# Low preset updated

By Steven Van · 2026-07-01

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](<https://creatorstoolbox.com/tools/perplexity>) Agent API has [updated its low preset](<https://docs.perplexity.ai/changelog#july-2026>) 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.

[![](<https://perplexity.mintlify.app/mintlify-assets/_next/image?url=%2F_mintlify%2Fapi%2Fog%3Fdivision%3DResources%26title%3DChangelog%26theme%3D820be4ec62923f2d29093b0d&w=1200&q=100>)](<https://docs.perplexity.ai/changelog#july-2026>)

![Perplexity](<https://www.google.com/s2/favicons?domain=perplexity.ai&sz=128>)

Perplexity

AI-powered answer engine — ask anything and get cited, real-time answers from across the web.

[View Perplexity →](<https://creatorstoolbox.com/tools/perplexity>)

Sources

[Original source](<https://docs.perplexity.ai/changelog#july-2026>)

[Read Low preset updated on Creators Toolbox](<https://creatorstoolbox.com/blog/perplexity-low-preset-updated>)

---
Canonical source: https://creatorstoolbox.com/blog/perplexity-low-preset-updated