theo

One API key. 300+ models. Theo routes every prompt to the perfect model, automatically.

300+Models
<1msRouting
99.9%Uptime
1API Key

THE MULTI-MODEL PROBLEM

You're building with AI. You shouldn't need a PhD in prompt engineering and 7 vendor relationships to ship.

7 API KEYS

Every provider has its own SDK, auth, billing dashboard, and rate limits. You're managing 7 relationships just to cover your use cases.

NO ROUTING

You're hardcoding model selection. One for code, another for chat, another for images - all manual, all fragile, all wrong when a model goes down.

FRAGMENTED BILLING

4 billing dashboards. 4 invoices. No unified view of what you're spending or which requests cost the most.

VENDOR LOCK-IN

Built your whole app on one provider's SDK. Now they raise prices 40% and you're rewriting everything.

THEO SOLVES ALL FOUR ↓

HOW IT WORKS

Every request flows through five stages. Your prompt in, the perfect model out, automatically.

CLICK ANY STEP TO LEARN MORE

<1ms
Classification
<500ms
First token
Auto
Failover
100%
Transparent

INTELLIGENT ROUTING

Intent classification in <1ms. The right model for every request, every time. No manual selection, no hardcoded logic.

You send a prompt. Theo detects the intent, scores every model on capability, latency, and cost, then routes to the winner. If that model goes down, failover happens in <100ms.

CLICK ANY MODEL TO SEE HOW IT'S SELECTED

WHY THEO'S ROUTING IS DIFFERENT

INTENT-FIRST, NOT KEYWORD-FIRST

Other routers match keywords. Theo classifies semantic intent, understanding that 'build me a dashboard' is a code task even without the word 'code'.

COST-AWARE SCORING

Every route weighs capability × latency × cost. Simple questions go to cheap models. Complex reasoning goes to frontier models. You save 40-60% automatically.

<1ms CLIENT-SIDE PRE-CLASSIFICATION

Keyword matching runs on the client before the request even hits the server. Server-side embedding check confirms. Classification adds virtually zero latency.

AUTOMATIC FAILOVER

If the selected model is down or rate-limited, Theo silently routes to the next best in <100ms. No try/catch blocks. No manual fallback logic.

WHAT DEVELOPERS BUILD

Real scenarios. Real code. See what Theo makes possible.

TRY IT LIVE

Type a prompt and watch Theo classify your intent in real-time. See which model gets selected and why.

TRY A PRESET OR TYPE YOUR OWN

Theo Code
code / think
Theo Fast
fast
Theo Image
image
Theo Roast
roast
Theo Video
video
Theo Research
research
quickstart.ts
import { Theo } from "@hitheo/sdk";

const theo = new Theo({ apiKey: "theo_sk_..." });

const result = await theo.complete({
  prompt: "Compare term life quotes",
  mode: "auto",
});

// → Theo Code (auto)

THREE LINES TO SHIP

npm install @hitheo/sdk - then pick your use case.

OPEN SOURCE · TYPESCRIPT · FULL DOCS

your-app.ts
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 Fast (quick chat)
});

console.log(res.text);
console.log(res.model);       // "theo-fast"
console.log(res.cost);        // "$0.0003"
TypeScriptStreamingTree-shakeable0 dependencies

SKILL STORE

An app store for AI capabilities. Install domain skills that give Theo specialized knowledge - or build and publish your own.

BROWSE · INSTALL · PUBLISH

skills.hitheo.ai
AllOfficialCommunity
Insurance
Insurance Quoting
by hitheo

Compare rates across 5+ carriers in real-time. Pre-built data connectors, carrier-specific rate tables, and compliance guardrails.

1.2k
Developer
Code Review
by hitheo

Analyze PRs for security vulnerabilities, performance issues, and architecture anti-patterns. GitHub, GitLab, Bitbucket.

3.4k
Research
Deep Research
by hitheo

Multi-step web research with source synthesis. Crawl, read, and produce cited reports, not just summaries.

2.8k
Data
Data Extraction
by community

OCR + structured extraction from PDFs, images, and scanned documents. Returns typed JSON, not raw text.

890
Content
Content Writer
by community

Blog posts, emails, social copy. Adapts tone to your brand voice. SEO optimization built-in.

1.6k
Custom
Custom Skill
by you

Define custom tools, knowledge bases, and workflows. Publish to the store or keep private to your org.

-

BUILD YOUR OWN

my-skill.ts
import { defineSkill } from "@hitheo/sdk";

export default defineSkill({
  name: "inventory-check",
  description: "Real-time inventory lookup and reorder alerts",
  tools: [checkStock, reorderAlert, getSupplierPrices],
  knowledge: ["./product-catalog/*.json"],
});

// Publish to the store:
// npx hitheo publish --public
// Other developers can install it instantly.

EARN FROM YOUR SKILLS

Publish skills to the store. Other developers install and use them. You earn credits for every API call that activates your skill.

SKILLS & TOOLS

Install domain skills that give Theo specialized knowledge. Like an app store for AI capabilities.

CLICK ANY SKILL TO SEE MORE

WORKS EVERYWHERE

Channel-agnostic core. Same brain, same memory, same skills - every channel. Open-source adapters. npm install and you're live.

