Skip to content
AI Atlas
ModelActive

Sonar Deep Research

Perplexity AI

Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...

quality50

Updated 3 h ago · first seen 11 Sept 2026

model_01M294WWJWDHW2Y1S0DWZFEKX9

Context
128K tokens
T2 · 3 h ago
Released
7 Mar 2025
T2 · 3 h ago

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history

13 claims · 13 properties

Release daterelease_date1

Claim history for Release date
ValueValid from → toStatusSourceConfidenceExtractor
7 Mar 2025currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Context windowcontext_length1

Claim history for Context window
ValueValid from → toStatusSourceConfidenceExtractor
128K tokenscurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Max outputmax_output_tokens1

Claim history for Max output
ValueValid from → toStatusSourceConfidenceExtractor
115.2K tokenscurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Modalitiesmodalities1

Claim history for Modalities
ValueValid from → toStatusSourceConfidenceExtractor
textcurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Input modalitiesmodalities_input1

Claim history for Input modalities
ValueValid from → toStatusSourceConfidenceExtractor
textcurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Output modalitiesmodalities_output1

Claim history for Output modalities
ValueValid from → toStatusSourceConfidenceExtractor
textcurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Descriptiondescription1

Claim history for Description
ValueValid from → toStatusSourceConfidenceExtractor
Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Instruct typeinstruct_type1

Claim history for Instruct type
ValueValid from → toStatusSourceConfidenceExtractor
deepseek-r1currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Openrouter idopenrouter_id1

Claim history for Openrouter id
ValueValid from → toStatusSourceConfidenceExtractor
perplexity/sonar-deep-researchcurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Reasoningreasoning1

Claim history for Reasoning
ValueValid from → toStatusSourceConfidenceExtractor
YescurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Structured outputstructured_output1

Claim history for Structured output
ValueValid from → toStatusSourceConfidenceExtractor
NocurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Supported parameterssupported_parameters1

Claim history for Supported parameters
ValueValid from → toStatusSourceConfidenceExtractor
frequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, temperature, top_k, top_p, web_search_optionscurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Tool callingtool_calling1

Claim history for Tool calling
ValueValid from → toStatusSourceConfidenceExtractor
NocurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →