Perplexity

Overview

Perplexity provides search-augmented language models that combine LLM capabilities with real-time web search, returning grounded responses with citations. Floopy proxies requests to Perplexity’s OpenAI-compatible API.

Supported Models

Setup

1. Go to Settings > Providers in the dashboard.
2. Click Add provider and select Perplexity.
3. Paste your Perplexity API key and click Save.

Usage

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.floopy.ai/v1",
  apiKey: process.env.FLOOPY_API_KEY,
});

const response = await client.chat.completions.create({
  model: "sonar-pro",
  messages: [{ role: "user", content: "What are the latest developments in fusion energy?" }],
});

from openai import OpenAI

client = OpenAI(base_url="https://api.floopy.ai/v1", api_key=os.environ["FLOOPY_API_KEY"])

response = client.chat.completions.create(
    model="sonar-pro",
    messages=[{"role": "user", "content": "What are the latest developments in fusion energy?"}],
)

curl https://api.floopy.ai/v1/chat/completions \
  -H "Authorization: Bearer $FLOOPY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "sonar-pro", "messages": [{"role": "user", "content": "What are the latest developments in fusion energy?"}]}'

Provider-Specific Features

• Search-grounded responses — All Sonar models include real-time web search, returning responses grounded in current information with source citations.
• Per-request fees — In addition to token costs, Perplexity charges per-request search fees ($0.005-$0.022 depending on model and search depth).
• Reasoning mode — sonar-reasoning-pro combines chain-of-thought reasoning with web search for complex analytical tasks.