Decisions · Notes

AI token cost calculator: what your usage costs on 18 models

Enter your monthly input and output, in tokens or words, and see the cost on GPT, Claude, Gemini, DeepSeek, Mistral, Grok and more at today's list prices.

Alan Lui · 19 November 2026

Type how much text your app or agent sends and receives in a month, and see what it costs on 18 AI models, at each provider's own list price. Prices were read off the providers' pricing pages on 19 November 2026: standard rate, no batch discount, no cache hits. One token is about four characters of English, so 1,000 tokens is roughly 750 words (what a token is).

How it works

Cost = input tokens × the input price + output tokens × the output price, each per million tokens. Words are converted at 4 characters per token (Perplexity's guide) and about 5 characters per word, so 1 million words is about 1.33 million tokens; for other languages and code the real count is usually higher. Reasoning models also bill their hidden thinking as output, so measure a few real runs before trusting any estimate, this one included.

What it leaves out

Discounts and surcharges that can move a real bill a long way: cached input (90% or more off at most providers), batch jobs (half price at OpenAI, Anthropic, Google and Mistral), DeepSeek's off-peak half price, long-prompt surcharges and regional endpoints. Each is set out on What do AI model APIs cost?. Google's Gemini 4 Carbon and Argon double to $4 / $20 per million tokens on 1 December 2026 (all dated price changes).

Prices from each provider's own pricing page, read on 19 November 2026; the source for each model is linked in the table. Developers paying for Claude by the token can compare with a flat plan on Claude Code pricing.

The page this is about: What does an AI model API really cost to run? — every figure sourced to the vendor's own page, with the date it was checked.