PromptSpend MCP server

Know the tab before you build. Estimate, compare and understand what an AI feature will cost — from a catalog that re-checks itself every morning, so the numbers are never a year out of date.

→ Open PromptSpend  ·  free  ·  open source  ·  no accounts, no tracking  ·  Writing: What LLM Cost Calculators Get Wrong  ·  August 2026 Price Movement Report

<!-- PROMO-VIDEO. A bare user-attachments URL on its own line: GitHub turns that into an inline player. Markdown image or link syntax does NOT work, and a release-asset URL downloads instead of playing, so do not "tidy" this into a relative path or a link.

The URL only exists after the file is dragged into a comment box in the web UI AND that comment is submitted; an abandoned draft uploads the file but does not retain it, and the URL then 404s. Verify any replacement before committing - a live attachment answers an unsigned request with 302 or 403, never 404. See docs/PROMO.md. -->

https://github.com/user-attachments/assets/8ddf3e53-2a97-4d86-ac93-d09507c387de

2 minutes 8 &mdash; press play, and hit &#128266; to unmute (GitHub starts videos silent). &nbsp;·&nbsp; Download the MP4

Why this exists

Every LLM cost calculator on the web has the same failure mode: it is a snapshot. Someone builds it, hard-codes a dozen model prices, and within a few months the entire premise is wrong — the models it compares have been superseded and the prices it quotes no longer exist.

PromptSpend is built the other way round. The pricing pipeline is the product; the calculator is what sits on top of it. Every morning a GitHub Action re-fetches the catalog from independent sources, merges them under an explicit trust order, runs sanity checks, and either commits the result or opens a pull request for a human. Capture patterns are family-level, so a brand-new model version is picked up automatically without anyone touching code.

What it does

Shortened. The full README is on GitHub.