. Per-user 100 MB media cap.

PDF

Text extracted automatically. Full document content injected as context.

Office Docs

Word, Excel, PowerPoint processed. Tables and structure preserved.

Code

Source files in dozens of languages. Indexed and made available verbatim to the model.

JSON / NDJSON

Parsed and structured. Schema detected. Key-value data available to models.

CSV / Logs

Tabular data parsed. Log files indexed. Plain text included directly.

Images

Passed to vision-capable models. Used for analysis, OCR, and visual reasoning.

Audio

Audio files transcribed and analyzed. Generated TTS clips saved to your account.

PCAP / PCAPNG

Network captures parsed. Packets, protocols, IPs, DNS, TLS, HTTP extracted.

Plus archives, structured data formats, and more. Async processing for large files.

05 · Models + routing

All major models.
One interface.

418 models available through a searchable selector. Pin a specific model or let the dispatcher route through tiered defaults. Bring your own API keys for direct provider billing.

# every request routed by complexity, domain & live price PROMPT (compressed first) │ ▼ AUTO-ROUTER complexity · domain · price · quality ├── T0 · LOCAL $0 · simple ├── DEEPSEEK code ├── CLAUDE creative ├── QWEN reasoning └── GEMINI vision
Routing

Tiered Routing

T1 handles everyday work fast. T2 brings frontier-class models for Pro. T3 takes on deep reasoning and heavy workloads. Circuit breakers fail over between tiers automatically — every routing decision is visible and overrideable.

Pinning

Model Pinning

Lock a conversation to a specific model. GPT-6 Astra, Claude Fable 5.1 (batch), Gemini 3.8 Flash (batch), Grok 4.6 — whatever you want. The pinned model handles every message.

Keys

BYOK Supported

Bring your own API keys. Requests go directly to the provider under your account. Your rates, your billing. Keys encrypted with AES-256-GCM.

Anthropic

Claude Fable 5.1 (batch) · Fable 5.1 · Opus 5

OpenAI

GPT-6 Astra · Astra (batch) · Astra Pro

Google

Gemini 3.8 Flash (batch) · 3.8 Flash · 3.7 Flash

xAI

Grok 4.6 · 4.5 · Build 0.1

+ 248 more

via multi-provider routing

Full model catalog →

06 · Web grounding

Live web data,
not cached answers.

Nyquest searches the web and fetches actual page content. Results are injected directly into model context before the response is generated.

Retrieval

Search + Fetch

Runs a web search, then fetches full page content. Sandboxed, content-type gated, size-capped. Sources logged for provenance.

Freshness

Current Information

Ask about today's news, current prices, recent events. Responses grounded in live data, not stale training data.

Built in

No API Keys Required

Web grounding is built into the platform. No Tavily key. No SerpAPI subscription. Toggle on and go.

07 · Memory

Conversations don't reset.

Full conversation history stored. A separate memory system extracts facts, sanitizes PII, scores them by confidence, and recalls the relevant ones via vector search at chat time.

History

Conversation Memory

Every conversation is stored. Auto-generated titles. Pick up where you left off. Soft-deleteable, searchable, organizable into projects.

Recall

Fact Recall

Embedding-indexed fact store. At chat time, your message is embedded and the top-K relevant facts are vector-searched and injected into context.

Scoring

Confidence Scoring

Newer and more-corroborated facts rank higher. Stale facts decay. PII and credential-shaped numerics are scrubbed before storage.

08 · Agents

Multi-step agents,
in the workspace.

Hand off a goal — not just a prompt. Agent mode plans, executes tools, and reports back. Steps stream live, every action is auditable, and per-run guardrails cap cost and time.

Plan

Planner + Runtime

The planner decomposes your goal into steps. The runtime executes each step, with the tool registry deciding what tools (search, fetch, artifact creation, memory query) the agent can call.

Stream

Live SSE Stream

Watch each step happen in real time. The agent timeline shows tool calls, intermediate reasoning, and partial results as they arrive — no polling, no surprises.

Limits

Guardrails

Every run has step, time, and cost caps. You can stop a run at any moment. Per-run state and per-step records are persisted — fully auditable.

Agent mode is in beta. Available on every plan.

09 · Analytics

See what the system is doing.

Every request is logged. Every routing decision is visible. You always know which model handled a request, how many tokens it used, and what it cost.

Usage

Usage Tracking

Per-request cost, tokens in/out, model used, latency. Broken down by day, by model, by conversation.

Routing

Routing Visibility

See which tier was selected, which model actually served the request, and why. No black-box decisions.

