Pay-per-token
perplexity-agent/Perplexity Agent
Perplexity Agent — connect via API key.
www.perplexity.aiQuick setup
Open the kRouter dashboard at http://localhost:20128
Go to Providers → click Perplexity Agent
Paste your API key, click Save
Test the connection
Use in your IDE
Point any OpenAI-compatible client at kRouter using your local API key.
# Endpoint
http://localhost:20128/v1
# API key (from Dashboard → API Keys)
sk-krouter-XXXX
# Model
perplexity-agent/<model-id>How Perplexity Agent billing works with kRouter
Perplexity Agent is pay-per-token. You bring your own API key and kRouter routes to it, so you keep your own rate limits and billing relationship. kRouter authenticates it via apikey.
Through kRouter, Perplexity Agent serves chat and code completion. Requests reach it through the same local OpenAI-compatible endpoint as every other provider, so switching to or from Perplexity Agent is a one-line model change in your client rather than a rewrite.
Perplexity Agent API exposes GPT, Claude, Gemini, Grok, GLM, Kimi, and Sonar models through one OpenAI-compatible Responses API.
Perplexity Agent links
Perplexity Agent FAQ
Is Perplexity Agent free through kRouter?
Perplexity Agent is pay-per-token: you bring your own API key and are billed by Perplexity Agent at their rates. kRouter adds nothing on top and is free and MIT-licensed.
How do I use Perplexity Agent with Claude Code or Cursor?
Connect Perplexity Agent in the kRouter dashboard, then point your tool at kRouter's local endpoint (http://localhost:20128/v1) with a kRouter API key. Any OpenAI-compatible client works, and models are addressed as perplexity-agent/<model>.
What happens when Perplexity Agent is rate limited?
kRouter detects the limit, parks that account until its real reset time, and fails over to your next connected account or provider — so the request still completes instead of erroring.