Can we run it inside our own network?

Yes. The router runs as a container or a Helm release on your infrastructure, and a routing rule keeps regulated data on the models you allow.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

How much can we save on our LLM bill?

On the public benchmark the router saved 89% against sending everything to the reference model. Import last month's provider bill on the bill page and the estimate is computed on your own traffic before you change a line of code.

If you run the platform

One decision layer, every model, no rewrite.

“Can one team keep up with the models, the prices and the outages for everyone?”Change one base URL. Every application, agent and person in the organisation gets the same catalogue, the same policy and the same fallbacks; when a provider fails or a price drops, you change one file and nobody else notices.

Get a free API key Talk to sales

A developer works at two monitors of code in a green-walled office — Photo: Zayed Hossain

How the promise is kept

Five things you can open today, not read about.

Every line below names the page or endpoint that does the work. Open it before you believe it.

OpenAI-compatible /v1 with model="auto", Anthropic Messages, and the full decision on POST /api/v1/route
SDKs and API
A reference catalogue of every vendor's models with live prices, benchmarks and releases - it moves with the market
Models
Circuit breakers, scored fallbacks and health per provider; a failing target drops down the ranking
Status
Managed rollout of the browser extension and the desktop app to every employee, settings locked where you say
Enterprise
Hosted, or self-hosted with Docker, Helm or the Azure Marketplace template - the same package either way
Downloads

What you leave with

You leave with a document, not a sales pitch.

targets.yaml and rules.yaml under version control: the whole organisation's AI policy in two text files anyone can review.

Photo: RDNE Stock project

The other readers

Same router, three more questions.

For the business

What it does for the whole organisation.

Cloud, self-hosted or on-premises
Run it where the data is
The same router ships as a hosted platform, a container image and a Helm chart; the data boundary is a routing rule.
Deployment options
One URL, every vendor
No vendor lock-in
Point your OpenAI-compatible client at one address; add, swap or retire providers in the catalogue without touching application code.
Every vendor side by side
89% less
Lower cost per request
On the 150-prompt benchmark the router spent 89% less than sending every prompt to the reference model, and the judged quality went up, not down.
Read the benchmark

Can we run it inside our own network?: Yes. The router runs as a container or a Helm release on your infrastructure, and a routing rule keeps regulated data on the models you allow.
Will this lock us into another vendor?: No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.
How much can we save on our LLM bill?: On the public benchmark the router saved 89% against sending everything to the reference model. Import last month's provider bill on the bill page and the estimate is computed on your own traffic before you change a line of code.

Bring your question. Leave with the number that answers it.

The free plan is enough to import a bill, route a first request and read its trace. When the numbers hold, the plans and the agreement follow.

Create a free account All four readers

Free plan, no card. Fifteen thousand decisions a month with the full trace.

One decision layer, every model, no rewrite.

One decision layer, every model, no rewrite.

Five things you can open today, not read about.

You leave with a document, not a sales pitch.

Same router, three more questions.

What it does for the whole organisation.

Run it where the data is

No vendor lock-in

Lower cost per request

Bring your question. Leave with the number that answers it.

One decision layer, every model, no rewrite.

Five things you can open today, not read about.

You leave with a document, not a sales pitch.

Same router, three more questions.

What it does for the whole organisation.

Run it where the data is

No vendor lock-in

Lower cost per request

Bring your question. Leave with the number that answers it.