llm-spend-guardStop your LLM API bills from spiraling

Enforce real-time token budgets for OpenAI, Anthropic Claude, and Google Gemini API calls in Node.js

Pre-request Blocking

Stops overspending before the API call is made, not after. No money wasted on runaway requests.

Single unified API for OpenAI (GPT-4o, GPT-4), Anthropic Claude, and Google Gemini.

Enforce limits at global, per-user, per-session, and per-route levels simultaneously.

Redis storage, Express/Next.js middleware, TypeScript-first. 18.6KB lightweight bundle.