Use case

Estimate retrieval-augmented generation cost for enterprise knowledge bases.

RAG systems add a persistent indexing baseline and per-query retrieval overhead on top of LLM cost. This calculator models the full lifecycle: embedding, indexing, retrieval and generation.

Tokens / event

5K – 50K

Events / user / day

10 – 80

Typical cost range

$0.01 – $0.20 per query

Recommended models

3

Run the numbers for your team

Open full calculator →

Calculator

Configure your team

Embedded in core workflows. Mixed adoption.

AI-assisted tasks

3 / 3

Annual estimate

$15.2K

Total token OpEx for 50 employees · Claude Sonnet 4

Tokens per employee / year54.00M
Total tokens / year2.70B
Input tokens2.11B78%
Output tokens594.00M22%
Cost per employee / year$304.56
Avg daily tokens / employee225.0K
Blended price$3.00 in · $15.00 out / 1M tokens
Working days assumed220
Task coverage100%

Recommended models for this workload

Frequently asked questions

What dominates RAG cost: indexing or queries?

For knowledge bases under 100M tokens, queries dominate. Above that, embedding refresh on document updates becomes the larger line item.

Related calculators and guides