For sale
LLM Cost Attribution Tool with Network-Layer Monitoring
Asking price
$35,000
Already have an account? Sign in
- Traffic
- 0-1K visits/mo
- Based in
- United States of America
- Listed
100% held in escrow until handoff
About this listing
Halton Meter meters LLM API spend at the network layer. A local daemon sits at the system proxy (mitmproxy with a locally trusted root CA), captures every request to Anthropic, OpenAI, Google and xAI, prices it from a versioned rates corpus, and attributes cost to project, machine and person. Because capture happens below the SDK, it works with any client, including tools that expose no hooks at all, such as Claude Code on a Max subscription. No competitor meters that surface.
A cloud dashboard adds workspaces, org roles, per-project and per-person reports, a rule-based optimisation recommender, and month-end reconciliation against the provider's own billing export. The rates corpus covers 60 rate rows resolving 75 model IDs with five priced fields each (input, output, thinking, cache read, cache write), a source string on every row, and a CI drift gate that blocks releases when the vendored rates diverge from the published mirror.
It is shipped, not a prototype. Daemon v0.6.4 is on PyPI with tagged releases from v0.6.0. The cloud has run in production on AWS since May 2026 with Clerk-managed Solo and Team self-serve billing. We have metered our own Anthropic spend with it since launch, roughly $9,900 across 102,000 requests and 368M tokens by mid-July 2026, with closed months reconciled against real Anthropic billing CSVs.
Sold as one lot: daemon, cloud backend and dashboard, rates corpus, two landing sites, docs site, design system, investor deck, domains, PyPI name and GitHub org, with full copyright assignment. Built by one operator with Claude as the second engineer; every repo carries its decision history in memory/ and docs/, which is why a newcomer can read it.