THEO BRAINSAME ORCHESTRATION · EVERYWHERE
WEB APP
TELEGRAM
WHATSAPP
REST API
CUSTOM
Telegram
@hitheo/telegram
User: What's the weather?
Theo: Quick one. Fast mode. ⚡
WhatsApp
@hitheo/whatsapp
User: Build me a landing page
Theo: Code mode. Warming up. 💻
REST API
@hitheo/sdk
User: POST /v1/completions
Theo: Your backend, your rules. Full control.

BRING YOUR STACK

Theo works with any framework, any runtime, any cloud. Install the SDK and go.

Next.jsExpressFastifyVercelCloudflare WorkersAWS LambdaSupabaseBunDenoNode.js

DEVELOPER DASHBOARD

One dashboard for everything. Keys, usage, logs, routing config. No more switching between 4 provider consoles.

api.hitheo.ai/dashboard
12,847
Requests today
340ms
Avg latency
$4.21
Cost today
6
Models used
REQUEST VOLUME (24H)
LIVE REQUESTS
15:42:03Fastfast$0.001 · 120ms
15:42:01Codecode$0.042 · 1.2s
15:41:58Imageimage$0.008 · 3.4s
API Keys
Create, rotate, and scope keys per environment
Usage Analytics
Per-model cost, latency, and volume breakdowns
Real-time Logs
Stream every request: model, mode, cost, duration
Routing Config
Override defaults, pin models, set cost caps

WHY THEO?

You could wire up multiple AI providers yourself. Here's what that looks like vs. Theo.

WITHOUT THEO47 LINES
import ProviderA from "provider-a-sdk";
import ProviderB from "provider-b-sdk";
import ProviderC from "provider-c-sdk";

// Init 3 SDKs
const a = new ProviderA({ apiKey: KEY_A });
const b = new ProviderB({ apiKey: KEY_B });
const c = new ProviderC({ apiKey: KEY_C });

// Manual routing logic
function pickModel(prompt: string) {
  if (isCodeTask(prompt)) return "a";
  if (isImageTask(prompt)) return "c";
  return "b"; // default
}

// Manual failover
try {
  const model = pickModel(userPrompt);
  if (model === "a") {
    res = await a.messages.create({...});
  } else if (model === "c") {
    res = await c.models.generateContent({...});
  } else {
    res = await b.chat.completions.create({...});
  }
} catch (e) {
  // Try fallback... manually
  res = await b.chat.completions.create({...});
}
WITH THEO6 LINES
import { Theo } from "@hitheo/sdk";

const theo = new Theo({ apiKey: "theo_sk_..." });

const res = await theo.complete({
  prompt: userPrompt,
  mode: "auto",
});
// Routing, failover, cost optimization,
// model selection - all handled.

HOW THEO COMPARES

vs. Direct Provider SDKs
They: One model per provider. You manage routing, failover, billing, and memory yourself. Locked into one vendor's SDK.
Theo: 300+ models through one SDK. Auto-routing, auto-failover, unified billing. Switch modes with one parameter change.
vs. Perplexity
They: Great for search, but it's a consumer product, not a developer API. No SDK, no model routing, no custom skills, no channel adapters.
Theo: Developer-first API with full SDK. You control the models, the routing, the memory, and deploy to any channel.
vs. Victory AI / Other Wrappers
They: Simple wrappers that proxy requests. No intent classification, no intelligent routing, no cross-session memory, no skill system.
Theo: Intent-driven routing in <1ms. Built-in memory that persists across sessions and channels. Extensible skill system for domain expertise.
vs. LangChain / LangGraph
They: Powerful frameworks but heavy. Requires deep setup, custom orchestration code, and your own infra for state management.
Theo: Zero-config orchestration. 3 lines to start. Hosted routing, memory, and skills with no infra to manage.
Auto failover
Model goes down? Theo switches in <100ms. You never notice.
Cost optimization
Theo routes simple tasks to fast models. You save 40-60% vs. always using the most capable model.
Built-in memory
Cross-session, cross-channel memory. No vector DB setup, no embedding pipeline.
Zero lock-in
Switch models by changing a mode string. No SDK rewrites, no migration.
Unified billing
One invoice, one dashboard. Per-request cost tracking across all providers.
Extensible skills
Install domain skills or build your own. No framework overhead.

PRICING

FREE

to start

Then pay-as-you-go per token. Passthrough model costs plus a small platform fee. No minimums. No commitments.

CREATE ACCOUNT
FREE TIER
1,000 requests/day
All 300+ models
Community support
Dashboard access
PAY-AS-YOU-GO
Unlimited requests
Per-token billing
Priority routing
Email support
ENTERPRISE
Dedicated routing
SLA guarantees
Custom skills
Slack support

DEVELOPERS SHIP FASTER

EARLY ACCESS FEEDBACK

We replaced 3 AI SDKs and 200 lines of routing logic with 6 lines of Theo. Our response times dropped 40% because Theo actually picks the right model.

Sarah K.
CTO, Series A SaaS

The memory system is what sold us. Our support bot remembers context across Telegram and web. Customers stopped having to repeat themselves.

Marcus D.
Lead Engineer, Fintech Startup

I built a custom insurance quoting skill in an afternoon. My agents now compare 5 carriers in real-time through a Telegram bot. That would have been a 3-month project.

Priya M.
InsurTech Founder

READY TO BUILD?

One API key. 300+ models. Intelligent routing. Built-in memory. Extensible skills. Open-source SDK.

Start free in 30 seconds. No credit card. Your users get better answers. You write less code.