Sonar

Name: Sonar
Author: Perplexity

PerplexityProprietaryPending Human Review

Sonar is Perplexity’s lower-cost search-grounded language model for concise answers with web citations. Its 2025 release replaced older Llama-branded online model aliases; the February update was explicitly based on Llama 3.3 70B. Search-depth settings and subsequent image-upload support extend the product without creating new catalog identities. The original Sonar Chat Completions service ended support on September 27, 2026, with remaining synchronous requests gradually reformulated through the Agent API. Sonar itself remains explicitly listed as perplexity/sonar in the current Agent API, unlike the retired Pro and research tiers mapped to presets.

2025-01-21

Llama-based decoder-only Transformer with search augmentation; current revision details undisclosed

Proprietary

Compare with other models

Specifications

Architecture: Llama-based decoder-only Transformer with search augmentation; current revision details undisclosed
License: Proprietary
Type: multimodal
Modalities: textimage

Benchmark Scores

Advanced Specifications

Model Family: Sonar
API Access: Available
Chat Interface: Not Available
Variants: sonarperplexity/sonarHigh/Medium/Low search modesFebruary 2025 Llama 3.3 update

Capabilities & Limitations

Capabilities: web-grounded answerscitationsimage inputsearch filters
Known Limitations: Search-grounded answers can still contain factual or citation errorsOriginal Chat Completions compatibility does not imply preservation of the old backendCurrent architecture and parameter count are not fully disclosed
Notable Use Cases: current-information assistantssource-linked question answeringlightweight research
Tool Use Support: Yes

Resources

Related Models

Sonar Deep Research

Perplexity

Sonar Deep Research was Perplexity’s separately named API model tier for extended research reports. It repeatedly searched and analyzed sources to produce a cited synthesis, with adjustable reasoning effort and synchronous or asynchronous research workflows. The Deep Research application was announced in February 2025, but this page dates the verifiable named API identity to March rather than assuming the app used the same model from launch. Its underlying model architecture and parameter count were not disclosed. Sonar Chat Completions support ended September 27, 2026; the provider maps this tier to Agent API research presets, and legacy asynchronous requests are no longer supported.

Sonar Reasoning Pro

Perplexity

Sonar Reasoning Pro was the higher-capability reasoning tier in Perplexity’s Sonar API, combining chain-of-thought reasoning with deeper web retrieval and more citations for multi-step questions. The distributor describes it as DeepSeek R1-powered, while the exact internal post-training recipe remains undisclosed. Public March 2025 provider documentation and serving records establish availability that month; a precise earliest launch day was not recovered. Search-effort settings belong to this model rather than separate pages. The original service ended support September 27, 2026, and compatibility requests are gradually reformulated as Agent API requests using presets, which does not establish continued serving of this historical model.

R1 1776

Perplexity

R1 1776 is Perplexity’s significant post-training of DeepSeek R1, targeting refusals and evasive responses around politically sensitive Chinese topics while retaining reasoning capabilities. It is an offline language model and does not use the Sonar search subsystem. The original publisher announcement and model repository have since become inaccessible, but the release is corroborated by the publisher’s February 18 communication, distributor records, and preserved model-card copies and weights. The MIT-licensed 671B checkpoint supports local deployment with substantial hardware resources. Perplexity removed the hosted model on August 1, 2025. Claims of being unbiased are publisher positioning rather than an established guarantee.