- Home
- AI support
- Token & Cost Calculator
Token & Cost Calculator
Paste a prompt or a file. The page estimates the tokens, shows how much of the context window it fills, and multiplies by the price you enter.
What it is for?Prices change often and differ per model. Copy them from the provider’s pricing page. Cached input and batch discounts are not included.
What it is for?
A token is a piece of text a model reads: often a whole short word in English, a part of a word in Turkish, a symbol or a few characters in code. Context windows, rate limits and prices are all counted in tokens, so the same page costs more in some languages than in others.
How the estimate works
Each model has its own tokenizer, and this page does not ship them. It counts characters and words and applies a ratio per text type: about 4 characters per token for English, fewer for Turkish, code and JSON. Expect the real count to land within roughly 15 percent. For an exact number, use the provider’s token counting endpoint.
Reading the result
The bar adds the expected reply to the prompt, because the reply has to fit in the same window. Leave room: the system prompt, tool definitions and earlier messages in a chat also use the window. Output tokens usually cost several times more than input tokens.