# Output tokens

Concept · [Building with AI](https://ecosystem.samcarlton.com/ai)

Also called: output token, completion tokens, generated tokens, tokens out, output cost

The [tokens](https://ecosystem.samcarlton.com/token) the model writes back. They cost more per token than input because producing text takes more computing work, and a model's [reasoning](https://ecosystem.samcarlton.com/reasoning-model) steps usually count as output too.

**For example:** Asking for a one-line answer instead of a three-page report cuts the output tokens, and the cost, of every call.

## Connects to (7)

- [Token](https://ecosystem.samcarlton.com/token): In AI, a small chunk of text, roughly a word or a piece of a word, that an LLM reads and writes.
- [Input tokens](https://ecosystem.samcarlton.com/input-tokens): The tokens an AI product sends to the model on each request: the instructions, the conversation so far, files and tool results.
- [Effort](https://ecosystem.samcarlton.com/effort): A setting that tells a reasoning model how much thinking to do before it answers.
- [Reasoning model](https://ecosystem.samcarlton.com/reasoning-model): A model, or a mode of a model, that works through a problem in intermediate steps before it answers.
- [Inference](https://ecosystem.samcarlton.com/inference): An AI model producing an answer to a request.
- [Next-token prediction](https://ecosystem.samcarlton.com/next-token-prediction): The one job a language model performs.
- [Model provider request](https://ecosystem.samcarlton.com/model-provider-request): One trip from an AI product to the model provider and back.

Map view: https://ecosystem.samcarlton.com/output-tokens