A feature matrix does not survive a finance review. The internal case for an LLM gateway is four measurable outcomes — total spend, unit cost, performance under load, and shipping speed — each with a number attached.
You could run your own LLM gateway, and some teams should. We chose to run one for you instead. Here is the operational bill self-hosting hands you, the mechanism we replace it with, what our choice genuinely costs you, and the teams that should still self-host.
Guardrails, audit trails, budgets, evals, A/B tests and prompt management are on every nRouter plan. Plans change the platform fee and the rate limits, never the feature set — here is the reasoning, the crossover math, and what the bet costs us.
The most important number in an LLM gateway is what a call cost, and it is the easiest one to fudge. We read the provider's settled cost and pass it through exactly; when it is unknowable we say unpriced, never zero.
nRouter has no sandbox, no sample dataset, and no demo mode. The dashboard figure, the playground response, the cost header and the ledger row are all produced by the same live path a paying request takes. The cost of that honesty is that there is nothing to look at until you have paid for a call.
Bring-your-own-key sounds customer-friendly and mostly relocates work to you. nRouter issues one key and credits and manages every provider account — here is the reasoning, the blast-radius math, what the choice costs you, and who should pick a BYOK gateway instead.
A gateway can take its cut two ways: silently, inside the per-token rate you can never decompose, or visibly, as a platform fee added at purchase. nRouter does the second, so every credit you buy is spendable at the provider's own settled cost.
Forwarding a request to a provider is a solved problem. Tenant isolation, credits that cannot go negative, guardrails on every call and one bill are not. That asymmetry decided what nRouter is — and what we refuse to ship.
