AI CostBase

What does it really cost to run AI?

Model APIs quote a token price. Production bills include speech, telephony, vector databases, retries, evals and human review — LLM inference is often only 15–35% of the total. These calculators do the math on all of it. Free, no signup.

🧮 AI Project Total CostThe full stack: inference + voice + images + vector DB + overhead. Start here. 📞 Voice Agent CostSTT + LLM + TTS + telephony, per call and per month. ✉️ AI SDR CostResearch + personalization + verification, per lead. 📚 RAG Pipeline CostOne-time embedding + per-query inference + vector DB. 💬 Chatbot CostSupport or product assistant, per conversation. 🎓 Fine-tuning CostTraining tokens × epochs + serving cost after launch. 🖼️ Image API CostGeneration at scale, per campaign and per month. 🧷 Embedding CostIndexing and refresh cost for any corpus size.

Why trust the numbers?

Every model price on this site is pulled daily, automatically from OpenRouter's public pricing API and rendered into the calculators as-is — no hand-maintained tables. Embedding endpoints aren't listed by that API, so they come from a second public source (LiteLLM's community price list), marked as such. Rates that aren't per-token (speech, telephony, vector DB) are editable inputs with the source and date stated next to them. Our method page shows every formula. If a number can't be sourced, it isn't shown.

→ See today's full model price table  ·  → What changed in prices recently

Start with the whole bill, not the token price

Every provider publishes a per-token price and none of them publishes the bill. A production AI system pays for the services wrapped around the model, the data layer underneath it, and the operational overhead above it — so an estimate built from token pricing alone is not conservative, it is simply incomplete.

The mistake almost every AI cost estimate makes

CostOn the vendor's pricing page?Who bills it
LLM inferenceYesYour model provider
Speech, telephony, image APIsNo — different vendors entirelyTwo or three more suppliers
Vector database and retrieval storageNoA hosting provider
Evals, tracing, observabilityNoAn observability vendor
Retries and fallbacksNo — invisible by designYour model provider again
Human review and escalationNoYour own payroll

Published breakdowns of running production systems land on the same range repeatedly: LLM inference accounts for roughly 15–35% of total operating cost. That is why this site is organised around the stack rather than around the token price. It is also why the most common cost question — "which model is cheapest?" — so often turns out to be the wrong question.

What is on this site

PageAnswers
AI project total costWhat does the whole thing cost per month, and what share is the model?
Voice agent costCost per call and per minute across speech, model, synthesis and telephony.
AI SDR costCost per lead and, more usefully, cost per meeting booked.
RAG pipeline costOne-time indexing, recurring query cost, and the refresh loop.
Chatbot costCost per conversation, and why length beats volume.
Fine-tuning costOne-time training versus monthly serving, and whether it pays back.
Image API costGeneration at scale, with regeneration overhead included.
Embedding costIndexing any corpus, and the query loop that never stops.
Model price tableToday's per-token prices for every model, with CSV download.
Price changesWhat moved overnight, and by how much.