Skip to content
New: a free website for your business, live in 48 to 72 hoursWorkflow automation on n8n and Claude, built for your businessFixed price, agreed before we start · Live in 5 to 10 business days30-day money-back guarantee on every planProfessional firms · Agencies · E-commerceYou own every workflow, in your own n8nClaude API: your data is not used for trainingHuman approval on every sensitive stepFree automation audit, no obligationNew: a free website for your business, live in 48 to 72 hoursWorkflow automation on n8n and Claude, built for your businessFixed price, agreed before we start · Live in 5 to 10 business days30-day money-back guarantee on every planProfessional firms · Agencies · E-commerceYou own every workflow, in your own n8nClaude API: your data is not used for trainingHuman approval on every sensitive stepFree automation audit, no obligationNew: a free website for your business, live in 48 to 72 hoursWorkflow automation on n8n and Claude, built for your businessFixed price, agreed before we start · Live in 5 to 10 business days30-day money-back guarantee on every planProfessional firms · Agencies · E-commerceYou own every workflow, in your own n8nClaude API: your data is not used for trainingHuman approval on every sensitive stepFree automation audit, no obligation
PURIST
30 days
Money-back window
14 h/wk
Modeled time saved
99.97%
Uptime SLA
< 7 days
Deploy time
PURIST AI
Claude Opus 4.7 · n8n v1.71 · <80ms
What type of business are you running? I'll show you exactly which processes we'd automate first and your estimated ROI.
Powered by n8n + Claude Opus 4.7 Get my free automation plan →

Free Tools /AI

RAG Chunk & Embedding Cost Calculator

Plan a knowledge-base chatbot: chunks, embedding cost, vector storage and re-indexing cost from your document volume.

  • Free, no signup
  • Runs in your browser
  • Nothing stored
Inputs
Result Updates as you type · runs in your browser

Calculating…

Who uses it, and for what

Founder

Know what it costs to put your help center or contracts behind an AI assistant before you start.

Developer

Size the vector database plan and test how chunk size changes the number of vectors.

Ops

Budget the monthly cost of keeping the index fresh as documents change.

How this tool works

01

Converts pages to tokens

Documents × pages × words per page × 1.33 tokens per word.

02

Splits into overlapping chunks

Each new chunk advances by chunk size minus overlap, so more overlap means more chunks and higher cost.

03

Prices embeddings and storage

Embedding cost uses your price per million tokens; storage is chunks × dimensions × 4 bytes, before index overhead.

Frequently asked questions

What chunk size should I use?

A common starting point is 300 to 800 tokens with 10 to 20% overlap. Then test retrieval with 20 real questions and adjust.

Is embedding the main cost of RAG?

Usually not. Embedding is cheap; the larger cost is the language model reading the retrieved chunks on every question.

Why does storage matter?

Hosted vector databases price by stored vectors or memory. Higher dimensions and more chunks raise the plan you need.

Done for you

Want this running inside your business, automatically?

We build the workflow behind tools like this one, wired to your CRM, inbox and apps, and keep it running. Fixed price, from $390 a month.