Sonar Reasoning Pro

Pricing — 1 offering(s)

Showing the active price and any recorded history. Full pricing history is available via the paid API — see API docs.

Capability profile

Operator guidance

Route here when the task genuinely needs chain-of-thought analysis on top of cited web search and can tolerate higher latency. For simple factual lookups it is slower and dearer than Sonar with no benefit. For exhaustive hundreds-of-sources reports, Sonar Deep Research is purpose-built and prices its citation/reasoning tokens separately. Outside Perplexity, pairing a standalone reasoning model (o-series, DeepSeek R1, Claude with extended thinking) with your own retrieval gives more control but loses the tuned grounding.

Use cases

• Complex, multi-step analytical questions that need both live web evidence and visible step-by-step reasoning
• Tasks with strict formatting or instruction constraints where a plain search model drifts
• Comparative / evaluative research questions (surfacing more citations per search than the plain search models) that don't need a full Deep Research report

Limitations

• Search-grounded only, with a mandatory per-request search-context fee ($6-$14 / 1K requests) on top of token cost
• Perplexity explicitly does not recommend it for simple factual queries, basic retrieval, or speed-critical applications
• Chain-of-thought tokens are billed as normal output tokens on this variant, so verbose reasoning directly inflates cost
• Underlying base model is not named in current Perplexity docs; the DeepSeek-R1 basis is a prior Perplexity claim
• Legacy Sonar Chat Completions surface migrating to the Agent API (support until 2026-09-27, Perplexity changelog)
• Capability ratings are qualitative from Perplexity's positioning; no independent published benchmark for the API model

Citations

• Perplexity API — Models overview
• Perplexity API — Sonar models
• Perplexity API — Pricing
• Sonar Reasoning Pro on OpenRouter (secondary — DeepSeek-R1 basis, CoT)