Output token
Also: output tokens, completion tokens
A piece of text the model writes. Output is usually priced higher than input.
The fuller definition
An output token is a unit generated by a model as part of its response. Providers may separately account for visible output and other model-specific processing.
2,000
8,000
4,000
2,000
A hypothetical 16,000-token budget. Real limits and token accounting depend on the model. Saving a file outside this budget does not mean it is present in the current context, and a passage inside it is not guaranteed equal attention.
A concrete example
A long answer requires more generated tokens than a short label.
The distinction that matters
Output limits, context limits, and billable-token accounting are related but not identical.
Related terms
Token
A piece of text, often part of a word, that the model actually works with. Models read and write tokens, not whole words.
Prompting & contextInput token
A piece of text you send to the model, including documents and instructions.
FoundationsContext window
How much text the model can hold in mind at once: your question, the documents you added, and the conversation so far. Anything outside it is invisible to the model.
Where it is taught
Give AI a brief it can actually followSource and further reading
Anthropic · Context engineeringThe definition and example are written for this library. The link gives background, official documentation or legal authority as labelled. Legal scope depends on the jurisdiction and current text; product features depend on release and settings.