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 / 3Annual estimate
$15.2K
Total token OpEx for 50 employees · Claude Sonnet 4
Recommended models for this workload
- Claude Sonnet 4 cost calculator — $3 in / $15 out per 1M tokens.
- Gemini 2.5 Pro cost calculator — $1.25 in / $10 out per 1M tokens.
- GPT-5 mini cost calculator — $0.25 in / $2 out per 1M tokens.
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
Token usage for operations managers
Model the AI footprint of operations leaders across process, SOP and analytics workflows.
Token usage for management consultants
Estimate AI consumption for analysts, managers and partners in a consulting firm.
AI cost for consulting firms
Model the full AI operating cost of a modern consulting firm — per consultant, per engagement, per practice.
AI cost for law firms
Quantify the real cost of AI-enabled contract review, drafting and research across an entire law firm.
AI agent cost calculator
Estimate the per-task and per-month cost of deploying autonomous AI agents.
AI code generation cost calculator
Estimate per-engineer and per-team cost of AI coding assistants.
AI code review cost calculator
Calculate the cost of automated AI code review and PR analysis.
AI customer support cost calculator
Model AI cost per conversation, per agent and per ticket volume.