# Perplexity — Low preset updated

- Company: Perplexity (perplexity.ai)
- Announced: 2026-07-31T12:18:23+00:00
- Category: model-update
- Subject: Sonar
- Models affected: openai/gpt-5.6-luna
- Source: https://docs.perplexity.ai/docs/resources/changelog#july-2026
- Record: https://forck.live/items/5067-low-preset-updated

The low preset of the Agent API now uses the openai/gpt-5.6-luna model with minimal reasoning effort and a 32,768-token maximum output. Frozen configurations need manual updates; dynamic requests update automatically.

## Evidence

Verbatim from https://docs.perplexity.ai/docs/resources/changelog#july-2026:

> The Agent API low preset now uses openai/gpt-5.6-luna with minimal reasoning effort and a 32,768-token maximum output.

---

Record: https://forck.live/items/5067-low-preset-updated
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md