RAG Cost Calculator
Estimate a RAG pipeline monthly bill: embedding tokens × embed $/1M, plus retrieval/rerank calls × unit price, plus LLM input/output tokens × model $/1M. Pick a model preset or enter custom rates. Sum is the USD total. Estimates only; each vendor’s official pricing prevails.
Math runs in your browser. Nothing is uploaded.
Embedding cost
—
Retrieval cost
—
LLM token cost
—
Total USD cost
—
Estimates only; official vendor pricing prevails (2026-10-30). Total = embed + retrieval + LLM input/output at your $/1M rates.
AI Agent Cost Calculator · LLM API Cost Calculator · Gemini Grounding Cost Calculator · OpenAI Token Cost Calculator
More in this group
- Algolia Cost Calculator Algolia Free · Grow · Grow+ → monthly $.
- MongoDB Atlas Cost Calculator Atlas M0 · Flex · Dedicated → monthly $.
- LLM Observability Cost Comparison Langfuse vs Braintrust vs LangSmith vs Helicone for one workload.
- Langfuse Cost Calculator Langfuse units (traces + observations + scores) → monthly cost.
- Braintrust Cost Calculator Braintrust GB processed + scores + retention → monthly cost.
- Vector Database Cost Comparison Pinecone vs Upstash Vector monthly cost for one workload.
- Pinecone Cost Calculator Pinecone storage + WU + RU vs $50 minimum → monthly cost.
- Upstash Vector Cost Calculator Upstash Vector PAYG vs Fixed $60 + break-even.
How it works
- How is RAG cost calculated?
- Total USD = (embed tokens ÷ 1M × embed $/1M) + (retrieval calls × unit price) + (LLM input ÷ 1M × in $/1M) + (LLM output ÷ 1M × out $/1M).
- What default embed price is used?
- Defaults to $0.15 per 1M tokens (Gemini Embedding text list). Override for OpenAI or other embedders.
- What if retrieval is free or bundled?
- Set retrieval unit price to 0. The calculator still shows embed and LLM lines.
- Can I use any LLM rates?
- Yes—pick a preset or type custom $/1M. Sibling OpenAI, Claude, Gemini, and Grok pages share the same token formula.
- Are results billing-grade?
- No. Planning estimates only; official invoices prevail.