Billing

Billing Transparency

Full transaction history. Wallet balance, charges, top-ups. Every dollar accounted for.

10 · Infrastructure

Built as a real system,
not a demo.

Purpose-built backend. Persistent storage. File processing pipelines. Background jobs. Daily backups. This is production infrastructure.

Rust/Axum Backend

Async, low-latency

Persistent Storage

Postgres, 36 tables

File Processing

14 types, 50+ ext.

Async Jobs

Per-artifact queue

Daily Backups

Automated

AES-256-GCM

Key encryption

SSE Streaming

Real-time tokens

418 Models

All major providers

11 · Chassis & customization

12 chassis.
Same workspace, different soul.

Same data, same flows, twelve radically different aesthetics. Each chassis is a complete visual identity — its own typography, palette, copy, and ambient effects. Switch any time. All chassis are included.

2036, not 2026

prism

Rainbow LED filament on deep violet-black. A single running spectrum, used with restraint. The future chassis.

Brand · default

nyquest

Near-black surfaces, teal accent, Outfit + DM Mono. The Nyquest brand — and the chassis you start on.

Cosmic terminal

apsis

Indigo and cyan glass. Stars in the background. The default for users who want depth and quiet light.

Painter's studio

atelier

Warm cream and vermilion. Italic accents. For long-form thinking and slow drafts.

Mid-century guide

atlas

Cobalt with mustard yellow accents. Confident, navigational. For planning and structured work.

Legal brief

courtroom

Parchment and oxford blue. Serif throughout. For research, citations, and careful argument.

Botanical journal

garden

Sage and lavender. Soft, organic, hand-bound feel. For reflection and personal notes.

Hacker terminal

matrix

Green-on-black. Monospace everything. CRT scanlines. For code and command-line minds.

Morning broadsheet

paper

Warm off-white and terracotta. Serif headlines. For writing, editing, and journalistic drafts.

Trading desk

quant

Dark navy and gold with a live ticker. Finnhub-backed market data. For numbers, analysis, and decisions.

Premium SaaS

ridgeline

Clean white with teal accents. Familiar and crisp. For work that's going in front of clients.

DAW / producer

studio

Deep dark with magenta and lime. High-contrast, energetic. For creative work and rapid iteration.

One state

Same data, different surface

Every chassis renders the same conversations, the same memory, the same artifacts. Switching is purely visual — no state migration, no settings to re-enter.

Character

Per-chassis copy + ambience

Each chassis ships its own templates and ambient overlays — quant has the live ticker, matrix has scanlines, apsis has a starfield. Beyond palette, the workspace feels different.

Contrast

WCAG-AA throughout

Every chassis is contrast-tuned for readability. Even matrix and studio meet AA on body text. No theme is for show only.

All 12 chassis included on every account. Switch any time from the chassis modal.

12 · BYOK — bring your own keys

Use your own API keys.
Pay provider rates directly.

BYOK is a first-class feature. Plug in your API keys for any supported provider and your requests go directly to that provider under your billing. No token resale. No middleman markup. No surcharge.

Encryption

AES-256-GCM at rest

Keys are encrypted the instant you paste them. Per-key nonce stored alongside ciphertext. Decrypted in memory only at dispatch. Never logged, never cached in plaintext, never sent anywhere except the provider you chose.

Passthrough

Direct provider passthrough

With BYOK, your request goes directly from Nyquest to the provider's API using your key. You pay the provider's published rate — or whatever volume discount you've negotiated. Nyquest adds zero token markup.

Adapters

Per-provider adapters

Each provider gets its own adapter handling auth, request shape, and streaming quirks. You can mix BYOK for one provider with hosted billing for others — the dispatcher routes accordingly.

# BYOK flow Your Prompt │ ├── 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
Providers

Supported providers

OpenAI (GPT-6 Astra · Astra (batch) · Astra Pro) · Anthropic (Claude Fable 5.1 (batch) · Fable 5.1 · Opus 5) · Google (Gemini 3.8 Flash (batch) · 3.8 Flash · 3.7 Flash) · xAI (Grok 4.6 · 4.5 · Build 0.1) · Any compatible endpoint via custom base URL.

Enterprise

Enterprise-friendly

Already have enterprise API agreements with volume pricing? BYOK preserves your negotiated rates. Committed-use discounts, reserved capacity, org-level billing — all stay intact.

Rotation

Key management

Add, rotate, or remove keys any time in Settings → Providers. Each key is scoped to its provider. Mix and match BYOK and hosted billing per provider.

