modelgrep
P

Perplexity: Sonar

perplexity/sonar

Vision
Use via OpenRouter ↗
Intelligence
Design Elo
Speed
94
72nd fastest
Latency
1.8s
first token
Input price
$1.00
208th cheapest
Context
127K

How it compares

Faster than75%
of all ranked models
Cheaper than30%
of all ranked models

Overview

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...

Benchmarks

independent · via OpenRouter
Artificial Analysis
GPQA Diamond
47%
Humanity's Last Exam
7%
SciCode
23%

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Perplexity$1.00$1.00100%

Specifications

Context window127K
Max output
Knowledge cutoff
Input modalitiestext, image
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Sonar FAQ

How much does Sonar cost?

Sonar costs $1.00 per million input tokens and $1.00 per million output tokens via OpenRouter, making it 208th cheapest of 298 paid models.

How fast is Sonar?

Sonar generates around 94 tokens per second with 1.8s time-to-first-token (p50), the 72nd fastest tracked model.

What is Sonar's context window?

Sonar supports a 127K-token context window. It accepts text, image input.

More from perplexity

All Sonar alternatives →

Compare head-to-head