Input token
Last verified
Input tokens are everything you send: the system prompt, conversation history, retrieved context, tool definitions and tool results. They are billed at a lower rate than output tokens, typically 3–5× cheaper.
Because they include history, input token count grows through a conversation. In an agent loop this is the dominant cost driver — step 20 resends everything from steps 1–19. See cost control for autonomous agents.
Prompt caching exists specifically to reduce the cost of input tokens you send repeatedly.