Output Tokens
Token Output
Tokens the model generates back. Billed at a higher rate, because generating costs more than reading.
Output tokens are the tokens the model generates back. They are billed at a higher rate than input tokens, commonly around five times, since producing them takes more compute.
Everything the model writes counts: the prose you read, the code it emits, the tool calls, and any extended thinking it does before answering. That last one surprises people. Reasoning tokens are billed as output even when the harness never shows them, and turning up effort spends more of them.
Output tokens also set the pace of a session. The model reads input quickly but generates output one token at a time, so when a turn feels slow it is almost always the output being written, not the input being read. A long wait usually means a long answer is coming.
Related terms
Input Tokens
Tokens the harness sends on each request. Billed at a lower rate than output tokens.
Effort
A dial for how much reasoning the model does before it answers. More effort means a better shot at hard problems.
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.
Latency
How long you wait. The time to the first token matters more than the total.
Want this working inside your team?
It starts with one conversation about your workflow.