Analyzes hundreds of sources, delivering expert-level insights in minutes. Deep Research API has a 93.9% accuracy on SimpleQA benchmark and attains a score of 21.1% accuracy on Humanity's Last Exam, significantly outperforming Gemini Thinking, o3-mini, o1, and DeepSeek-R1.
Added Feb 25, 2025
Context Window
60.0K
Max Output
128.0K
Input Price (Auto)
$3.40/1M
Output Price (Auto)
$13.60/1M
Cache Read (Auto)
$1.70/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
No benchmark data is available yet for this model.
Providers
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare Perplexity Deep Research with similar models from the same provider or model family.
Perplexity Simple
sonarA Perplexity model that gives fast, straightforward answers.
Perplexity Pro
sonar-proSonar Pro tackles complex questions that need deeper research and provides more sources.
Perplexity Reasoning Pro
sonar-reasoning-proPerplexity's Sonar Reasoning Pro uses DeepSeek R1's thinking process combined with looking up on the web to tackle complex questions that need deeper research and provides more sources.
Perplexity Academic Researcher
perplexity-academic-researcherSonar Reasoning Pro with Perplexity's academic search mode. Prioritizes scholarly and peer-reviewed sources from academic repositories and returns cited research synthesis.
Sofya Research
sofya-researchSofya Research runs a web research agent and returns a structured report with sources, sub-queries, and token usage metadata.
Linkup Research High
linkup-research-highLinkup Research with high reasoning depth. Runs an async web research agent and returns a sourced answer for complex research tasks. Responses can take several minutes.