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.

Customer support · use case

Answer the easy tickets cheaply. Escalate the hard ones before they get worse.

Route support tickets by what they are: FAQs to a small, fast model; complex or sensitive cases to a stronger one; complaints, chargebacks and 'let me speak to a person' to a human queue - one policy, every ticket traced, the cost of each on the ledger.

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

A support desk's traffic is mostly simple and occasionally serious. One model for all of it either pays frontier prices to answer 'where is my order' or lets a small model mishandle a furious customer - and the handover to a person is a rule someone wrote into the bot, not something the router can see.

What changes

FAQs and status questions answered by the cheapest model that meets your quality rules
Complaints, chargebacks and repeat tickets escalated to a stronger model or a person automatically
Every ticket's route, cost and outcome on the record for the support lead

One request

What happens, step by step

Small models answer FAQs; angry or complex tickets escalate to a frontier model or a human.

Ticket arrives
Complaint or chargeback detected
Small model removed from the candidates
Frontier model or human queue answers
Decision logged with the reason

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

A customer support request, quoted live“Customer writes: 'Where is my order #48213? It said delivered yesterday but nothing arrived.' Draft a reply with the next step.”

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. The escalate action comes from the request itself - a complaint, a chargeback, a ticket that bounced twice.

rules.yaml - customer support (reference configuration)yaml

rules:
  - name: faqs-on-the-small-model
    when:
      domains: [customer_support]
      max_complexity: 0.35
    prefer: [llm-small]
    weight: 0.8

  - name: upset-or-complex-escalates
    when:
      domains: [customer_support]
      actions: [escalate]
    prefer: [llm-frontier, human-escalation]
    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 customer support 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.

What the team is dealing with today

rules: - name: faqs-on-the-small-model when: domains: [customer_support] max_complexity: 0.35 prefer: [llm-small] weight: 0.8 - name: upset-or-complex-escalates when: domains: [customer_support] actions: [escalate] prefer: [llm-frontier, human-escalation] pin: true

Answer the easy tickets cheaply. Escalate the hard ones before they get worse.

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 customer support rules and change what you disagree with.

Answer the easy tickets cheaply. Escalate the hard ones before they get worse.

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 customer support rules and change what you disagree with.