AI FinOpsmetering proxy + margin intelligence

Know your margin
on every customer.

Marginary ties every LLM call to a customer and joins it with your Stripe revenue. So you can see where your AI product makes money and where it burns it, for every customer, feature, and agent run.

Estimate your AI margin

One baseURL change. Prompts never stored. Metering failures never block your calls.

MetersOpenAIAnthropic
JoinsStripe
Adapters (soon)LiteLLMHeliconeOpenTelemetry
01Setup

Live in minutes, not sprints.

No SDK to adopt, no agent to deploy. Marginary is a streaming-safe proxy in front of the APIs you already call. Your provider keys pass through untouched. Marginary never stores them and never logs them.

STEP 1 / POINT

Change one line

Swap your baseURL. Requests stream through byte for byte. If our metering breaks, your calls still go through.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.marginary.xanova.ai/v1",  // ← the only change
  defaultHeaders: { "X-TokenOps-Key": env.TOKENOPS_KEY },
});
STEP 2 / TAG

Attach business context

Headers, not payload changes. Every request lands attributed to a customer, feature, workflow, or agent run. Attribution happens on your server, so end users can't spoof it.

await client.chat.completions.create(body, {
  headers: {
    "X-TokenOps-Customer": "acme",
    "X-TokenOps-Feature": "support_chat",
    "X-TokenOps-Agent-Run": "run_4921",
  },
});
STEP 3 / JOIN

Connect revenue

Sync Stripe subscriptions read-only (or post revenue manually). Cost meets revenue, and every customer gets a live gross margin.

$ GET /api/margin

acme      revenue $199.00
          cost    $312.40
          margin  −57%  ● losing money
02Product

Unit economics as infrastructure.

Built for the money path. Prices live in a database, not in code, and the math is fixed-point. If we don't know a model's price, we say unknown instead of guessing.

Attribution you can trust

Cost is attributed at the proxy, keyed by your server's API key and headers. Not self-reported from the client, and not spoofable by end users. Per customer, user, feature, workflow, and agent run.

Margin, not just spend

Stripe subscriptions sync read-only into a revenue join, and every customer gets a live gross margin. Worst first, so the account quietly eating your pricing plan is row one.

Free-tier burn detection

Free plans with real AI cost are flagged before they compound. Know which signups to convert, cap, or cut, with the dollar amount attached.

Budgets that act

Soft alerts or a hard block at the proxy, per org, customer, or feature. The only sanctioned way a request gets rejected, and the only 402 you'll ever be glad to see.

Fail-open by design

Streaming passes through byte-for-byte. If our recorder, pricing lookup, or budget engine fails, your customer's AI call still completes. Auth is the only thing that fails closed.

Metadata only, always

Prompts and completions are never stored, logged, or traced. Not in the database, not in error logs, not anywhere. Token counts, models, latency, and your business tags. That's the entire record.

03Positioning

Cost tracking is a commodity.
Margin is the business.

Great tools already exist for traces, routing, and invoices. None of them answer the founder's question:

“Which customers do I lose money on?”

Answering it takes joining per-request cost to per-customer revenue. And revenue lives in Stripe, not in your traces.

CategoryMain buyerPrimary value
LLM observabilityLangfuse · HeliconeAI engineersDebug traces and prompts
Model gatewaysLiteLLM · PortkeyPlatform teamsRouting, keys, rate limits
Usage billingOpenMeter · LagoBilling & RevOpsMetering and invoicing your customers
MarginaryAI FinOpsFounders, SaaS & ops teamsCost vs revenue: gross margin per customer
04AI cost calculator

What does your AI actually cost?

Back-of-the-envelope unit economics for your AI feature. List prices, no caching discounts. Production traffic is spikier than any average, which is rather the point.

05Pricing

Flat pricing. Obviously.

A margin product that wrecked your margin with usage-based billing would be a bad joke. Early access pricing. The founding cohort locks it in.

Indie
$19 /mo
Solo builders
  • 1 project
  • 100k tracked requests / mo
  • Cost by customer & feature
  • Budgets & alerts
  • 30-day retention
Get early access
Startup
$79 /mo
Early SaaS teams
  • 3 projects
  • 1M tracked requests / mo
  • Stripe margin join
  • Free-tier burn detection
  • Hard budget blocks
  • 90-day retention
Get early access
Growth
$199 /mo
Higher-volume apps
  • 10 projects
  • 5M tracked requests / mo
  • Everything in Startup
  • Agent-run economics (soon)
  • 12-month retention
Get early access
Agency
$299 /mo
Multiple client apps
  • Unlimited client workspaces
  • Per-client cost reports
  • Markup invoicing (soon)
  • Everything in Growth
Get early access

Your margin is already moving.
See it.

We're onboarding a founding cohort of AI SaaS teams spending $100 to $10k a month on model APIs. Setup is one line. The first worst-margin customer usually shows up the same day.

Book a free margin audit