Sonar Pro tackles complex questions that need deeper research and provides more sources.
Context Window
200.0K
Max Output
128.0K
Avg output tokens (7d)
166 tokens
Input Price (Auto)
$3.00/1M
Output Price (Auto)
$15.00/1M
Cache Read (Auto)
$1.50/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
3.6
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
57.8%
Better than 32% of models compared
HLE
Humanity's Last Exam
6.6%
Better than 43% of models compared
Coding
LiveCodeBench
Contamination-free coding benchmark
27.5%
Better than 30% of models compared
Math
AIME
American Invitational Mathematics Examination
29.0%
Better than 55% of models compared
Math-500
Diverse mathematical problem solving benchmark
74.5%
Better than 36% of models compared
Knowledge
MMLU-Pro
Professional and academic subject knowledge
75.5%
Better than 50% of models compared
Last updated Sep 7, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare Perplexity Pro with similar models from the same provider or model family.
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 Deep Research
sonar-deep-researchAnalyzes 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.
Perplexity Simple
sonarA Perplexity model that gives fast, straightforward answers.
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.
Synth 2.5 Pro Preview
synth-2.5-proSynth 2.5 Pro Preview is a low-cost text model designed for role-play, character dialogue, and collaborative storytelling.
GPT 6 Astra Pro
openai/gpt-6-astra-proGPT 6 Astra in Pro reasoning mode. Uses additional model work for difficult tasks, with higher latency and token usage at the same per-token rates. Reasoning effort remains independently configurable.