- Glossary
- Token
What is a token in an LLM?
A token is the unit of text a language model reads and writes. Models split text into tokens, which are often word fragments: one token is roughly four characters of English. Providers price requests per token and limit how many tokens a request may contain, so token counts drive both cost and context limits.
Also called: LLM token · Last updated
Input and output tokens
Input tokens are everything you send: system prompt, conversation history, tool definitions, and documents. Output tokens are what the model generates. Output tokens usually cost several times more than input tokens, so long answers cost more than long prompts of the same size.
Counts differ between models
Each model family uses its own tokenizer, so the same text produces a different count on different models. Treat any count from one tokenizer as an estimate for another model, and rely on the usage block in the API response for billing.