Perplexity: Sonar Deep Research

perplexity/sonar-deep-research

Try Sonar Deep Research for free in your browser, and add it to your app for free with Puter.js AI API.

Try it free Add to your app

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

puter.ai.chat("Explain quantum computing in simple terms", {
    model: "perplexity/sonar-deep-research"
}).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-deep-research"
        }).then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>

Model Card

Sonar Deep Research is Perplexity's expert-level research model designed for exhaustive multi-step retrieval, synthesizing hundreds of sources into comprehensive reports. It autonomously searches, reads, and evaluates sources while refining its approach for in-depth analysis across domains like finance, technology, and health. Ideal for detailed market analyses, literature reviews, and projects requiring synthesis of multiple information sources.

Context Window 128K

tokens

Max Output 115K

tokens

Input Cost $2

per million tokens

Output Cost $8

per million tokens

Input text

modalities

Tool Use No

Release Date Mar 7, 2025

Try Sonar Deep Research for free

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

Chat perplexity/sonar-deep-research

Chat with Sonar Deep Research

More AI Models From Perplexity

Find other Perplexity models →

Chat

Sonar Pro Search

Sonar Pro Search is Perplexity's most advanced agentic search system, available exclusively via OpenRouter API, adding autonomous multi-step reasoning to Sonar Pro. Instead of single query+synthesis, it plans and executes entire research workflows using tools, making it ideal for deeper reasoning and analysis. This model powers Perplexity's Pro Search mode on their consumer platform.

Chat

Sonar Pro

Sonar Pro is Perplexity's advanced search model with a 200K token context window, delivering 2x more citations and search results than standard Sonar for complex queries. It handles in-depth, multi-step queries with enhanced content understanding and supports longer, more nuanced follow-up conversations. Best for enterprise applications requiring deeper research and comprehensive source attribution.

Chat

Sonar Reasoning Pro

Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT), designed for complex multi-step analysis and logical problem-solving. It excels at tasks requiring step-by-step thinking, strict instruction adherence, and information synthesis across sources with built-in web search. Ranked among the top models in Search Arena evaluations, statistically tied with Gemini-2.5-Pro-Grounding.

Frequently Asked Questions

How do I use Sonar Deep Research?

You can access Sonar Deep Research 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.

Can I try Sonar Deep Research for free?

Sonar Deep Research is free to try with a Puter account. Every account includes a free AI allowance, and you can chat with it in the playground on this page. You can upgrade your account anytime for a larger allowance.

Is the Sonar Deep Research API free for developers?

Sonar Deep Research is free to integrate using the Puter.js AI API. With the User-Pays Model, you can add AI to your app for $0, since users cover their own AI usage through their Puter account.

What is the pricing for Sonar Deep Research?

Sonar Deep Research costs $2 per 1M input tokens and $8 per 1M output tokens.

	Price per 1M tokens
Input	$2
Output	$8

Who created Sonar Deep Research?

Sonar Deep Research was created by Perplexity and released on Mar 7, 2025.

What is the context window of Sonar Deep Research?

Sonar Deep Research supports a context window of 128K tokens. For reference, that is roughly equivalent to 256 pages of text.

What is the max output length of Sonar Deep Research?

Sonar Deep Research can generate up to 115K tokens in a single response.

What types of input can Sonar Deep Research process?

Sonar Deep Research accepts the following input types: text. It produces: text.

Does Sonar Deep Research support tool use (function calling)?

No, Sonar Deep Research does not currently support tool use (function calling).

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

Yes — the Sonar Deep Research 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.

Add Sonar Deep Research to your app for free

Developers can integrate Sonar Deep Research for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.

Get started How pricing works