Fast preset updated

The Agent API's 'fast' preset now uses the openai/gpt-5.6-luna model with minimal reasoning effort and priority processing. Dynamic requests automatically adopt the change; frozen configurations require manual updates. Priority processing costs 2x the standard token prices.

From the source
The Agent API fast preset now uses openai/gpt-5.6-luna with minimal reasoning effort and priority processing.
docs.perplexity.ai

Visit source ↗docs.perplexity.ai

Announced: 19 Aug 2026 00:47 UTC
Detected: 30 Aug 2026 08:37 UTC (+11d after)
Pricing: Priority processing uses 2× the model's standard token prices.

Other stories

xAI · 29 AugGrok Bot now works with XCapability change

GitHub · 28 AugGitHub Copilot weekly releases — August 24Capability change

Perplexity · 28 AugGLM 5.3API release

Amazon · 28 AugSpreading the load: How Salesforce met Multi-AZ HA with SageMaker Inference ComponentsCapability change

Hugging Face · 28 AugThe Open ASR Leaderboard Adds Its First Global South Language

Capability change

Amazon · 27 AugBuild agentic creative workflows with Amazon Quick and falCapability change