Why LowRouter exists
LLM inference is now a default building block. Most teams that ship features on top of it end up writing the same gateway twice: once to abstract the provider, again to track usage and bills. That gateway sees every prompt and every response, yet it is usually written as glue code rather than maintained as a product.
LowRouter is that gateway as a product, with two opinions baked in.
Opinion one: the footprint of a request is part of its cost
Most billing dashboards show tokens and dollars. LowRouter also reports the energy a request consumed and the grams of CO₂e the inference is estimated to have produced. Both numbers are estimates (see methodology for the formula and its limits), but once they are visible a developer can compare requests on carbon and choose differently.
We do not claim that every request is “green” or that the estimate is exact. We claim that the estimate exists, that the formula is documented, and that the inputs are auditable.
Opinion two: routing should be explicit and sovereign
When you pick a model in most gateways, you pick a brand. The brand hides who actually serves the tokens: which provider, which region, which hardware tier. That is convenient until a region requires data residency, a provider has an outage, or a contract requires a specific operator.
LowRouter exposes the route. Every response says which provider served
the request and from which region, and the dashboard lets operators
choose policies (prefer-region, prefer-low-carbon, prefer-cheapest,
fixed-provider) that map to those constraints. You delegate the route
with an auto/<creator>/<model> ID and take it back with an explicit
four-segment one; either way it is a single field.
What LowRouter is not
It is not an inference engine. The actual work happens at OpenAI, Anthropic, Mistral, and other providers. LowRouter forwards the request, measures it, and accounts for it.
It is not a benchmarking tool. The dashboard does not rank models on quality. We expose what we can measure faithfully (usage, latency, energy, carbon) and leave subjective judgements to you.
It is not a free service. The credits model is documented in credits and billing. A sustainability claim means little if the cost of running the infrastructure is hidden, so we charge what running it actually costs.
Who it’s for
- Developers who want one endpoint and one bill across multiple providers, plus enough metadata to debug and improve their app.
- Operators who need data residency, audit trails, and a clear picture of which provider served what.
- Sustainability and compliance teams who want a number for their organisation’s AI footprint that they can defend.
The dashboard and these docs are public, so you can read what we measure and how, and decide whether the trade-offs fit.