Sonar Reasoning Pro
Sonar Reasoning Pro combines the deepest web retrieval in the Sonar family with chain-of-thought reasoning to return well-sourced, structured answers within a context window of 127K tokens.
import { streamText } from 'ai'
const result = streamText({ model: 'perplexity/sonar-reasoning-pro', prompt: 'Why is the sky blue?'})Frequently Asked Questions
What makes Sonar Reasoning Pro different from Sonar Reasoning?
Sonar Reasoning Pro combines Pro-level deep web retrieval (more sources) with chain-of-thought reasoning. Standard Sonar Reasoning uses base-level retrieval with reasoning. The Pro variant goes further on both search and deliberation.
How does Sonar Reasoning Pro compare to chaining a search API with a separate reasoning model?
Sonar Reasoning Pro integrates search, retrieval, source evaluation, reasoning, and cited answer generation into a single API call. This cuts latency and operational complexity versus wiring separate services. The model is tuned to reason over its own search results.
What types of queries benefit most from Sonar Reasoning Pro?
Competitive intelligence, regulatory research, technical due diligence, and strategic analysis when the answer depends on reasoning across many sources. It fits questions that need both broad retrieval and structured analysis.
What is the context window for Sonar Reasoning Pro?
127K tokens. This supports extended multi-turn research sessions where prior search results and reasoning inform subsequent queries.
How much does Sonar Reasoning Pro cost?
Pricing appears on this page and updates as providers adjust their rates. AI Gateway routes traffic through the configured provider.
How do I authenticate with Sonar Reasoning Pro through AI Gateway?
Use your AI Gateway API key with the model identifier `
perplexity/sonar-reasoning-pro`. AI Gateway handles provider routing and authentication. You don't need a separate Perplexity API key when using gateway-managed access.Does Sonar Reasoning Pro show its reasoning process?
Yes. The chain-of-thought reasoning trace appears in the response. It shows how the model analyzed and connected information from the retrieved sources to reach its conclusion.