See where your AI spend goes.

Marginal tracks the cost of every LLM call and slices it by the fields you care about — customer, feature, environment, model.

Start tracking Read the docs

import { Marginal } from "marginal-sdk";

const marginal = new Marginal({ apiKey: process.env.MARGINAL_API_KEY });

const response = await openai.chat.completions.create({ /* … */ });

marginal.track({
  provider: "openai",
  model: response.model,
  usage: response.usage,
  fields: { customer: "acme-corp", feature: "support-bot" },
});

One call per LLM request — the cost is computed server-side from the model price catalog.

Slice by any field

Register your vocabulary — customer, feature, environment — and group or filter spend by it. Unregistered keys are stripped and reported back, so dashboards stay clean.

LLM-aware pricing

Send provider, model, and the response's usage object; cost is computed server-side against a daily-synced model price catalog. Unpriced models are surfaced, never a silent $0.

SDKs that stay out of the way

TypeScript and Python, zero dependencies, buffered and fire-and-forget. track() never throws and never blocks your request path.