Queries per month
5,000
Search or answer requests that call the generation model.
RAG cost planning
RAG Cost Calculator
Plan retrieval-augmented generation costs by modeling query volume, context tokens, and answer length. No documents or private text are collected.
Scenario assumptions
Start with these editable numeric assumptions, then adjust the calculator fields to match your own traffic and token usage.
Retrieved context tokens
2,500
Chunks, citations, and source excerpts included with each query.
Question and instructions
500 tokens
User question, system guidance, and output formatting instructions.
Output tokens per answer
700
Average generated answer length after retrieval.
Estimated results
Run the calculator to see projected cost and usage volume.
Enter your usage details, then select Calculate estimate to see your projected cost.
Estimated cost = input usage cost + output usage cost + supported optional charges.
How to read the output
Use the result as a planning estimate, then validate against provider pricing and real usage once the workflow is live.
Generation cost
RAG spend is often driven by the size of retrieved context sent into the model for every query.
Context sensitivity
Run low and high context scenarios to see how chunk count and context length affect monthly cost.
Embedding note
If your provider charges separately for embeddings, estimate indexing and query embedding costs alongside this generation estimate.
Models to consider
These options come from the central model data and are suggestions to evaluate, not claims that one model is best for every workload.
Anthropic
Claude Sonnet 5
Text model to evaluate for retrieval answer generation.
Input $2.00 / 1M, output $10.00 / 1M.
Open modelAnthropic
Claude Sonnet 4.6
Text model to evaluate for retrieval answer generation.
Input $3.00 / 1M, output $15.00 / 1M.
Open modelGemini
Gemini 3.5 Flash
Text model to evaluate for retrieval answer generation.
Input $1.50 / 1M, output $9.00 / 1M.
Open modelDeepSeek
DeepSeek-V4-Flash
Text model to evaluate for retrieval answer generation.
Input $0.22 / 1M, output $0.66 / 1M.
Open modelRelated planning pages
Continue to a semantically related calculator, provider, or guide without entering private content.
AI API Pricing guide
Read ai api pricing guide before refining calculator assumptions.
Input vs Output Tokens guide
Read input vs output tokens guide before refining calculator assumptions.
AI API Cost Calculator
Estimate provider, model, token, and monthly AI API cost.
AI Token Calculator
Forecast spend from known input and output token volumes.
RAG app FAQ
Short answers for estimating this scenario without sharing private prompts, documents, or customer data.
What affects RAG app cost the most?
The biggest drivers are query volume, retrieved context size, answer length, selected model price, and whether embeddings are billed separately.
Are retrieved documents included in the URL?
No. This calculator only uses numeric token assumptions and safe model/provider slugs, never raw document text.
How should I estimate retrieved context tokens?
Start with average chunk size multiplied by the number of chunks sent to the model, then add question and instruction tokens.