Sonar Pro
Perplexity's advanced search model delivering deeper reasoning, richer citations, and multi-step query handling for complex research tasks.
Perplexity Search-augmented AI with deep citation support
Sonar Pro is a search-augmented text generation model developed by Perplexity, designed to handle complex research queries that require thorough source attribution and multi-step reasoning. It operates with a 200,000-token context window, allowing it to process large volumes of information within a single session. The model supports both text and image inputs and can produce up to 8,192 output tokens per response. It also includes function calling, structured output generation, and a reasoning mode for analytical tasks.
Sonar Pro is Perplexity's premium tier offering within the Sonar model family, delivering approximately twice the citations and search results compared to the standard Sonar model. This makes it particularly well-suited for enterprise applications, professional research workflows, and use cases that demand comprehensive source coverage and reliable multi-step query handling. The model's training data extends through March 2025, and its live web search integration means responses can draw on current information beyond that date. It is available via API for developers building research-intensive or knowledge-heavy applications.
What Sonar Pro supports
Web Search Integration
Retrieves live web results at inference time, providing grounded answers with citations. Delivers approximately 2x more citations per response compared to the standard Sonar model.
Large Context Window
Supports a 200,000-token context window, enabling processing of lengthy documents or extended multi-turn conversations in a single session.
Multi-Step Reasoning
Includes a reasoning mode that breaks down complex queries into sub-tasks, gathers information from multiple angles, and synthesizes a coherent response.
Vision Input
Accepts image inputs alongside text, allowing the model to interpret and reason over visual content as part of a query.
Structured Output
Supports structured output generation and function calling, making it suitable for integration into programmatic workflows and agent pipelines.
Content Moderation
Includes built-in content moderation support to help filter and manage outputs in safety-sensitive deployment contexts.
Ready to build with Sonar Pro?
Get Started FreeBenchmark scores
Scores represent accuracy — the percentage of questions answered correctly on each test.
| Benchmark | What it tests | Score |
|---|---|---|
| MMLU-Pro | Expert knowledge across 14 academic disciplines | 75.5% |
| GPQA Diamond | PhD-level science questions (biology, physics, chemistry) | 57.8% |
| MATH-500 | Undergraduate and competition-level math problems | 74.5% |
| AIME 2024 | American math olympiad problems | 29.0% |
| LiveCodeBench | Real-world coding tasks from recent competitions | 27.5% |
| HLE | Questions that challenge frontier models across many domains | 7.9% |
| SciCode | Scientific research coding and numerical methods | 22.6% |
Common questions about Sonar Pro
What is the context window size for Sonar Pro?
Sonar Pro supports a 200,000-token context window, allowing it to process large documents or long multi-turn conversations within a single session.
What is the maximum number of output tokens per response?
Sonar Pro can generate up to 8,192 output tokens per response.
What is the knowledge cutoff date for Sonar Pro?
The model's training data extends through March 2025. However, because Sonar Pro integrates live web search, it can also surface information published after that date.
Does Sonar Pro support image inputs?
Yes, Sonar Pro supports both text and image inputs, enabling the model to interpret visual content as part of a query.
How does Sonar Pro differ from the standard Sonar model?
Sonar Pro is Perplexity's premium tier and delivers approximately twice the citations and search results per response compared to the standard Sonar model. It also includes a reasoning mode and supports more complex, multi-step queries.
Does Sonar Pro support function calling?
Yes, Sonar Pro supports function calling and structured output generation, making it compatible with agent-based and programmatic integration workflows.
Parameters & options
Determines whether or not a request to an online model should return citations.
Determines whether or not a request to an online model should return images.
Explore similar models
Perplexity Sonar Deep Research
Perplexity's exhaustive deep research model that autonomously searches hundreds of sources to deliver expert-level analysis and comprehensive reports.
Perplexity Sonar Reasoning Pro
Perplexity's premier reasoning model combining DeepSeek R1-powered Chain-of-Thought reasoning with real-time web search for comprehensive, citation-rich answers.
Perplexity Sonar
Perplexity's lightweight, real-time AI search model that delivers fast, citation-backed answers by connecting directly to the live web.
Google Gemini 3.1 Pro
Google's frontier reasoning model delivering enhanced software engineering, agentic reliability, and multimodal intelligence across a 1M-token context window.
OpenAI GPT‑5.2 Pro
The most capable model series yet for professional knowledge work.
Nvidia Nemotron 3 Nano 30B
NVIDIA's compact open-weight hybrid MoE model with 30B total / 3.5B active parameters, delivering strong reasoning and coding performance up to 1M context.
Start building with Sonar Pro
No API keys required. Create AI-powered workflows with Sonar Pro in minutes — free.