13 · Public API · api.nyquest.ai Live

Public REST API

Same routing, same models, same wallet — accessible programmatically. Issue an API key from your account and integrate Nyquest directly into your apps, agents, or scripts.

Compatible

OpenAI-compatible

POST /v1/chat/completions with streaming SSE. Drop-in replacement for any OpenAI-compatible client — just point base_url at https://api.nyquest.ai and pass your nq-v1-... key.

Stateless

Stateless by design

API-key requests skip memory recall and conversation persistence. Each call is independent — no surprising prior-context bleed. Mirrors industry-standard developer-API behavior.

Unified

Same wallet, same routing

API requests draw from your wallet balance and route through the same dispatcher tiers as the app. Pin a model with model=... or let the router choose. BYOK works here too.

# quickstart curl https://api.nyquest.ai/v1/chat/completions \ -H "Authorization: Bearer nq-v1-..." \ -H "Content-Type: application/json" \ -d '{"model": "claude-sonnet-4-6", "messages": [{"role": "user", "content": "hi"}]}'

Manage keys in Settings → API Keys. Per-key usage and rate-limit tracking. Revoke any time.

14 · Self-hosted · open source · MIT v3.2.8

Compression Engine

The compression engine the platform grew from is open source at v3.2.8. Run it on your own infrastructure, behind your own firewall. Prompts never leave your network. Built for privacy-sensitive and air-gapped environments. v3.2 adds a published Docker image — pull from GHCR or build from source.

$ docker pull ghcr.io/nyquest-ai/nyquest-engine:3.2.0 && \ docker run --rm --network host ghcr.io/nyquest-ai/nyquest-engine:3.2.0
532Rules
<1msp50 Hot Path
75%Max Savings
~3,730×Cache Hit
Release

The v3.2.8 engine

The public release of the engine Nyquest is built on; the hosted platform has since moved to a later, proprietary build. Six-stage pipeline: normalize, OpenClaw agent mode, cache reorder, regex compression (532 rules across 19 categories with RegexSet prefilter and bounded LRU cache), local LLM semantic stage, auto-scale + forward. Sanitized for public release.

Deploy

Docker or bare metal

Multi-stage Dockerfile (Rust builder + Debian-slim runtime, non-root user, tini PID-1) auto-published to ghcr.io/nyquest-ai/nyquest-engine on every release tag. Or build the single Rust binary from source with the one-shot installer. Runs on a Raspberry Pi (rules only) or with GPU for the semantic stage.

License

Open source

MIT licensed. Nyquest-ai/nyquest-rust-fullstack-3.2.0. GitHub Actions CI · 47 / 47 tests passing · Docker auto-publish on tag. Privacy mode by default — no telemetry, no phone-home, prompts never logged.

15 · Browser extension v1.2.0

Compress in the browser

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.

Add to Chrome — Free 32 KB · Manifest v3
Overlay

Real-time HUD

Floating overlay on every AI chat showing original tokens, compressed tokens, and savings — updates live as you send messages.

Tuning

Adjustable level

Slider from gentle to aggressive. Test panel previews compression on any text before committing. Tune per workflow.

Stats

Session dashboard

Popup with session stats, live feed of compressed messages, cumulative savings. See exactly what the extension is doing.

Chrome extension ships 281 rules — a curated subset optimized for browser-side execution. The full engine runs 532 rules.

16 · Comparison

Which one fits

ProductWhere it runsHow you reach itBest for
Nyquest App app.nyquest.ai Sign in to the web app Day-to-day work, multi-model chat, artifacts, agents
Public API api.nyquest.ai nq-v1-... bearer token Integrating Nyquest into your own apps or agents
Self-Hosted Engine Your machine / VM Clone on GitHub Air-gapped or privacy-sensitive deployments
Chrome Extension Your browser Chrome Web Store Compressing prompts on existing AI sites you already use

17 · Roadmap

What's next

Now · production

App · Public API · Self-hosted engine v3.2 · Docker image on GHCR · Chrome extension v1.2.0 · Self-learning tiered routing · Local $0 tier · BYOK · Web grounding · Memory recall · 14 artifact types · Agent mode (beta) · 12 chassis · Audio + image generation · Wallet billing

Next

Encryption-at-rest for messages and memory · Native MCP server interface · T0 self-hosted dispatcher tier (local GPU endpoint) · Outbound webhooks · Batch endpoints

Future

Mobile native apps · Additional provider integrations · Multi-arch Docker images (ARM64) · Expanded agent tool registry

Pick a way in

Open the app, grab an API key, clone the engine, or install the extension. They all share the same DNA.