Perplexity Sonar Reasoning
Perplexity's reasoning model with chain-of-thought and integrated web search.
Perplexity Sonar Reasoning is text & chat AI model from Custom, priced at €1.00 per 1M input tokens with a 127K tokens context window.
0.7
Pricing
API Integration
Use our OpenAI-compatible API to integrate Perplexity Sonar Reasoning into your application.
npm install railwailimport railwail from "railwail";
const rw = railwail("YOUR_API_KEY");
// Simple — just pass a string
const reply = await rw.run("sonar-reasoning", "Hello! What can you do?");
console.log(reply);
// With message history
const reply2 = await rw.run("sonar-reasoning", [
{ role: "system", content: "You are a helpful assistant." },
{ role: "user", content: "Explain quantum computing simply." },
]);
console.log(reply2);
// Full response with usage info
const res = await rw.chat("sonar-reasoning", [
{ role: "user", content: "Hello!" },
], { temperature: 0.7, max_tokens: 500 });
console.log(res.choices[0].message.content);
console.log(res.usage);Deep dive — Perplexity AI's Perplexity Sonar Reasoning
Perplexity AI was founded in August 2022 by Aravind Srinivas (CEO, former OpenAI and DeepMind researcher), Denis Yarats (former Quora), Johnny Ho (former Quora) and Andy Konwinski (Databricks co-founder). Headquartered in San Francisco, Perplexity built one of the first AI-native search products — an answer engine combining live web retrieval with LLM synthesis and inline citations. The company has raised over $500M from investors including IVP, Nvidia, NEA, Jeff Bezos and SoftBank, with a 2024 valuation above $9B. Perplexity offers its Sonar API for developers to access search-grounded LLM responses. Sonar Reasoning, released January 2025, is built on the open-source DeepSeek-R1 reasoning model wrapped in Perplexity's live web-search retrieval stack with the reasoning trace exposed in the API response.
Visit Perplexity AI →Sonar Reasoning is Perplexity's hosted deployment of DeepSeek-R1 (671B Sparse Mixture-of-Experts, 37B active per token, DeepSeekMoE architecture with Multi-head Latent Attention) wrapped in Perplexity's retrieval pipeline. The base model uses 256 fine-grained experts plus shared experts, top-8 routing, 128K context, and was trained by DeepSeek with the GRPO reinforcement-learning recipe described in the R1 technical report. Perplexity hosts the model on US-based infrastructure, applies its own safety post-training on the Perplexity domain, and exposes the reasoning chain-of-thought as a separate field in the API response alongside the final answer. Each request triggers a live web-search retrieval that injects ranked passages into the model context with source URLs returned alongside the answer. Released January 2025 via the Sonar API.
- Parameters
- 671B total, 37B active per token (DeepSeek-R1 base)
- Context
- 127K tokens
- Combines live web search with explicit reasoning traces
- Returns ranked citations with source URLs alongside answers
- Strong on math, logic and research-style questions
- Reasoning chain-of-thought exposed in the API
- Knowledge always current via live search — bypasses model cutoff limits
- Cheaper than OpenAI o-series for comparable reasoning quality at release
- Hosted on Perplexity's US infrastructure
- Best for: research-grade Q&A, market intelligence, citation-required workflows, fact-grounded reasoning.
Inherits DeepSeek-R1's training pipeline (DeepSeek-V3-Base ~14.8T tokens of multilingual web, code and math, followed by the R1 reasoning RL stage with GRPO). Perplexity adds retrieval-grounded supervised fine-tuning on its domain. Base model knowledge cutoff approximately July 2024 — but live search overrides for current questions.
License: Perplexity API Terms of Service. The base DeepSeek-R1 weights are MIT-licensed and can be self-hosted separately, but the live-search and reasoning-citation pipeline are Perplexity-specific and hosted-only.
Known limitations
- Reasoning latency is high (typically 5-20s) due to thinking tokens plus search
- Quality depends on what the search retrieves — bad sources lead to bad answers
- Per-call cost includes reasoning tokens plus search — can be expensive on long answers
- No vision input
- Reasoning trace can be verbose and not directly user-facing
- Hosted-only — Perplexity does not offer self-hosting for the Sonar stack
Frequently asked questions
Related Models
View all Text & ChatClaude Opus 4
Anthropic's most powerful model. Exceptional at complex analysis, agentic tasks, and extended reasoning.
Claude Sonnet 4
Anthropic's most capable model. Excellent for complex analysis, coding, math, and creative writing.
DeepSeek V3.1
DeepSeek's refreshed V3.1 release. 671B MoE / 37B active. Tops open-weights leaderboards on coding and reasoning.
DeepSeek V4 Pro
DeepSeek's April 2026 flagship. 1.6T MoE / 49B active params, 1M context, rivals top closed-source models on STEM and coding at a fraction of the price.
Start using Perplexity Sonar Reasoning today
Get started with free credits. No credit card required. Access Perplexity Sonar Reasoning and 100+ other models through a single API.