perplexityChat

Perplexity: Sonar

perplexity/sonar

127KContext Window

Supported Protocols:max_tokenstemperaturetop_ptop_kfrequency_penaltypresence_penaltyweb_search_options

Normal

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.

Capabilities

👁 VisionText GenerationCode GenerationAnalysis & ReasoningReasoning

Technical Specs

Input Modality

Text、Image

Output Modality

Text

Arch

—

Default Temperature

0.7

Default Top_P

Pricing

Pay per use, no monthly fees

Billing Type	Unit	Price
Text Input	—	$1.0000/M tokens
Text Output	—	$1.0000/M tokens
Web Search	—	$0.0050/次

Quick Start

from openai import OpenAI

client = OpenAI(
    base_url="https://api.uniontoken.ai/v1",
    api_key="YOUR_UNIONTOKEN_API_KEY",
)

response = client.chat.completions.create(
    model="perplexity/sonar",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

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