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.

Contact

Talk to a person. Get a reference, then a reply within one business day.

Use this page for an annual agreement, a pilot, a managed deployment or a routing audit of the traffic you already pay for. Tell us your expected monthly volume, the regions you need and whether you bring your own model providers; you get a reference and a confirmation e-mail at once.

What the enterprise plan commits to

Monthly availability: 99.9%
Support answered within: 4 h

Measured, not promised: a workspace on the plan reads its own month against these commitments at GET /api/v1/sla. Organisation SSO, region pinning, custom quotas and retention are part of the plan; what every plan includes is on the pricing page.

Talk to sales

An agreement, a pilot, or an audit of your current traffic.

Everything else - a bug, an invoice, a question about your workspace - is faster through a support ticket; the channels are below the form.

Startups under two years old, open-source maintainers and educators can ask for a discount on the self-serve plans at support@opensmartroute.ai (subject Discount) - name the workspace and, for startups, the founding date.

A support agent wearing a headset at her desk — Photo: Yan Krukau

Other reasons to write

The right door for everything else.

Prefer e-mail? support@opensmartroute.ai

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.

Or skip the call and route a request.

Most questions are answered by a trace. The free plan needs no card and the playground needs no account.

Create a free account Open the playground

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

Talk to a person. Get a reference, then a reply within one business day.

An agreement, a pilot, or an audit of your current traffic.

The right door for everything else.

What it does for the whole organisation.

Run it where the data is

No vendor lock-in

Lower cost per request

Or skip the call and route a request.

Talk to a person. Get a reference, then a reply within one business day.

An agreement, a pilot, or an audit of your current traffic.

The right door for everything else.

What it does for the whole organisation.

Run it where the data is

No vendor lock-in

Lower cost per request

Or skip the call and route a request.