THE CONTROL PLANE FOR AI APPLICATIONS

One API.
Every model.
Complete control.

Route AI requests, monitor usage, and control costs across providers — through one developer-friendly gateway.

OpenAI-compatible APIBring your own keyLocal demo works now
app.routiqel.com / overviewDEMO MODE
WORKSPACE / OVERVIEW

Usage overview

Illustrative data
Requests1,284example events
Success rate99.1%simulated
Est. spend$2.16demo estimate
Request activity
MonWedFriSun
chat.completionsroutiqel-demo · 218 tokens
142 ms$0.0002
Early access · Local MVPExample dashboard data is simulated and labeled.

THE OPERATIONAL GAP

AI infrastructure shouldn’t slow you down.

Every new provider adds another interface, another bill, and another place where reliability can slip.

01

Inconsistent APIs

Provider-specific conventions make changes ripple through product code.

02

Limited visibility

Request volume, latency, and errors can be scattered across different tools.

03

Unplanned spend

Usage can grow before a team has a clear view of its costs and limits.

04

Operational overhead

Retries, provider failover, and access management take time away from the product.

DEVELOPER EXPERIENCE

One integration.
A clearer view of your AI stack.

Keep your application code pointed at one endpoint. Start with the deterministic demo provider, then configure an authorized provider in your workspace.

  • OpenAI-compatible request shape
  • Project-scoped API keys
  • Request metadata logged without prompt text
Read the quickstart
import json
from urllib.request import Request, urlopen

payload = {
    "model": "routiqel-demo",
    "messages": [{"role": "user", "content": "Hello"}],
}
request = Request(
    "http://localhost:8000/v1/chat/completions",
    data=json.dumps(payload).encode(),
    headers={"Authorization": "Bearer rtq_YOUR_PROJECT_KEY", "Content-Type": "application/json"},
    method="POST",
)
with urlopen(request) as response:
    print(json.load(response)["choices"][0]["message"]["content"])

Requires an API key created in your Routiqel workspace. The demo adapter needs no provider credentials.

HOW IT WORKS

One request path. More control around it.

Connect an authorized provider, choose a route, send requests, and use the resulting metadata to understand your stack.

01

Connect

Configure an authorized provider, or use the local sandbox.

02

Route

Set a primary provider and optional demo fallback.

03

Observe

Review request status, latency, tokens, and estimates.

04

Control

Set a project budget and enforce a hard monthly limit.

Request logsRouting rulesBudget checks

Routiqel authenticates the project, applies limits, selects a route, and records request metadata. Local demo architecture · not an AWS deployment

WHO IT’S FOR

Spend less time stitching systems together.

AI product startups

Build a provider-aware request path while keeping early usage visible.

SaaS teams

Manage multiple model integrations through one application-facing API.

Engineering teams

Inspect request health and configure practical controls per project.

Cost-conscious builders

Estimate usage and define a budget limit before spend surprises you.

EARLY ACCESS

Try the local MVP for free.

No billing integration is implemented. Local demo usage is simulated; connecting an external provider uses your own account and may incur provider charges.

See availability and limitations
FREE BETA$0 during local preview
  • Gateway sandbox
  • Local request analytics
  • Project API keys and budgets
  • No hosted service or billing
Ask about the project

FAQ

Clear answers for your first integration.

Routiqel is an early-stage project. Product behavior and availability are described as they exist in this local MVP.

Browse documentation
Does Routiqel provide AI models?

No. Routiqel is an infrastructure layer that routes requests to a deterministic local adapter or an AI provider account you configure.

Do I need an external provider key to try it?

No. The local demo adapter works without provider credentials. It returns deterministic simulated responses.

Are cost figures exact provider bills?

No. The dashboard records estimates from available token counts and configured example rates. They are not invoices or guaranteed provider charges.

Does the gateway support streaming?

Streaming is not supported in this MVP. The API accepts non-streaming chat completion requests.

Is Routiqel hosted on AWS today?

No. The local MVP runs on your machine with SQLite. AWS services are documented as a proposed production architecture only.

How are provider credentials handled?

Configured credentials are encrypted by the local API before storage and are never included in browser responses. Production key management still needs a deployment review.

TAKE CONTROL OF YOUR AI INFRASTRUCTURE

Start with one request.

Explore the simulated demo or contact us about the project.

Contact RoutiqelRead the docs