Sonar API

Perplexity Sonar is a fast search-augmented language model grounded in real-time web data for up-to-date answers.

Modalities: Text, ImageText
In / Out price: $1/$1per 1M
Context window: 125K tokens
Released: Sep 9, 2025

Sonar overview

Sonar by Perplexity

Perplexity Sonar API delivers fast, real-time search and AI-powered synthesis with accurate, cited answers from multiple sources.

Sonar specs

Model ID: perplexity/sonar
Developer: Perplexity
Context window: 128,000 tokens
Max output: 100,000 tokens
Input: Text, Image
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

Perplexity Sonar Description

Perplexity AI’s Sonar is an advanced multimodal AI assistant optimized for real-time, context-aware web search, synthesis, and conversational analytics. Designed for both professional and consumer workflows, Sonar combines fast, authoritative information retrieval with robust reasoning over retrieved documents.

Performance Benchmarks

Model Architecture: Hybrid system combining proprietary and open-source LLMs (LlaMa 3.1 70B base, custom Perplexity fine-tuning), with integrated real-time web search and multi-document synthesis.
Context Window: Dynamic, automatically adjusts to the retrieved content and query complexity.‍
Tool Integration: Native live web search, academic databases, and citation engine for source-backed answers.

Performance Metrics

Sonar demonstrates consistency in real-time information retrieval and source-backed answer quality. Its upward trend in query volume and user engagement signals strong market fit for knowledge-intensive workflows. The trade-off for rapid, cited answers is slightly higher latency compared to pure LLM chatbots, but with greater accuracy and transparency.

Key Capabilities‍

Perplexity Sonar API delivers authoritative outputs for information-dense workflows.

Advanced Search & Synthesis: Excels in cross-referencing multiple web sources, distilling complex information, and presenting it with clarity and transparency.
Conversational Analytics: Supports multi-turn, context-aware dialogues for research, business intelligence, and decision support.
Tool Utilization: Integrates proprietary live web search, enabling real-time fact-checking and source citation.

Comparison with Other Models

Vs. Claude 4 Opus: Sonar specializes in live, cited answers from the web, while Claude 4 Opus leads in autonomous coding, reasoning, and agentic workflows. Sonar is optimized for users who need answers grounded in the latest, most authoritative sources rather than long-context reasoning or code generation.

‍Vs. Gemini 2.5: Sonar emphasizes real-time search and synthesis; Gemini models offer broad multimodal capabilities and long-context reasoning but may not always surface citations or real-time data as explicitly.

‍Vs. OpenAI GPT-4: Perplexity Sonar is purpose-built for retrieval-augmented generation (RAG) and source transparency; GPT-4 is a generalist model, best for broad reasoning and creative tasks without built-in web sourcing.

Limitations

Perplexity/Sonar specializes in real-time research, multi-source synthesis, and cited analytics, setting it apart for up-to-date, accurate, and verifiable answers. However, its limitations are equally distinctive:

No Traditional Coding or Reasoning Benchmarks: Unlike models such as Claude Opus 4 or Kimi K2, Perplexity Sonar does not publish standard coding or reasoning metrics (e.g., SWE-bench, LiveCodeBench) because its architecture is optimized for real-time, sourced knowledge retrieval rather than autonomous coding or long-horizon reasoning
Best for Research and Analytics, Not Code: It excels in tasks requiring live web search, deep citation, and business intelligence, but is less suitable for pure code generation, agentic autonomy, or scenarios where generative program synthesis is critical.‍
Static Knowledge and Reasoning: For tasks beyond the scope of its search-embedded, live-updated knowledge, Perplexity Sonar operates like any RAG (Retrieval-Augmented Generation) system: without real-time, cited web access, it cannot claim dramatic accuracy or recency advantages over other frontier models.

Use cases

Research & Analysis: Rapid literature review, competitive intelligence, and academic research.
Business Intelligence: Real-time market analysis, news monitoring, and executive briefing.
Education & Content Creation: Answering complex questions with cited sources, content summarization, and explanation generation.
Technical Support: Troubleshooting, documentation lookup, and workflow guidance with source grounding.

Capabilities

Streaming
Structured outputs
Web search

Sonar benchmarks by Artificial Analysis

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

Humanity's Last Exam#334 / 4584.9%Score GPQA Diamond#325 / 43947.1%Score LiveCodeBench#161 / 26329.5%Score MMLU-Pro#168 / 26868.9%Score

Benchmark results

Compare 13 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 API pricing

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

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

Sonar 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	$1	$1
Venice Uncensored	$0.2116	$0.9522
Codestral 2508	$0.3174	$0.9522
GLM 4.6V	$0.3174	$0.9522
Sonar Pro	$3	$15

How to use the Sonar 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",
  "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",
    "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",
    "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 FAQ

What is the context window of Sonar?

Sonar has a 128,000 tokens context window and can return up to 100,000 tokens.

What inputs and outputs does Sonar support?

Sonar takes image, text as input and returns text.

What is the model ID for Sonar?

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

When was Sonar released?

Sonar became available on September 9, 2025.

How much does Sonar cost?

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

Does Sonar support streaming?

Yes, Sonar can stream responses as they are generated.

Can Sonar read images?

Yes, Sonar accepts image input alongside text.

Who created Sonar?

Sonar was built by Perplexity.

What is Sonar best suited for?

Sonar is a fast, search-augmented model grounded in real-time web data, suited for tasks that need up-to-date information.

Can Sonar return images in its responses?

No. Sonar can accept image inputs but only produces text output.

Start building with Sonar

Get API key

Sonar API

perplexity/sonar

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",
  "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",
    "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",
    "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 API

Sonar overview

Sonar by Perplexity

Sonar specs

Perplexity Sonar Description

Performance Benchmarks

Performance Metrics

Key Capabilities‍

Comparison with Other Models

Limitations

Use cases

Capabilities

Sonar benchmarks by Artificial Analysis

Benchmark results

Humanity's Last Exam

GPQA Diamond

LiveCodeBench

MMLU-Pro

MATH-500

Sonar API pricing

Sonar vs other models: token prices

How to use the Sonar API

Build with your agent

1Get your API key

2Make your first request

Related articles

Sonar FAQ

Start building with Sonar

Sonar API

Build with your agent

1Get your API key

2Make your first request

Sonar API

Sonar overview

Sonar by Perplexity

Sonar specs

Perplexity Sonar Description

Performance Benchmarks

Performance Metrics

Key Capabilities‍

Comparison with Other Models

Limitations

Use cases

Capabilities

Benchmark results

Sonar API pricing

Sonar vs other models: token prices

How to use the Sonar API

Build with your agent

1Get your API key

2Make your first request

Models similar to Sonar

Sonar Pro

GLM-5

Grok Build 0.1

GPT-6.1 Terra

Claude 4.5 Haiku

Grok Code Fast 1

Related articles

Sonar FAQ

Start building with Sonar