Your session has been flagged for unusual activity.
Please confirm you're human to continue.
A decoding method that samples the next token from the smallest set whose probabilities add up to p, avoiding both repetitive and incoherent text.
Holtzman et al. (2020) showed that always choosing the most likely tokens makes generated text bland and repetitive, while sampling from the full distribution makes it incoherent. Their fix, nucleus (top-p) sampling, restricts each choice to the dynamic "nucleus" of tokens that together hold probability mass p, then samples from that set.
Top-p is paired with temperature in most chat APIs to balance variety against coherence; the related top-k method instead keeps a fixed number of candidates.
Primary, peer-reviewed and archival sources for this definition.
Run the same prompt across ChatGPT, Claude, Gemini and Grok — grounded in your own sources, cross-checked against each other.
Try MultipleChat FreeContinue learning
See the AI subscription that replaces separate ChatGPT, Claude, Gemini and Grok accounts.
Multi-model AIRun the same prompt through ChatGPT, Claude, Gemini and Grok before trusting one answer.
GuideChoose the best model for writing, research, coding, documents, images and business work.
Buyer intentOne app for several frontier AI models, side-by-side comparison and model collaboration.
PlatformA professional workspace for using several AI models, comparing answers and creating deliverables.
Core conceptUse several frontier models together for stronger answers and fewer blind spots.
ComparisonCompare several AI answers side by side when the output matters.
WorkflowBuild a professional AI stack for documents, research, writing, images and automation.
Free toolsStart with free tools, then upgrade when multi-model workflows save real time.
