Request count and dollar cost tell different stories, and the gap between them is where the savings are. Here are the four shapes an overlay of cost and usage produces, which one to chase first, and what makes the numbers trustworthy enough to act on.
Your balance is not a stored number, it is the sum of a ledger. Here is how to read the four numbers on the balance card, the entry types behind them, and the two identities that prove your balance is doing what it should.
"The AI bill went up" becomes a query once spend carries structure. Three attribution layers — virtual keys, teams, and the OpenAI-spec user field — turn one opaque total into a breakdown you can group, filter, and cap.
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.
Image, video and audio models price per image, per second and per minute, not per token — and the expensive ones are the newest ones. nRouter holds a modality-appropriate reservation before the call and reports an unknowable cost as unpriced, never as zero.
A coding agent turns one task into hundreds of model calls. Here is how a gateway gives each run a hard ceiling that holds under burst, a fallback path that does not strand a half-finished edit, and a cost you can read per task.
A RAG app makes two kinds of model call and most teams only ever price one of them. Put embeddings and chat behind one gateway key and the cost of answering a question becomes a single number, under a single budget, with one fallback.
If you resell AI, the model bill is the wrong unit. Attribute every call to the customer it served with the OpenAI user field, cap each customer independently, and reconcile the sum against your ledger to the cent.
"Who rotated that key, and from where?" should be a filter, not an archaeology project. Here is the audit-trail contract we hold ourselves to on an LLM gateway: complete actor attribution, one shared client-IP path, append-only entries, and reads that are role-scoped and tenant-isolated.
nRouter vs Eden AI for teams running OCR, vision and translation alongside their LLM traffic. What a focused gateway serves, what it deliberately does not, and how to split a multi-service invoice before you move anything.
Point your Anthropic client at one gateway base URL and every Claude call arrives with a hard budget, a fallback path, a per-request cost header, and a team it can be billed to. No SDK rewrite, no provider key to paste.
Provider pricing does not normalize on its own — per-token, per-image, per-second, provisioned. Here is how nRouter turns that into one settled cost per request that your app, your ledger and your dashboard all read, and why an unknown cost is reported as absent rather than as zero.
nRouter is a managed LLM gateway. One OpenAI-compatible key reaches every model in your catalog, every response carries its exact cost, and guardrails, budgets, A/B tests and prompt management are on every plan, not gated.
One user action becomes fifty model calls across four agent roles. Here is how to attribute that spend by role, by run and by step, reconcile it against the ledger, and put a ceiling under it that application code cannot bypass.
