Perplexity

Perplexity: Sonar

perplexity/sonar

Access Sonar from Perplexity using Puter.js AI API.

Get Started
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';

puter.ai.chat("Explain quantum computing in simple terms", {
    model: "perplexity/sonar"
}).then(response => {
    document.body.innerHTML = response.message.content;
});
<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.chat("Explain quantum computing in simple terms", {
            model: "perplexity/sonar"
        }).then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>
# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://api.puter.com/puterai/openai/v1/",
    api_key="YOUR_PUTER_AUTH_TOKEN",
)

response = client.chat.completions.create(
    model="perplexity/sonar",
    messages=[
        {"role": "user", "content": "Explain quantum computing in simple terms"}
    ],
)

print(response.choices[0].message.content)
curl https://api.puter.com/puterai/openai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_PUTER_AUTH_TOKEN" \
  -d '{
    "model": "perplexity/sonar",
    "messages": [
      {"role": "user", "content": "Explain quantum computing in simple terms"}
    ]
  }'

Model Card

Sonar is Perplexity's lightweight, cost-effective search model built on Llama 3.3 70B, optimized for speed (1200 tokens/second) and quick factual queries. It provides real-time web search with grounding and citations, ideal for simple Q&A and straightforward integrations. Best for everyday use cases where fast, accurate answers are needed without complex reasoning.

Context Window 127K

tokens

Max Output N/A

tokens

Input Cost $1

per million tokens

Output Cost $1

per million tokens

Release Date Feb 18, 2025

 

Model Playground

Try Sonar instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.

Chat perplexity/sonar
Perplexity
Chat with Sonar
Powered by Puter.js

Benchmarks

How Sonar performs on standard evaluations.

Artificial Analysis
Intelligence Index
15.5
Better than 40% of tracked models
BenchmarkScore
GPQA Diamond Graduate-level science Q&A
47.1%
Humanity's Last Exam Cross-domain reasoning
7.3%
LiveCodeBench Recent coding problems
29.5%
SciCode Scientific programming
22.9%
MATH-500 Competition math
81.7%
AIME 2024 Advanced math exam
48.7%

Scores sourced from Artificial Analysis.

Frequently Asked Questions

How do I use Sonar?

You can access Sonar by Perplexity through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.

Is Sonar free?

Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Sonar to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.

What is the pricing for Sonar?
Pricing for Sonar is based on the number of input and output tokens used per request.
Price per 1M tokens
Input$1
Output$1
Who created Sonar?

Sonar was created by Perplexity and released on Feb 18, 2025.

What is the context window of Sonar?

Sonar supports a context window of 127K tokens. For reference, that is roughly equivalent to 254 pages of text.

Does it work with React / Vue / Vanilla JS / Node / etc.?

Yes — the Sonar API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.

Get started with Puter.js

Add Sonar to your app without worrying about API keys or setup.

Read the Docs View Tutorials