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.

From the source
The Agent API low preset now uses openai/gpt-5.6-luna with minimal reasoning effort and a 32,768-token maximum output.
docs.perplexity.ai

Visit source ↗docs.perplexity.ai

Announced: 31 Jul 2026 12:18 UTC
Detected: 30 Aug 2026 08:37 UTC (+29d after)

Other stories

Perplexity · 28 AugGLM 5.3API release

Perplexity · 27 AugDeepSeek V4 Flash 0731New model

Perplexity · 27 AugNVIDIA Nemotron 3.5 LightningCapability change

Perplexity · 27 AugNVIDIA Nemotron 3 UltraCapability change

Google DeepMind · 27 AugGemini Omni 1.1 Flash lets you build with more control

Model update

xAI · 29 AugGrok Bot now works with XCapability change