Short answerTokens are the small pieces of text models read and write. Providers bill per million tokens, with separate prices for input and output. A rough rule of thumb is that a token is a few characters, so a word is often one to two tokens.
Input and output
Input tokens are everything you send: instructions, retrieved passages, history and the question. Output tokens are the answer. Both providers list separate prices per million input and output tokens (price comparison).
Estimating
- Count words in your instructions and multiply by about 1.5 for tokens (a rough estimate).
- Add the retrieved passages, history and question.
- Multiply by questions per month and apply the price.
The free checker shows an approximate token count for your pasted instructions (characters divided by four).
Lowering cost
Shorter instructions, fewer retrieved passages and output caps: ways to reduce cost. How much fits in one request: context window.
Check your GPT before you move it
Paste your instructions, file names and Actions schema into the free checker. It runs in your browser and builds a portable bundle. Nothing is uploaded.
Open the free checkerRelated guides
Sources
Pages describing other companies' products reflect their public documentation on the date shown and can go out of date.