The Magic of AI

AI cost calculators

Fourteen calculators covering the costing questions that come up repeatedly when you build with AI. Each one runs entirely in your browser against the price index, which is re-verified from vendor pricing pages every week. None of them send your inputs anywhere.

Calculator

LLM API cost calculator

Price an LLM feature per month across 27 models from OpenAI, Anthropic, Google, Mistral and DeepSeek, with caching and batch discounts included.

Calculator

Token estimator and cost checker

Paste any text and estimate its token count, then see what it costs to send through 27 different LLM APIs. Runs entirely in your browser — nothing is uploaded.

Calculator

AI chatbot cost calculator

Price an AI chat feature including the history you resend every turn. Compare full history, sliding window and rolling summary side by side.

Calculator

RAG pipeline cost calculator

Price a retrieval-augmented generation pipeline end to end: initial embedding, re-embedding on updates, vector storage and the generation cost of every query.

Calculator

Prompt caching savings calculator

Find out how much prompt caching actually saves on your workload, and the hit rate you need before the cache-write premium pays for itself.

Calculator

Batch API savings calculator

See exactly what the 50% batch discount is worth on your workload, and how much of your traffic can tolerate the asynchronous turnaround.

Calculator

Self-hosting vs API break-even calculator

Compare renting a GPU to serve an open-weight model against paying per token, including utilisation, redundancy and the ops time nobody budgets for.

Calculator

Context window cost calculator

Check whether your document fits a model's context window, what a full-context call costs, and at what query volume retrieval becomes cheaper than stuffing.

Calculator

Fine-tuning vs prompting cost calculator

Fine-tuning buys a shorter prompt. Work out how many requests it takes for those saved tokens to repay the training run and the higher inference rate.

Calculator

AI image and video generation cost calculator

Price a generative image or video pipeline across Imagen, FLUX, Stable Diffusion, Veo, Kling, Luma and Runway — including the retries nobody budgets for.

Calculator

Speech-to-text and text-to-speech cost calculator

Price transcription and synthetic voice at your volume across OpenAI, Deepgram, AssemblyAI, Google and ElevenLabs, with the real cost per hour of audio.

Calculator

AI subscription vs API cost calculator

Compare paying per seat for AI assistants against building on the API directly, and find the team size where the answer flips.

Calculator

AI ROI calculator

Turn hours saved into money, subtract what the tooling costs, and get a payback period with a sensitivity range instead of a single optimistic number.

Calculator

Model switch savings calculator

Price your current workload on your current model, then on every alternative, and see exactly what a migration would save or cost per year.

How to choose one

If you are pricing a feature that calls an LLM, start with the LLM API cost calculator — it prices your workload against every model in the index at once and shows you the spread you are choosing within. If you already know which model you are using and want to find savings, the model switch savings calculator and the prompt caching savings calculator are the two highest-yield places to look.

For architecture decisions rather than pricing ones, the context window cost calculator and the RAG cost calculator answer the same question from opposite directions, and the self-hosting vs API calculator settles the one that generates the most arguments.

Every calculator has a full explainer beneath it covering what it models, what it deliberately leaves out, and the judgement you still have to make. The methodology page documents the conversions used throughout.