Low preset updated
By Steven Van ·
The Agent API low preset now uses openai/gpt-5.6-luna with minimal reasoning effort and a 32,768-token maximum output.
Perplexity's Perplexity Agent API has updated its low preset to use openai/gpt-5.6-luna with minimal reasoning effort and a 32,768-token maximum output. Requests using the dynamic low preset pick up the change automatically; anyone on a frozen configuration needs to update the model, reasoning effort, and output limit to match.
Perplexity
AI-powered answer engine — ask anything and get cited, real-time answers from across the web.
View Perplexity →