Bring-Your-Own-Key · no surprise bills

The AI assistant that routes to the cheapest model that can actually do the job — and verifies its own work.

One assistant on top of every model — frontier and open-weight. Routel picks the right one for each task, double-checks its answers before you see them, remembers what matters, and keeps your data yours. Typically ~80% cheaper than running everything on a frontier model.

Works in your browser · installable on phone & desktop · no credit card to start · your keys, your data.

The AI tools you use have four expensive problems

We lived all of these. Routel exists to fix them.

💸 Surprise billsUsage-based billing that spikes without warning.
🎲 Opaque limitsVague “you’ve hit your cap” mid-task, no counts.
🤖 Flaky agentsTasks fail mid-run; you pay for silent retries.
🔒 Your dataPrompts and memory locked in someone’s black box.
🧾 Frontier taxPaying top-model prices for trivial requests.

How Routel works

Four wedges, one assistant.

🧭 Smart routing

Every request is classified and sent to the cheapest model that can handle it — a fraction-of-a-cent open model for routine work, a frontier model only for genuinely hard reasoning. You see the cost and the routing reason on every reply.

Verified agent loop

For multi-step goals, Routel runs plan → act → verify → repair. An independent checker model must approve the result before you see it. If it fails, Routel auto-repairs and re-checks — so you stop paying for broken attempts.

🧠 Memory you own

Preferences and facts live in a portable file you can read, edit, and export. Your assistant remembers your stack, your tone, your constraints — and you can take it with you anytime.

🛡️ Private by design

Bring your own key: prompts run on your provider account. We redact emails, phone numbers, keys, and card/SSN patterns before any cloud call, and we never train on your data.

Who we are

Routel is built by a small, independent team of engineers and operators who got tired of watching AI bills balloon and agents fall over on real work. We’re not a frontier lab and we’re not trying to be — we don’t train giant models. We build the layer that makes the models you already pay for cheaper, more reliable, and more private.

We believe the best AI product isn’t the one with the biggest model — it’s the one that uses the right model for each job, proves its work, and treats your data and your money with respect.

Why we built it

In 2025–2026 the tools we relied on changed billing overnight and sent developers surprise invoices. Agent products burned credits on retries that failed silently. Frontier subscriptions charged premium prices for tasks a model 30× cheaper could nail. And our prompts — often containing sensitive code and customer data — disappeared into systems we couldn’t inspect.

So we built the assistant we wanted: one that routes intelligently, checks itself, caps your spend with your permission, and keeps your keys and data under your control. Routel is a client you point at your own provider accounts — like an editor or a terminal — not a reseller standing between you and the model. That design is deliberate: it keeps you in a direct, compliant relationship with each AI provider.

No key poolingNo training on your dataSpend caps + alertsOpen, portable memoryCoined, independent brand

Up and running in three steps

Create your free account

Email and password. Accept the Acceptable Use Policy. No card required.

Connect your own API key

Paste an OpenRouter key (one key → many cheap + frontier models) or OpenAI/Anthropic. It’s encrypted at rest and used only for your requests.

Set your spend cap and go

Pick a monthly hard cap. Chat or run the agent — every reply shows the model, the cost, and what frontier would have cost. No surprises, ever.

Security & privacy

Privacy isn’t a setting here — it’s the architecture.

🔑 BYOK, encrypted

Your provider key is encrypted with AES-256-GCM and used only to serve your requests. We never pool one key across users.

🩹 PII redaction

Emails, phone numbers, API keys, card numbers and SSNs are stripped before any off-device call — on by default.

🚫 No training on your data

We don’t use your prompts or outputs to train models, and we never build competing models from provider outputs.

📒 Audit trail

Every request logs which model and provider served it, so you always know where your data went.

💳 Spend caps

A hard monthly cap you control, with an alert at 80%. A surprise bill is structurally impossible.

📦 Data portability

Export your memory anytime as a plain JSON file. Your context is yours to keep or take elsewhere.

Simple, honest pricing

A small flat fee for the layer. Compute runs at cost on your own key — we don’t mark up tokens.

Free
$0
  • BYOK chat with smart routing
  • Live cost per message
  • PII redaction
  • $5/mo spend cap
Start free
Solo
$9/mo
  • Everything in Free
  • Verified agent loop
  • $50 cap, you adjust
  • Email support
Choose Solo
Pro · popular
$19/mo
  • Everything in Solo
  • Managed-compute add-on (optional)
  • $200 cap, you adjust
  • Priority support
Choose Pro
Team
$15/seat
  • Everything in Pro
  • Shared memory spaces
  • Org spend caps
  • Admin + audit
Choose Team

Prices shown are illustrative launch pricing. You’ll always see compute cost at cost; the flat fee is for the routing, verification, memory, and privacy layer.

FAQ

Is Routel just a “wrapper” around ChatGPT/Claude?

No. Routel is a Bring-Your-Own-Key client: your requests run on your provider account under your terms with each AI provider — like an IDE or terminal that you point at your own credentials. We never pool one API key to resell access, which is both better for you and the compliant way to build.

Which models can I use?

Through an OpenRouter key you reach dozens of models — DeepSeek, Llama, Gemini, GPT, Claude and more — with one key. You can also connect OpenAI or Anthropic directly. Routel routes each task to the cheapest one that can handle it.

How do you save me money?

Routine work (summaries, formatting, simple Q&A) goes to models that cost a fraction of a cent; frontier models are reserved for genuinely hard reasoning. On a typical mix that’s around an 80% cut versus running everything on a frontier model — and you see it live, per message.

What about accuracy?

The agent loop adds an independent verification step that catches incomplete or off-task results and repairs them before delivery. It reduces errors significantly — but no AI is perfect, so always review important outputs. AI output carries no warranty.

Can I install it on my phone?

Yes. Routel is an installable web app (PWA): open it on your phone and choose “Add to Home Screen,” or click “Install” on desktop. No app store needed.

Do you train on my data?

No. We don’t use your prompts or outputs for training, and we don’t build competing models from provider outputs. Your memory file is yours to export anytime.

Stop overpaying for AI.

Connect your key, set a cap, and let Routel route the rest.

Start free