Modelpeers

Perplexity Agent API changelog

Every change to Perplexity Agent API that Modelpeers has recorded, newest first, each with the source it came from. The record starts Aug 27, 2026.

All (5)Releases (2)Retiring (1)Prices/limits (2)

October 2026

Claude Opus 5.5 character

Perplexity Agent API and Claude Opus 5.5

2 products from Perplexity AI and Anthropic

Limits change

Perplexity Agent API xhigh effort raises max steps from 100 to 300

The xhigh level stays on Claude Opus 5.5 with GPT-6.1 Sol as fallback. Context compaction starts at 150,000 tokens, and it no longer sends a system prompt.

Before

100 max steps

After

300 max steps

Who is affected:
Agent API users on xhigh effort or frozen configurations.
What to do:
Copy the updated values if you use a frozen configuration.

August 2026

Perplexity Agent API and Gemini 3.7 Flash

2 products from Perplexity AI and Google

Price change

Perplexity Agent API raises the price of Gemini 3.7 Flash

Pricing for google/gemini-3.7-flash on the Perplexity Agent API and Orchestrator API rose on August 27, 2026 to $0.75 per million input tokens, $0.075 per million cached input tokens and $3.75 per million output and reasoning tokens.

After

$0.75 input, $0.075 cached input, $3.75 output per 1M tokens

Who is affected:
Apps that call Gemini 3.7 Flash through the Perplexity Agent API.
Action needed:
Check your costs for Gemini 3.7 Flash calls.

Get this changelog in a feed reader with the RSS feed.