Skip to content

Model Library

PerplexityReleased January 28, 2025

Sonar Reasoning

Perplexity · Released January 28, 2025

Intelligence score

12

At a glance

Intelligence
12
Speed
—
Latency
—
Input price
Not published
Output price
Not published
Context window
130Ktokens
Parameters
—

Summary

Comparison summary

Sonar Reasoning scores 12 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other reasoning models in a similar price tier (median: 14).

Specifications

Technical specifications

Model nameSonar Reasoning
ProviderPerplexity
Release dateJanuary 28, 2025
Intelligence score12
Speed—
Latency (TTFT)—
Input priceNot published
Output priceNot published
Context window130,000 tokens
Parameters—
ReasoningYes
Input modalitiestext
Output modalities—
Open weightsNo
License—
API availability—
SourceModel Intelligence legacy profile: sonar-reasoning

FAQ · 14

Frequently asked questions

Sonar Reasoning was released on January 28, 2025.

Sonar Reasoning was created by Perplexity.

Sonar Reasoning scores 12 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other reasoning models in a similar price tier (median: 14).

Yes, Sonar Reasoning is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.

Sonar Reasoning supports text input.

Sonar Reasoning supports text output.

No, Sonar Reasoning does not support image input. It can only process text.

No, Sonar Reasoning is not multimodal. It only supports text input.

Sonar Reasoning has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.

No, Sonar Reasoning is proprietary. The model weights are not publicly available.

Sonar Reasoning is a proprietary model and Perplexity has not disclosed the model size or parameter count.

Sonar Reasoning achieves a score of 12 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.

Check the providers page for current API availability.

Visit the providers page to see availability.