Input tokens only
Krun One scores the options you send. It does not generate a completion, so there are no output tokens, andusage has no output_tokens field.
How input tokens are counted
- Tokens are counted with the Krun One tokenizer, by the model itself. They are not estimated.
- Each question is scored as its own sequence: the context plus that question’s options.
input_tokensis the sum over all questions in the request. - Adding questions to a request adds tokens, because the context is read once per question.
Media inputs
Images, documents and audio are counted as input tokens too, and they produce more tokens than a short text. As a rough guide:input_tokens can be null in the rare case that the model backend does not report it.