Free tool · no signup

RAG Cost Calculator

What does a production RAG app actually cost to run? Estimate the one-time ingest, the per-query LLM spend, and your monthly bill. All prices are editable — defaults are representative list prices, not gospel.

Your corpus

Your traffic

Your LLM

Estimated monthly cost
$—
— per query · — queries/mo
LLM input LLM output Embeddings
One-time ingest (embed corpus)
Monthly · LLM (answers)
Monthly · embeddings (queries + refresh)
Corpus size
Pricing it out means you're building it for real.
CiteKit ships the production pipeline — retrieval, citations, RLS, and an eval harness — so you don't hand-roll it.
Get CiteKit — $129
How RAG cost works

Three line items, and one usually dominates.

1. Ingest (one-time): you embed your whole corpus once. Cheap per token, but scales with corpus size. 2. Per-query embeddings: each question is embedded — tiny. 3. Per-query LLM: the retrieved chunks become input tokens, plus the answer as output tokens. At any real query volume, the LLM is almost always the bill.

The lever most teams miss: retrieval quality. Sending 6 precise chunks instead of 15 mediocre ones cuts input tokens — and improves answers — more than swapping to a cheaper model. That's why CiteKit ships an eval harness: cheaper and better.

Get the RAG production checklist — 25 items across retrieval, eval, security, deploy.