Sonar Pro API

Perplexity Sonar Pro is an advanced search-augmented language model with deeper reasoning and broader web coverage.

Modalities: Text, ImageText
In / Out price: $3/$15per 1M
Context window: 200K tokens
Released: Sep 9, 2025

Sonar Pro overview

Sonar Pro by Perplexity

Perplexity Sonar Pro API delivers fast, reliable search with deep insights and cited, up-to-date information for research and competitive analysis.

Sonar Pro specs

Model ID: perplexity/sonar-pro
Developer: Perplexity
Context window: 200,000 tokens
Max output: 100,000 tokens
Input: Text, Image
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

Perplexity Sonar Pro Description

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.

Performance Benchmarks

Search Efficiency: Rapidly synthesizes information from numerous sources into coherent, sourced responses.
Accuracy: Ensures high factual precision, directly citing authoritative references to support all claims.
Optimized for real-time complex queries with response generation typically achieved in seconds.

Performance Metrics

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.

Key Capabilities

Advanced Research: Aggregates, compares, and distills data from diverse sources into actionable insights.
Real-Time Synthesis: Incorporates live web data, academic papers, and proprietary datasets to provide up-to-date answers.
Customization: Tailors response depth, style, and sourcing per user or developer requirements.

Comparison with Other Models

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.

Limitations

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.

Use cases

Research & Analysis: Academic literature reviews, competitive intelligence, and market research.
Business Decision Support: Due diligence, executive briefings, and data-driven strategy formulation.
Technical & Scientific Inquiry: Summarizing recent findings, elucidating complex concepts, and delivering methodologically rigorous answers.
Education & Learning: Providing sourced explanations, study aids, and curated reading recommendations.

Capabilities

Streaming
Structured outputs
Web search

Sonar Pro benchmarks by Artificial Analysis

See how Sonar Pro scores on independent evaluations. Data retrieved Nov 3, 2026.

Humanity's Last Exam#267 / 4586.6%Score GPQA Diamond#283 / 43957.8%Score LiveCodeBench#173 / 26327.5%Score MMLU-Pro#128 / 26875.5%Score

Benchmark results

Compare 14 models available on AI/ML API across 5 independent benchmarks.

Humanity's Last Exam

Expert-written questions across academic subjects.

MATH-500

Competition mathematics problems.

Sonar Pro API pricing

Sonar Pro pricing in US dollars
Usage	Price	Unit
Input	$3	1M tokens
Output	$15	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

Sonar Pro vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
Sonar Pro	$3	$15
Sonar	$1	$1
Claude 4.5 Sonnet	$3	$15
Claude 4.5 Sonnet Thinking	$3	$15
Claude Sonnet 4.6	$3	$15

How to use the Sonar Pro API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl '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": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "perplexity/sonar-pro",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = 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": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

Sonar Pro FAQ

What is the context window of Sonar Pro?

Sonar Pro has a 200,000 tokens context window and can return up to 100,000 tokens.

What inputs and outputs does Sonar Pro support?

Sonar Pro takes image, text as input and returns text.

What is the model ID for Sonar Pro?

Use perplexity/sonar-pro as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

When was Sonar Pro released?

Sonar Pro became available on September 9, 2025.

How much does Sonar Pro cost?

Sonar Pro costs $3 input and $15 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Does Sonar Pro support streaming?

Yes, Sonar Pro can stream responses as they are generated.

Can Sonar Pro read images?

Yes, Sonar Pro accepts image input alongside text.

Who created Sonar Pro?

Sonar Pro was built by Perplexity.

What kind of tasks is Sonar Pro suited for?

Sonar Pro is a search-augmented model built for deeper reasoning and broader web coverage in text and image-based conversations.

Can Sonar Pro search the web while answering?

Yes, Sonar Pro includes web search as one of its core features and capabilities.

Start building with Sonar Pro

Get API key

Sonar Pro API

perplexity/sonar-pro

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl '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": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "perplexity/sonar-pro",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = 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": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

Sonar Pro API

Sonar Pro overview

Sonar Pro by Perplexity

Sonar Pro specs

Perplexity Sonar Pro Description

Performance Benchmarks

Performance Metrics

Key Capabilities

Comparison with Other Models

Limitations

Use cases

Capabilities

Sonar Pro benchmarks by Artificial Analysis

Benchmark results

Humanity's Last Exam

GPQA Diamond

LiveCodeBench

MMLU-Pro

MATH-500

Sonar Pro API pricing

Sonar Pro vs other models: token prices

How to use the Sonar Pro API

Build with your agent

1Get your API key

2Make your first request

Related articles

Sonar Pro FAQ

Start building with Sonar Pro

Sonar Pro API

Build with your agent

1Get your API key

2Make your first request

Sonar Pro API

Sonar Pro overview

Sonar Pro by Perplexity

Sonar Pro specs

Perplexity Sonar Pro Description

Performance Benchmarks

Performance Metrics

Key Capabilities

Comparison with Other Models

Limitations

Use cases

Capabilities

Benchmark results

Sonar Pro API pricing

Sonar Pro vs other models: token prices

How to use the Sonar Pro API

Build with your agent

1Get your API key

2Make your first request

Models similar to Sonar Pro

Sonar

Claude Sonnet 4.6

Kimi K3

Claude 4.5 Sonnet

Claude 4.5 Sonnet Thinking

Aion-3.0

Related articles

Sonar Pro FAQ

Start building with Sonar Pro