RAG cost

RAG Cost Calculator

Separate the cheap one-time indexing bill from the recurring query bill.

Free · no signup · runs in your browser

What this calculator is for

RAG systems have two different economic shapes: indexing is mostly tied to corpus size, while generation scales with every user query. Keeping them separate shows what will dominate as traffic grows.

The math

Monthly RAG = generation + vector/retrieval; indexing is modeled separately

Actual invoices can differ because providers may apply long-context pricing, caching rules, batch rates, tool-call fees, regional processing, negotiated contracts, taxes, or future pricing changes. Treat the output as a planning estimate.

Pricing sources

Current model rates are sourced from official provider pricing pages and verified on August 28, 2026. The methodology page records the source links and known limitations.

Frequently asked question

Is embedding usually the biggest RAG cost?

Often no. For active products, repeated generation over retrieved context can outweigh the one-time embedding bill, but your architecture and provider choices matter.

Can I use this estimate for a production budget?

Use it to create scenarios and catch order-of-magnitude mistakes. Before committing spend, verify the selected model's live provider pricing and compare the estimate with actual usage telemetry.