sonar-pro-search

completions

byopenrouter

sonar-pro-search

completions

Published by: perplexityProvider:

openrouter

Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based on tokens plus $18 per thousand requests. This model powers the Pro Search mode on the Perplexity platform. Sonar Pro Search adds autonomous, multi-step reasoning to Sonar Pro. So, instead of just one query + synthesis, it plans and executes entire research workflows using tools.

Released

Jan 21, 2025

Knowledge

Jul 25, 2024

Context

200K

Input

$3 / 1M tokens

Output

$15 / 1M tokens

Capabilities: reasoning

Accepts: text, image

Returns: text

Released Jan 21, 2025Knowledge Cutoff: Jul 25, 2024

Context: 200K Input: $3 / 1M tokensOutput: $15 / 1M tokensCapabilities: reasoningAccepts: text, imageReturns: text

Access sonar-pro-search through LangDB AI Gateway

Recommended

Integrate with perplexity's sonar-pro-search and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.

Unified API

Cost Optimization

Enterprise Security

Get Started Now

Free tier available • No credit card required

Instant Setup

99.9% Uptime

10,000+Monthly Requests

Benchmark Results for sonar-pro-search

Category Performance Scores:

Academia: Score 43.00 (Top 61% - Rank #216)
Marketing: Score 61.46 (Top 13% - Rank #47)
Science: Score 59.14 (Top 54% - Rank #192)
Writing: Score 56.67 (Top 24% - Rank #85)

Overall Performance: 55.06784722222223 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AIME	29.00	Top 49%	Mathematics
AAII	28.20	Top 60%	General
GPQA	57.80	Top 56%	STEM (Physics, Chemistry, Biology)
HLE	7.90	Top 24%	General Knowledge
LiveCodeBench	27.50	Top 70%	Programming
MATH-500	74.50	Top 66%	Mathematics
MMLU-Pro	75.50	Top 49%	General Knowledge
SciCode	22.60	Top 73%	Scientific

GPQA Score: 57.80 - Graduate-level reasoning benchmark

Model Comparison:

Provider: openrouter

Model Type: completions

Context Size: 200000 tokens

Comparing against 354 models in the database

Category Scores

Benchmark Tests

View Other Benchmarks

AIME

29.0

Mathematics

AAII

28.2

General

GPQA

57.8

STEM (Physics, Chemistry, Biology)

HLE

7.9

General Knowledge

LiveCodeBench

27.5

Programming

MATH-500

74.5

Mathematics

MMLU-Pro

75.5

General Knowledge

SciCode

22.6

Scientific

Metric	AIME	AAII	GPQA	HLE	LiveCodeBench	MATH-500	MMLU-Pro	SciCode
Score	29.0	28.2	57.8	7.9	27.5	74.5	75.5	22.6

Compare with Similar Models

gemini-2.5-pro-preview

Code Examples

Integration samples and API usage

Code Samples for sonar-pro-search

Python SDK Example:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.us-east-1.langdb.ai//projects/<your_project_id>",
    api_key="<your_api_key>"
)

response = client.chat.completions.create(
    model="sonar-pro-search",
    messages=[
        {"role": "user", "content": "Hello, how are you?"}
    ]
)

print(response.choices[0].message.content)

TypeScript SDK Example:

import OpenAI from 'openai';

const client = new OpenAI({
    baseURL: "https://api.us-east-1.langdb.ai//projects/<your_project_id>",
    apiKey: "<your_api_key>"
});

const response = await client.chat.completions.create({
    model: "sonar-pro-search",
    messages: [
        { role: "user", content: "Hello, how are you?" }
    ]
});

console.log(response.choices[0].message.content);

cURL Example:

curl -X POST "https://api.us-east-1.langdb.ai//projects/<your_project_id>/v1/chat/completions" \
  -H "Authorization: Bearer <your_api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sonar-pro-search",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: sonar-pro-search

Provider: openrouter

API Endpoint: $https://api.us-east-1.langdb.ai/

Create API Key

Related Models

Similar models from openrouter

sonar-pro-search

sonar-pro-search

Access sonar-pro-search through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

afm-4.5b

aion-1.0

aion-1.0-mini

aion-rp-llama-3.1-8b

coder-large

cogito-v2-preview-deepseek-671b

sonar-pro-search by openrouter - AI Model Details, Pricing, and Performance Metrics

sonar-pro-search

sonar-pro-search

Access sonar-pro-search through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

afm-4.5b

aion-1.0

aion-1.0-mini

aion-rp-llama-3.1-8b

coder-large

cogito-v2-preview-deepseek-671b