AI your customers actually use. theo is the chat widget, automation engine, and orchestration API that ships in minutes.
CHOOSE YOUR PATH
You want AI your customers actually use. What you get is a grab-bag of bots, dashboards, and Zapier tape. Theo is one system that covers it all.
Your team is stitching together a chat vendor, a CRM, a Slack bot, and a form builder. Nothing talks to each other and no one has the full picture.
Every chat bot on the market looks the same. Generic personas, generic bubbles, generic answers. Nothing that feels like your company.
You have no idea who asked what, when, from where, or what the AI told them. No audit log. No receipts. No way to investigate later.
Your bot is tied to one model and one vendor. Prices go up, quality drifts, and migrating means rebuilding everything from scratch.
Every request flows through six stages. Your prompt in, the perfect engine out, automatically.
CLICK ANY STEP TO LEARN MORE
DOCS: ORCHESTRATION PIPELINE →Build it in the dashboard, paste a single line of HTML, and Theo is live for your customers — on your brand, under your domain.
<script src="https://hitheo.ai/embed/loader.js" data-config="your-widget-id" async ></script>
Theme, tone, logo, lead form, intent rules — point, click, ship. Everything updates live in the preview.
npm install @hitheo/sdk - then pick your use case.
OPEN SOURCE · TYPESCRIPT · FULL DOCS
DOCS: SDK REFERENCE →import { Theo } from "@hitheo/sdk";
const theo = new Theo({ apiKey: "theo_sk_..." });
const res = await theo.complete({
prompt: "Explain quantum computing simply",
mode: "auto", // → routes to Theo Flash (quick chat)
});
console.log(res.text);
console.log(res.model); // "theo-1-flash"
console.log(res.cost); // "$0.0003"Same brain, same memory, same skills. Every channel. Open-source adapters.
Every action in Theo fires a signed event. Route it to Slack, email, your CRM, or any of 5,000+ apps — without writing a backend.
Stream every completion with mode, tokens, and cost into your warehouse.
Theo-Webhook-Signature: v1=…{
"event": "completion.created",
"mode": "fast",
"tokens": 340,
"costCents": 2
}One dashboard for everything. Keys, usage, logs, routing config. No more switching between 4 provider consoles.
The right model for every message. Every time. Automatically.
Click any model to explore
Docs: Engine Routing →Theo reads every prompt and picks the right engine in the background. No keywords, no configuration, no routing tables to maintain.
Simple questions use fast, cheap models. Complex reasoning gets the premium ones. You save on every routine request, automatically.
Most prompts classify in milliseconds. Quick answers feel instant. Long-running tasks stream so users never wonder if it froze.
If one provider hiccups, Theo slides to the next. Your widget, your app, and your automations keep working. Your users never notice.
Type a prompt and watch theo decompose it into a multi-model execution chain, routed and run in real time.
TRY A MULTI-MODEL PRESET OR TYPE YOUR OWN
// The same routing happens whether you call it from your app,
// embed the widget, or type in the playground.
theo.ask({
prompt: "Build me a video about a dog on a skateboard and roast me about it",
mode: "auto",
});
// → Theo Code (auto)Add funds. Use the API. Simple.
Add dollars to your balance and draw down per token. Passthrough model costs plus a small platform fee. No plans. No subscriptions. No commitments.
CREATE ACCOUNTBilling by OpenCharts Inc., the company behind Theo.
PARTNERS & PLATFORMS
Customers & Partners




Channels & Integrations
SHOWCASE
Real products powered by the theo API — from healthcare to insurance to creative tools.
One API key. Ten intelligent engines. Automatic routing. Conversations & memory. Extensible skills. Open-source SDK.
Start free in 30 seconds. No credit card. Your users get better answers. You write less code.