Where does the saving install?
BV‑SALA is not an app, not an extension, not a ChatGPT setting. It's a piece of code a developer places inside their own application, right where that application calls the OpenAI or Anthropic API. It can only save where a per-token bill exists — and can only measure it where it sees every request go by.
The layer lives inside your code
The same call, with and without the layer. Traffic always travels straight from your application to the provider — BV‑SALA is not a middleman server and never sees your data from outside.
That green box is an npm package inside the application's code. That's why the key question is never “what do I install?” but “who wrote the code that calls the API?” — that person is who can install it. The one exception is a coding terminal like Claude Code: there the “bvsala claude” gateway sits in front without touching a single line of code.
Your case, in 10 seconds
Four ways of using AI, and what BV‑SALA can do in each one.
You pay a flat fee (or nothing): there is no per-token bill to reduce, and it's a closed product where nobody can place software between the app and its models. BV‑SALA's saving simply doesn't apply here — and no product can honestly promise it there.
Exactly the same case: flat subscription and closed product. Use Claude with peace of mind — there is no token spend to optimize from outside.
On a subscription, same as above: flat fee, nothing to install. With an API key there is a real per-token bill — and the meter is live: “bvsala claude” launches Claude Code through the local gateway and your spend shows up in your panel, token by token, without touching a line of code. Saving there is the next phase — first we measure for real.
The case BV‑SALA exists for. Your app calls the API with your key, the provider bills every token, and the layer installs in three steps: package, license, and wrapping the call. From the first request it returns a SavingsReport with the verified saving.
Estimate vs. measurement
The product has two different numbers, and they shouldn't be mixed.
The calculator in the pricing section projects your savings from your own numbers: requests, tokens and model. It's an honest projection — that's why it carries the “estimate” tag.
Every call returns a SavingsReport: the calls you never paid for and the net saving per request. Auditable, request by request, on your own infrastructure.
The full install, if you build an app
# 1 · the package pnpm add @bivelio/savings-layer # 2 · the license (from your dashboard) export BIVELIO_LICENSE_KEY=… # 3 · wrap the call — this is the entire code change const layer = createSavingsLayer({ provider, licenseKey, … }); const { text, report } = await layer.generate({ model, messages }); console.log(report.cost.netSavings) // ← the saving, measured