Login
PerplexityFastFastActive

Perplexity: Sonar

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...

Image
Start with this modelBrowse all models
Specification
Model ID
perplexity/sonar
Modality
Text+image >text
Context
127.1K tokens
Input
$1.00/1M
Output
$1.00/1M
Web search
$5000.00/1M
Updated
Sep 20, 2026
Scores
Capabilities
  • No tool calling listed
  • Supports vision inputs
  • Supports long-context workflows
  • Lighter reasoning profile

Input and output

Accepts Text, Image inputs. Returns Text outputs.

Supported parameters

frequency_penaltymax_tokenspresence_penaltytemperaturetop_ktop_pweb_search_options

Related models

Prism ML

PrismML: Ternary Bonsai 2 27B

Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...

Z.ai

Z.ai: GLM 5.3 FlashX

GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...

Unbiased

Pareto

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.