SpendTag — Per-customer LLM cost attribution proxy

See exactly which customer is burning your OpenAI budget

Problem

Once the AI bill stops being a rounding error, the first question is "which customer is that," but provider dashboards have no concept of your tenants; instrumenting every call site with logging is the obvious fix, yet nobody wants to touch production code for it.

Solution

A proxy layer: swap the base URL, keep your own provider key, add a customer-id and feature-name header to each request; the proxy attributes cost per request and shows real-time views by customer and feature, with budget alerts and optional model downgrade when a tenant exceeds its cap.

Users

SaaS teams running multi-tenant products on OpenAI/Anthropic APIs, AI app developers and indie hackers.

MVP

OpenAI-compatible proxy endpoint; cost attribution by customer-id and feature; real-time dashboard; daily/monthly per-tenant budget alerts; three-line integration docs; content-logging off by default.

Revenue

Tiered subscription by attributed request volume; free up to 100k requests/month; enterprise self-hosted plan with SSO.

Why now

Agent and AI features are inflating API bills fast while attribution tooling is nearly absent; a proxy offers non-invasive adoption and an indie developer can ship a first version in days.