Short answer: make every indexing and retrieval decision attributable to a tenant before the Node. js service sends text to an embedding model or an LLM. Count with the model's tokenizer, reject unbudgeted work, and record actual usage after each call.
Source: [Dev.to](https://dev.to/finnianfox8297/6-nodejs-tenant-guardrails-for-cheap-invoice-rag-count-embeddings-and-llm-spend-570g)