Input Tokens
Token Input
Tokens the harness sends on each request. Billed at a lower rate than output tokens.
Input tokens are the tokens the harness sends on each request: the system prompt, the conversation history, the tool results, everything the model reads before it writes. They are billed at a lower rate than output tokens, because processing them costs less than generating them.
In agentic work, input tokens make up most of the bill. The model is stateless, so each turn re-sends the entire session as input. The input for turn fifty contains the previous forty-nine turns. A single request might produce a few hundred output tokens but re-send a hundred thousand input tokens of accumulated history.
The prefix cache reduces the cost, and clearing or compacting between tasks reduces it further. When the bill is high but the agent is barely writing anything, the input side is where to look.
Related terms
Output Tokens
Tokens the model generates back. Billed at a higher rate, because generating costs more than reading.
Cache Tokens
Input tokens the provider cached from a previous request, billed at a much lower rate.
Prefix Cache
The provider-side store that lets consecutive requests skip re-processing a shared prefix.
Token
The unit a model reads and writes. Roughly word-sized, but not exactly.
Cost per Token
What you pay for each unit of text the model reads or writes.
Want this working inside your team?
It starts with one conversation about your workflow.