Free with BYOK or any currently-free model. No subscription. Pay only for usage.
369+
Models
14
Artifact Types
10
Visual Chassis
Live
Web Grounding
BYOK
Your Keys
// What Nyquest Is
One workspace. Not ten tabs.
Most AI tools lock you into one model, one provider, one set of constraints. Nyquest connects 300+ models through a single interface with routing, memory, file processing, agents, and live web data built in.
DON'T PICK ONE MODEL
Use the right model for each request. Tiered routing handles selection based on plan, capability, and complexity.
DON'T LOSE CONTEXT
Upload files, they become context. Memory persists across sessions with vector recall and confidence scoring.
DON'T GUESS THE COST
Wallet-based billing. Balance visible. Charges transparent. No surprise invoices.
DON'T RELY ON STALE DATA
Web grounding fetches live page content and injects it into context. Not cached. Not summarized by a middleman.
// New · Multi-Model Splicer
Multi-Model Splicer
Run one prompt through multiple AI models, compare their answers, and get a consensus-backed response with agreement scoring.
ONE PROMPT, MANY MODELS
Fan a single query out to Claude, GPT, Gemini, DeepSeek, Qwen and more — in parallel.
CONSENSUS ENGINE
Agreement scoring, the dominant position, divergence points, and a synthesized answer.
SIDE-BY-SIDE
Compare each model's response, token usage, latency, and cost at a glance.
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.
Plus archives, structured data formats, and more. Async processing for large files.
// 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.
🎨
Image Generation
Describe what you want. Nyquest detects image intent and routes automatically. Images appear inline in your conversation and saved to your gallery.
🔊
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.
🖼️
Studio Interfaces
Dedicated Image Studio and Audio Studio for focused media work. Choose models, adjust settings, and manage generated files in one place.
// Models + Routing
All major models. One interface.
300+ 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.
🧭
Tiered Routing
T1 Haiku 4.5 default. T2 Sonnet 4.6 for Pro. T3 Opus 4.7 for Teams. Circuit breakers fail over between tiers automatically — every routing decision is visible and overrideable.
📌
Model Pinning
Lock a conversation to a specific model. GPT-5.5, Claude Sonnet 4.6, Gemini 3.1 Pro, Grok-3 — whatever you want. The pinned model handles every message.
🔑
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.
Sign up free. Bring your own keys for any provider, or use whichever models are currently free in the catalog. The first time you fund your wallet, your account flips to Pro permanently — every model unlocked, higher rate limits, larger files, live operator support. No monthly fee. No auto-renewal.
Free
BYOK + free models · 20 req/min · 10 MB
Pro
All 369+ models · 120 req/min · 100 MB · live support
No Markup
Standard provider rates
BYOK Free
Use your own keys, $0
How Pro works: sign up free — bring your own keys or use whichever models are currently free. The first time you fund your wallet (minimum $5), your account becomes Pro permanently and every model in the catalog unlocks. There's no recurring charge — the wallet pays only for the actual model calls you make at standard rates. Stay Pro forever even after the balance ticks down.
Nyquest searches the web and fetches actual page content. Results are injected directly into model context before the response is generated.
🌐
Search + Fetch
Runs a web search, then fetches full page content. Sandboxed, content-type gated, size-capped. Sources logged for provenance.
📰
Current Information
Ask about today's news, current prices, recent events. Responses grounded in live data, not stale training data.
🔓
No API Keys Required
Web grounding is built into the platform. No Tavily key. No SerpAPI subscription. Toggle on and go.
// 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.
💬
Conversation Memory
Every conversation is stored. Auto-generated titles. Pick up where you left off. Soft-deleteable, searchable, organizable into projects.
🧠
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.
🔄
Confidence Scoring
Newer and more-corroborated facts rank higher. Stale facts decay. PII and credential-shaped numerics are scrubbed before storage.
// 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.
🧩
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.
📡
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.
🛡️
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.
// 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 Tracking
Per-request cost, tokens in/out, model used, latency. Broken down by day, by model, by conversation.
🧭
Routing Visibility
See which tier was selected, which model actually served the request, and why. No black-box decisions.
💵
Billing Transparency
Full transaction history. Wallet balance, charges, top-ups. Every dollar accounted for.
// Developers
Public API. Same routing.
Integrate Nyquest into your own apps and agents. OpenAI-compatible chat completions, streaming SSE, stateless by design. Same wallet, same dispatcher tiers, same model catalog.
Nyquest's compression engine — the same code that runs in production behind app.nyquest.ai — is published under MIT/Apache-2.0. v3.2.0, full Rust, drop-in proxy, Docker image on GHCR. Install with one command.
Point your existing OpenAI or Anthropic client at localhost:5400 and ship. Auto-detects provider, translates between formats, streams SSE through unchanged. Pull the Docker image from ghcr.io/nyquest-ai/nyquest-engine:3.2.0 or build from source.
Local LLM stage
Optional Qwen 2.5 1.5B via Ollama condenses long system prompts (56%) and conversation history (75%) on top of the 532-rule pipeline. Bounded LRU cache gives ~3,730× speedup on repeated content.
Privacy mode
No telemetry, no phone-home. Prompt content is never logged — only token counts and savings %. Admin endpoints expose hit counts and regex sources, never data. Run it air-gapped if you want.
