AI Unit Economics

RAG Retrieval Cost Calculator

How much does RAG retrieval cost per query when you change chunk depth? Compare baseline and candidate chunk assumptions before changing retrieval settings in production.

How this tool works

This simulator runs the deterministic RAG economics model twice with shared assumptions and isolates what chunk count and chunk size changes do to cost per user and break-even price.

How It Works

  1. Set provider/model plus workload assumptions used in both runs.
  2. Set baseline and candidate chunk assumptions.
  3. Compare retrieval tokens, cost deltas, and break-even deltas.

Formula

retrieval_tokens_per_request = retrieved_chunks * tokens_per_chunk

total_cost_delta = cost_candidate - cost_baseline

Assumptions and Units

  • Currency: USD
  • Token unit: token
  • Baseline and candidate use the same non-chunk assumptions
  • Pricing source: daily snapshot in repo, no runtime scraping

Related resources: Cache Savings Simulator, Context Window Cost Calculator, RAG Cost per User, How To Choose Chunk Size and Chunk Count.

Loading chunk impact simulator...