APIPerplexity AI · Joined Oct 29, 2026

Perplexity Agent API

API at Perplexity AI

Perplexity Agent API does not have a researched profile yet. Everything here comes from its recorded changes and public listings, each linked to its source.

The basics

As of Nov 1

Status: Available

Updates

Oct 29

New release

Perplexity Agent API lists GPT-6 Astra at $10 per million input tokens

The model docs now list openai/gpt-6-astra at $10.00 per million input tokens and $50.00 per million output tokens up to 272k input tokens, with flex and priority tiers.

After

$10.00 input, $50.00 output per million tokens

Oct 29

New release

Perplexity Agent API adds DeepSeek V4 Pro at $1.32 per million input tokens

The model docs list perplexity/deepseek-v4-pro-0813 at $1.32 per million input tokens, $0.044 per cached input token million, and $3.96 per million output tokens. It is also available through the Orchestrator API.

After

$1.32 input, $3.96 output per million tokens

Oct 29

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

Full changelog, by month

Works with

From recorded changes

Claude Opus 5.5

Model · 1 shared change

DeepSeek-V4-Pro

Model · 1 shared change

Gemini 3.7 Flash

Model · 1 shared change

GPT-6 Astra

Model · 1 shared change

What people say

Reviews

No reviews yet. Be the first to review Perplexity Agent API.

Used Perplexity Agent API? Tell other builders what worked and what did not.