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.

Healthcare · use case

Route sensitive healthcare workloads to approved models - and take the decision out of every application.

Protected health information is detected on the way in; external models are removed from the candidates; the on-prem model answers; complex clinical questions go to a clinician; the decision is logged. Controls you configure for a regulated workload - data boundaries, regions, PII handling, audit - not a certificate.

Try OpenSmartRoute free Talk to sales about a pilot

Free plan, no card. Self-hosting is free forever; the rules below run the same way on both.

The situation

What the team is dealing with today

Clinical and administrative teams want the same AI tools everyone else has, and every application they use would need its own rule about what may leave the network. One missed rule is a breach. The decision has to live in one place, before any model is called.

What changes

PHI detected and external models removed before a request is scored
Complex clinical questions routed to a clinician for review
Every routing decision logged with the policy that was applied

One request

What happens, step by step

PII never leaves your boundary - a policy rule, not a promise. Everything else routes on cost.

PHI detected on the way in
External models removed
On-prem model selected
Complex clinical questions to a clinician
Decision logged

Route a request like this in the playground and read the trace

A healthcare request, quoted live“Summarise this discharge note for the patient, Maria Jensen, DOB 1961-04-12: metformin increased to 1000 mg twice daily, follow-up in six weeks.”

Quoting every candidate in the public catalogue...

The policy

Two text files, not a rewrite

This is the rules.yaml that produces the behaviour above; targets.yaml names the models, agents and people it refers to. Policies run before scoring, so no objective weight can trade the boundary away.

rules.yaml - healthcare (reference configuration)yaml

rules:
  - name: phi-stays-onprem
    when:
      contains_pii: true
    prefer: [llm-onprem]
    avoid: [llm-frontier, llm-mid]
    weight: 1.0

  - name: clinical-review
    when:
      domains: [medical]
      min_complexity: 0.6
    prefer: [clinician-review]
    pin: true

Example: Illustrative configuration or synthetic data, not a customer's.A reference configuration to start from - rules the router enforces as written, not a description of how a named customer runs it.

Other use cases

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.

Start with the healthcare rules and change what you disagree with.

OpenSmartRoute is open source and the free plan keeps the full trace of every decision. Create a workspace, paste the rules, route a request.

Create a free account Read the benchmark

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

Route sensitive healthcare workloads to approved models - and take the decision out of every application.

rules: - name: phi-stays-onprem when: contains_pii: true prefer: [llm-onprem] avoid: [llm-frontier, llm-mid] weight: 1.0 - name: clinical-review when: domains: [medical] min_complexity: 0.6 prefer: [clinician-review] pin: true

Route sensitive healthcare workloads to approved models - and take the decision out of every application.

What the team is dealing with today

What happens, step by step

Two text files, not a rewrite

What it does for the whole organisation.

Run it where the data is

No vendor lock-in

Lower cost per request

Start with the healthcare rules and change what you disagree with.

Route sensitive healthcare workloads to approved models - and take the decision out of every application.

What the team is dealing with today

What happens, step by step

Two text files, not a rewrite

What it does for the whole organisation.

Run it where the data is

No vendor lock-in

Lower cost per request

Start with the healthcare rules and change what you disagree with.