What a token is

Models read and write in tokens, which are neither characters nor words. Frequent chunks collapse into one token, so English averages about four characters per token and common words take just one. Korean spends close to one token per syllable, so the same volume costs more tokens. Billing is per token.

What counts as input is easy to miss

Input tokens are not just what the user typed this turn. The system prompt, any pasted documents, tool definitions, and in a chat the entire prior conversation all go back in on every turn. A ten-turn conversation sends far more input on the last turn than the first. This is the most common reason an estimate comes out too low.

Put the total of all of that into the input field above. For chat, multiplying by your average turn count lands closer to reality.

Korean runs about 2.7x

For the same character count, Korean spends two to three times the tokens of English. We approximate 2.7x. The multiplier itself does not vary by model, but the amount it adds does: from ₩148 to ₩1.54M a month depending on which model you pick. Building in Korean means the cost of choosing wrong is that much larger.

Read the breakdown across 194 models

What this number leaves out

The rates here are the published list prices from the catalogue. Real bills are usually lower. Prompt caching discounts the repeated prefix, batch requests are close to half price at some vendors, and a few models have volume tiers. In the other direction, sending images or audio adds tokens on top.

Won figures use the exchange rate from the last collection. Contracts and invoices are in dollars, so leave room for the rate to move when you set a budget.

How far to trust these numbers

If you entered token counts yourself, the arithmetic is exact. If you pasted text, tokenizers differ by model and the estimate can be off by around 25%. When you need precision, count once through the vendor's own token-counting API and put that number in the field above.