Sulat.com
AI models
$10 off the fastest DeepSeek V4.1 Flash, Kimi K3 and GLM 5.3 from Synthetic
Eden AI logo

Model details

Sonar Deep Research

Sonar Deep Research is a reasoning-focused model within Perplexity's Sonar family, designed to conduct exhaustive searches across hundreds of sources and assemble them into detailed, expert-level reports rather than single answers. Perplexity positions it for situations where the reader needs a structured view of many documents, their disagreements, dates, and underlying claims, making it well suited to work that depends on breadth of evidence and explicit citation of where each finding originated.

In practical use, Sonar Deep Research fits multi-source investigative tasks such as market and competitor mapping, academic and literature reviews, due-diligence and vendor evaluation, and tracking regulation or emerging trends where separating enacted rules from proposals and commentary matters. Pricing on the official Perplexity documentation reflects its research workflow, with separate rates for input, output, citation, search-query, and reasoning tokens, while the Sonar line is being phased toward Perplexity's Agent API, with support scheduled through late September 2026.

Eden AIperplexityai/sonar-deep-researchsonar

Quick Info

Powered by
Provider
Eden AI
Model key
perplexityai/sonar-deep-research
Release date
Feb 1, 2025
Last updated
Sep 1, 2025
Knowledge cutoff
2025-01
Input modalities
Output modalities
Capabilities

Cost

Input token cost
$2.00
Output token cost
$8.00

Limits

Output tokens
32,768 tokens
Context window
128,000 tokens

Transparent token rates

Compare Sonar Deep Research pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about Sonar Deep Research

We haven't found any news about Sonar Deep Research yet. New models can take a few days to get coverage, so check back soon or look again now.

Videos about Sonar Deep Research

More models around Sonar Deep Research