Show HN: Marginal – See which customers and features drive your AI API costs

Marginal, a new cost-observability tool for AI API usage, launched with TypeScript and Python SDKs plus an HTTP API, enabling developers to track the cost of every LLM call and slice spend by customer, feature, or model. The tool computes costs server-side against a daily-synced price catalog, flags unpriced models instead of averaging them away, and integrates via a single track() call per request. Marginal aims to answer 'why was the bill that high?' by automatically charting spend across dimensions and logging every API request outcome.

TypeScript SDK · Python SDK · HTTP API 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, model. npm install marginal-sdk · pip install marginal-sdk The dashboard From “the bill doubled” to a named cause Slice spend by what matters in your product, see every dimension charted automatically, and check exactly what your integration sent. Spot the spike without building a chart Insights charts spend for every dimension automatically — each model, provider, and registered field gets its own chart. No setup, no query builder. Know exactly what landed Every API request is logged with its outcome — accepted counts, rejected events and why, stripped keys, unpriced models. Debug your integration without guessing. Never a silent $0 Unknown model? The event still lands, flagged as unpriced — visible in the dashboard and the API response, never averaged away. Set a custom price and it applies at ingest. How it works One call per LLM request. That's the whole integration. - 1 Pick your connection npm install marginal-sdk , pip install marginal-sdk , or no install at all — POST JSON to the HTTP API from any language. The SDKs are zero-dependency, buffered, fire-and-forget: track never throws and never blocks your request path. - 2 Track each LLM call Name the provider, paste the response's model and usage as-is — Marginal detects the usage shape and computes the cost server-side against a daily-synced model price catalog. - 3 Slice your spend Group and filter by customer, feature, model — any field you register. Save the views you keep coming back to. js 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" }, } ; python import os from marginal import Marginal marginal = Marginal api key=os.environ "MARGINAL API KEY" response = client.chat.completions.create ... marginal.track provider="openai", model=response.model, usage=response.usage.model dump , fields={"customer": "acme-corp", "feature": "support-bot"}, curl -X POST https://api.marginalhq.com/v1/events \ -H "Authorization: Bearer $MARGINAL API KEY" \ -H "Content-Type: application/json" \ -d '{ "events": { "provider": "openai", "model": "gpt-4o-2024-08-06", "usage": { "prompt tokens": 2006, "completion tokens": 300 }, "fields": { "customer": "acme-corp", "feature": "support-bot" } } }' The cost lands computed, priced at that day's catalog rates — no token math in your codebase. Cost observability Built to answer “why was the bill that high?” Slice by any field Register your vocabulary — customer, feature, anything you slice by — then 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 from a daily-synced price catalog, with per-project overrides. Prices are frozen at ingest. Saved views Any Explorer state — range, filters, group-by — saves as a named view. The questions you ask every week are one click away. SDKs that stay out of the way TypeScript and Python, zero dependencies. Events buffer locally and flush in batches in the background; network failures retry and then warn — your app never notices. Prefer no SDK? The HTTP API is a single JSON POST. Let your coding agent do the integration Paste marginalhq.com/llms.txt /llms.txt into Claude Code, Cursor, or any coding assistant and it has everything it needs to wire up Marginal — or follow the per-provider recipes yourself. Integration recipes /docs/integrations From zero to a live spend dashboard in five minutes. Create a project, register your fields, drop in one track call. Your next deploy starts answering questions.