← Glossary / 41 of 100
n. / Models and tokens
Input tokens
Definition
Input tokens are the tokens you send to a model in a call: the system prompt, conversation history, retrieved documents, tool definitions and the user message. They are usually billed at a lower rate than output tokens.
In more detail
In agents the input grows with every step, because each loop resends the earlier messages and tool results. That makes input tokens the biggest cost driver in long runs. Prompt caching, shorter history and tighter retrieval are the main ways to reduce them.
Example
An agent step sends a 900-token system prompt, 1,500 tokens of chat history and 2,000 tokens of retrieved text. The call used 4,400 input tokens before the model wrote a word.
