sonar

completions

byopenrouter

sonar

completions

Published by: perplexityProvider:

openrouter

Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features optimized for speed.

Released

Jan 21, 2025

Knowledge

Jul 25, 2024

Context

127072

Input

$1 / 1M tokens

Output

$1 / 1M tokens

Accepts: text, image

Returns: text

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

Context: 127072 Input: $1 / 1M tokensOutput: $1 / 1M tokensAccepts: text, imageReturns: text

Access sonar through LangDB AI Gateway

Recommended

Integrate with perplexity's sonar 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

Category Performance Scores:

Academia: Score 37.95 (Top 68% - Rank #228)
Marketing: Score 56.15 (Top 23% - Rank #78)
Science: Score 51.16 (Top 70% - Rank #235)
Writing: Score 50.04 (Top 41% - Rank #138)

Overall Performance: 48.82388888888888 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AIME	48.70	Top 31%	Mathematics
AAII	28.80	Top 56%	General
GPQA	47.10	Top 69%	STEM (Physics, Chemistry, Biology)
HLE	7.30	Top 24%	General Knowledge
LiveCodeBench	29.50	Top 60%	Programming
MATH-500	81.70	Top 55%	Mathematics
MMLU-Pro	68.90	Top 68%	General Knowledge
SciCode	22.90	Top 69%	Scientific

GPQA Score: 47.10 - Graduate-level reasoning benchmark

Model Comparison:

Provider: openrouter

Model Type: completions

Context Size: 127072 tokens

Comparing against 335 models in the database

Category Scores

Benchmark Tests

View Other Benchmarks

AIME

48.7

Mathematics

AAII

28.8

General

GPQA

47.1

STEM (Physics, Chemistry, Biology)

HLE

7.3

General Knowledge

LiveCodeBench

29.5

Programming

MATH-500

81.7

Mathematics

MMLU-Pro

68.9

General Knowledge

SciCode

22.9

Scientific

Metric	AIME	AAII	GPQA	HLE	LiveCodeBench	MATH-500	MMLU-Pro	SciCode
Score	48.7	28.8	47.1	7.3	29.5	81.7	68.9	22.9

Compare with Similar Models

gemini-2.5-pro-preview

Code Examples

Integration samples and API usage

Code Samples for sonar

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",
    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",
    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",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: sonar

Provider: openrouter

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

Create API Key

Related Models

Similar models from openrouter

sonar

sonar

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

sonar

sonar

Access sonar 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