TRANSFORMERS & LLMs • 70 / 397
Follow text from characters to tokens, attention, transformers and generation.
Maximum Output
Maximum output is the configured cap on how many tokens the model may generate in a response.
Think of it like
Think of Maximum Output as part of a very fast reader that repeatedly decides what information matters and what should come next.
Real life
Autocomplete, translation and chat assistants depend on concepts such as Maximum Output.
SRE lens
A tight output cap can protect latency and spend in automation.
Remember thisMaximum output is the configured cap on how many tokens the model may generate in a response.