All AI models · LLM benchmarks · Methodology

Perplexity

Sonar Deep Research

Sonar search model for current answers, retrieval, and citation-backed chat

Model facts

Context window
128K tokens
Maximum output
33K tokens
Cheapest paid input
$2 per 1M tokens
Cheapest paid output
$8 per 1M tokens
Open weights
no
Providers
7

Capabilities and modalities

reasoning, temperature control, text.

Observed price history

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

API providers

  • Eden AI — model id perplexityai/sonar-deep-research; $2 input / $8 output per 1M tokens; provider documentation
  • Helicone (Perplexity) — model id sonar-deep-research; $2 input / $8 output per 1M tokens; provider documentation
  • Kilo Gateway (Perplexity) — model id perplexity/sonar-deep-research; $2 input / $8 output per 1M tokens; provider documentation
  • LLMTR — model id perplexity/sonar-deep-research; $2 input / $8 output per 1M tokens; provider documentation
  • OpenRouter — model id perplexity/sonar-deep-research; $2 input / $8 output per 1M tokens; provider documentation
  • Perplexity (Perplexity) — model id sonar-deep-research; $2 input / $8 output per 1M tokens; provider documentation
  • SAP AI Core — model id sonar-deep-research; $2 input / $8 output per 1M tokens; provider documentation