AI Economics v1.01About AI Economics v1.01
AI Economics v1.01 exists to answer one question quickly and accurately: what will this actually cost? LLM API pricing varies widely across providers and model tiers, and it's easy to underestimate cost at scale when you're only looking at a single request. We built a calculator that makes the full picture — per-request, daily, monthly, and yearly cost — visible in a few clicks, backed by a maintained pricing dataset instead of numbers copied from a blog post that's gone stale.
Alongside the calculator, we publish a token counter for measuring real prompts, a full model directory for browsing pricing and context windows side by side, and tools for exploring self-hosting open-weight models on Azure GPU VMs.
How the math works
A token is roughly 4 characters, or about ¾ of a word, in typical English text. Providers bill input and output tokens at different rates, per million tokens:
cost = (input_tokens × input_price + output_tokens × output_price) / 1,000,000 × requests
Prompt caching can cut repeated-context input costs by 50–90% on providers that support it — see the model's cached input price where available.
Frequently asked questions
Input tokens are everything you send to the model — system prompt, conversation history, and the user's message. Output tokens are what the model generates in response. Most providers bill these at different rates, with output usually costing 3-5x more per token.