Give your AI a crown.
Not a text box. A Queen.
Vaela is the persona at the heart of every agent you forge. She speaks in a voice you choose, runs on the model you pick, and remembers the conversation as it goes. This is the real thing, streaming live — not a screenshot.
- ›Streams token-by-token from the selected model
- ›Swap her brain without losing the persona
- ›Keeps context across the whole thread
The internet is full of flat chatbots.
One Queen. Many minds.
Alibaba's flagship Mixture-of-Experts model — 35B total, 3B active per token (256 experts). Tuned for fast, responsive agentic reasoning and real-world utility.
Z-AI's latest flagship for long-horizon tasks. A substantial leap over GLM-5.1, delivering a solid 1M-token context for the first time.
Efficiency-focused MoE — 284B total / 13B active with a 1M-token window. Tuned for fast, high-throughput inference while holding up on reasoning and coding.
MoE with 1.6T total parameters (49B active) and a 1M-token context. Built for advanced reasoning, coding, and long-running agent tasks.
Coding-focused agentic model built on Kimi K2.6. Strengthens end-to-end task completion across complex software-engineering workflows.
Open-source, native multimodal agentic model. Advances long-horizon coding, coding-driven design, and swarm-based task orchestration.
Built for frontier reasoning, orchestration, and coding agents — up to 5x faster inference and ~30% lower cost on agentic workloads, up to 1M-token context.
Alibaba's most capable Qwen3.5 — a 397B/17B-active MoE with a 262k window (extensible to 1M via YaRN), strong tool calling, and MCP integration.
Z-AI's next-generation flagship for agentic engineering with significantly stronger coding than its predecessor. SOTA on SWE-Bench Pro.
Native omnimodal model with strong agentic capabilities across text, image, video, and audio in a unified architecture.
Google's instruction-tuned Gemma 4 — a capable, efficient open model for general chat, reasoning, and assistant workloads.
Open multimodal model on a hybrid MoE architecture for strong accuracy across image, video, audio, and text — powers always-on sub-agents.
Three steps. One sovereign.
Pick from 12+ live models. Fast and cheap, or a 1M-context flagship for the heavy stuff — it is one click to switch.
beginName her and write the system prompt that sets her voice, rules, and personality. This is what makes her yours.
beginChat live, right in the browser. Hold $VQ to keep the Court open and deploy her wherever you reign.
beginEverything a persona needs.
Route her through 12+ frontier models — Qwen, GLM, DeepSeek, Kimi, Nemotron, Gemma. Swap the brain mid-conversation; the persona stays.
Replies stream token-by-token, the way you saw above. No spinner, no dead air — you watch her think.
A name and a system prompt define her voice, manners, and rules. Shape a concierge, an analyst, a companion — or a queen with attitude.
She remembers the thread and who came back. Continuity across the session, not a goldfish that resets every message.
Give her a way to speak and a temperament to match. Warm, sharp, regal — tuned to the personality you wrote.
The Court runs on Solana. Holding $VQ unlocks the studio where you forge, tune, and deploy your own Queen.
Hold the key. Enter the Court.
$VQ is the key to the Court — the Throne Room where you forge personas, tune their minds, and deploy your own Queen. Live on pump.fun: hold 50,000 $VQ to enter, connect your wallet, and the doors open.
- ›Solana-native, fair launch on pump.fun
- ›Hold 50,000 $VQ to unlock the Throne Room
- ›One token, one Court — no tiers, no seats
Now live on pump.fun. Always verify the address against @VaelaQueenAI before you buy.
One endpoint. Every model.
Your persona, any model, one streaming chat API. Pick the brain by id, pass a system prompt, read the stream.
const res = await fetch('/api/chat', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
model: 'Qwen/Qwen3.6-35B-A3B',
system: 'You are Vaela, a sovereign AI queen.',
messages: [{ role: 'user', content: 'who are you?' }],
}),
});
// read res.body as an SSE stream of {choices:[{delta}]}