Perplexity Sonar Pro is a next-generation AI assistant engineered for deep research, real-time information synthesis, and precise question answering. It leverages Perplexity’s proprietary hybrid architecture and advanced search integration to deliver fast, comprehensive, and well-sourced answers for knowledge-intensive workflows.
Sonar Pro is highly adaptable across diverse query types, including factual lookups, multi-step reasoning, and competitive analysis. It excels in synthesizing information from multiple sources, achieving a high normalized user satisfaction score and effectively addressing a broad spectrum of research needs.
.avif)
Vs. Claude Opus 4: Sonar Pro is tailored for real-time, multi-source information synthesis and precise citation—making it ideal for research and fact-checking, whereas Claude Opus 4 leads in autonomous coding and long-horizon reasoning tasks.
Vs. Gemini 2.0: Sonar Pro emphasizes live, cited answers and research workflows, while Gemini focuses on broad knowledge recall and creative generation.
Vs. ChatGPT-4: Sonar Pro’s standout feature is its integration of live web search and inline sourcing, offering higher transparency and recency compared to ChatGPT-4’s static knowledge cutoff.
Sonar Pro’s core advantage is its live, citable source integration. However, its performance on pure reasoning or coding benchmarks (e.g., SWE-bench) is not publicly benchmarked. For complex code generation or autonomous agent tasks, alternatives like Claude 4 Opus might be better suited.
Accessible via AI/ML API. Documentation: available here.
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "perplexity/sonar-pro", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "perplexity/sonar-pro", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"perplexity/sonar-pro","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| Intelligence | 11.8 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Sonar Pro This page | Chat + assistants | |||
| Reasoning + agents | ||||
| Balanced coding + agents | ||||
| Long-context, multimodal & agentic workflows | ||||
| Reasoning + agents |
Sonar Pro has a 200,000 tokens context window and can return up to 100,000 tokens.
Sonar Pro takes image, text as input and returns text.
Use perplexity/sonar-pro as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Sonar Pro became available on September 9, 2025.
Sonar Pro is priced at input $3.9 / 1M tokens, output $19.5 / 1M tokens.
Yes, Sonar Pro can stream responses as they are generated.
Yes, Sonar Pro accepts image input alongside text.
Sonar Pro was built by Perplexity.
Sonar Pro is a search-augmented model built for deeper reasoning and broader web coverage in text and image-based conversations.
Yes, Sonar Pro includes web search as one of its core features and capabilities.
