All AI models · LLM benchmarks · Methodology

Perplexity

Sonar Reasoning Pro

Web-grounded Sonar for multi-step research questions that need cited reasoning

Model facts

Context window
128K tokens
Maximum output
4K tokens
Cheapest paid input
$2 per 1M tokens
Cheapest paid output
$8 per 1M tokens
Open weights
no
Providers
10

Capabilities and modalities

reasoning, structured output, attachments, temperature control, text, image.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
default18.0not measurednot measurednot measured

Observed price history

  • 2026-08-24: $2 input / $8 output per 1M tokens

API providers

  • DevPass (LLM Gateway) — model id sonar-reasoning-pro; $2 input / $8 output per 1M tokens; provider documentation
  • Eden AI — model id perplexityai/sonar-reasoning-pro; $2 input / $8 output per 1M tokens; provider documentation
  • Helicone (Perplexity) — model id sonar-reasoning-pro; $2 input / $8 output per 1M tokens; provider documentation
  • Kilo Gateway (Perplexity) — model id perplexity/sonar-reasoning-pro; $2 input / $8 output per 1M tokens; provider documentation
  • LLM Gateway (Perplexity) — model id perplexity/sonar-reasoning-pro; $2 input / $8 output per 1M tokens; provider documentation
  • OpenRouter — model id perplexity/sonar-reasoning-pro; $2 input / $8 output per 1M tokens; provider documentation
  • Opper — model id perplexity/sonar-reasoning-pro; $2 input / $8 output per 1M tokens; provider documentation
  • Perplexity — model id sonar-reasoning-pro; $2 input / $8 output per 1M tokens; provider documentation
  • AnyAPI — model id perplexity/sonar-reasoning-pro; not published input / not published output per 1M tokens; provider documentation
  • Vercel AI Gateway — model id perplexity/sonar-reasoning-pro; not published input / not published output per 1M tokens; provider documentation