What Does This Mean?
The maximum number of tokens a language model can handle in one request, set by its context window; text beyond the limit must be shortened, split or dropped. Tokens are the integer-indexed pieces of text, produced by a tokenizer such as byte-pair encoding, that the model actually processes. Some limits cover input and output together, others cap them separately.
EXPLAINER
Bits & Proofs · original source ↗
The preview image is loaded from YouTube when this page opens, so YouTube receives your IP address and browser details, as with any request to another site. The video itself loads only after you click play. Details in our Terms
REAL-WORLD EXAMPLE
""The document went over the token limit, so the model cut off the end.""
LORE & ORIGIN
The idea follows from how large language models work: attention is computed within a context window that bounds how much text the model considers at once. Wikipedia's article on large language models gives early examples, such as GPT-2 with a context window of about 1,000 tokens, and notes that context length is often written into model names, as in 128K-token variants.
MENTIONS OVER TIME
Radar observation data not yet available for this term.
RELATED SEARCHES
TOP PLATFORMS
Not enough Radar data yet to show a platform breakdown.
WHEN DID YOU FIRST HEAR THIS?
CLICK AN OPTION BELOW TO CAST YOUR VOTE.
[ VOTE TO REVEAL COMMUNITY RESULTS ]