Quantum Encoding
100+ models · 10 providers · one key

Build anything
with AI.

Describe what you want. We chat it through, plan it, then build it. Or skip the chat and call the SDK yourself.

Try
Prefer code? Read the SDK docs →

SDK

Or build it yourself

Five lines to your first call. Same API surface in every language. Switch models by changing a string.

$ npm install quantum-ai-sdk 
import { QuantumClient, userMessage, responseText } from "quantum-ai-sdk";

const client = new QuantumClient("qai_your_key");

const response = await client.chat({
  model: "claude-sonnet-4-6",
  messages: [userMessage("Build me a REST API for a todo app")],
});

console.log(responseText(response));
// Cost: $0.003 — billed automatically
ChatStreamingImagesVoiceVideoEmbeddingsTTSSTTRAGRealtimeBatchTool Calling

Proof

We build on it too

Every product below runs on the same API, the same billing, and the same SDK you'll use. This is our proof it works.

Mission Control

Your API playground

An AI coding workspace where an architect agent decomposes your project, assigns models, and deploys worker agents in parallel. Watch them read, write, test, and commit — in real time. Built entirely on the Quantum API.

  • Multi-model orchestration — pick a different model per task
  • Full project workspace with file I/O, git, and shell access
  • Visual workflow builder, dependency graphs, live agent streams
  • Test API calls, compare models, prototype before you code
Open Mission Control
🦆

Cosmic Duck

Your users can build this

A consumer AI app for everyone — chat, voice conversations, image generation, video, music, document processing. Desktop, Android, iOS. Same API, same credits, same key. Proof that the platform scales to consumer products.

  • Chat with any model — Claude, GPT-5, Grok, Gemini, DeepSeek
  • Realtime voice, TTS, STT, voice cloning
  • Image, video, and music generation
  • Cross-platform — Tauri desktop, Android, iOS
Visit cosmicduck.dev

Mission Control — live demo

mission-control

Models

Every provider. You choose.

Run the same task across providers and compare results, speed, and cost. We route. You decide.

Claude

Anthropic
opus-4.7 sonnet-4.6 opus-4.6 haiku-4.5

GPT-5

OpenAI
gpt-5.5 gpt-5.4 gpt-5-mini codex

Grok

xAI
grok-4.2 grok-4.1 code-fast

Gemini

Google
3.1-pro 3-flash 2.5-pro 2.5-flash

DeepSeek

DeepSeek
v4-pro v4-flash

Plus ElevenLabs, HeyGen, Stability, and more. Full model list in the docs.

Pricing

Pay for what you use

No subscriptions. No seat fees. No minimum commitment. Per-token pricing, transparent on every request.

How it works

Buy credits

Top up your balance. Credits never expire. Every API call deducts the exact token cost.

Every request

Transparent cost

Every response includes the exact cost in the headers. No surprises, no hidden fees, no mystery bills.

Volume

Batch: 50% off

Submit batch jobs for async processing. Same models, same quality, half the price.

See full pricing table by model →

Get started

Free credits on signup

No credit card. No subscription. Sign up, get an API key, start building.

Create your account Read the Docs

Or just at the top.