Sonar Deep Research
VerifiedPerplexity's Sonar Deep Research excels at in-depth text analysis with large context.
About Sonar Deep Research
Sonar Deep Research functions as a proprietary text-based LLM from Perplexity AI. Its 128000-token context window enables processing of lengthy documents and multi-turn research sessions without truncation. The model remains closed-weight with no public parameter count disclosed.
Designed for depth rather than breadth, it prioritizes coherent synthesis over long contexts. Users apply it to tasks such as literature reviews, multi-source analysis, and iterative question refinement where continuity matters.
Typical usage involves Perplexity's platform for research queries that exceed standard context limits. It delivers structured responses while maintaining factual grounding across extended threads.
Capabilities
How Sonar Deep Research compares
Sonar Deep Research (striped bar) vs other language models on intelligence, speed and price.
Price
USD per 1M output tokens · Lower is better · Sonar Deep Research ranks #96 of 98
Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Comprehensive Topic Exploration
Sonar Deep Research handles multi-step queries requiring synthesis of information across sources, leveraging its 128k token context for sustained analysis.
Report Generation on Current Events
The model supports creation of structured summaries that incorporate up-to-date details through Perplexity's search integration.
Academic and Technical Literature Review
It excels at processing long documents and maintaining coherence over extended research sessions within the given context window.
Strengths & limitations
Strengths
- +Strong search integration for current information
- +Transparent sourcing and citations
- +Effective at deep research tasks
- +Handles extended context windows
Limitations
- –Text-only modality
- –Dependent on external search quality
- –Less specialized for creative or coding tasks
Cost calculator
Estimate what Sonar Deep Research would cost for your usage.
Based on Sonar Deep Research's $2.00/1M input · $8.00/1M output. Estimate only — actual cost varies by provider and caching.
Quick start
OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "perplexity/sonar-deep-research",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: perplexity/sonar-deep-research
Editor's verdict
Sonar Deep Research is Perplexity's proprietary language models with a 128K-token context window.
At $8.00 per 1M output tokens, it is premium-priced for its class.
It is available through Perplexity's API and aggregators like OpenRouter.
Best suited to strong search integration for current information and transparent sourcing and citations.
Frequently asked questions
The model supports a context length of 128000 tokens as specified in its technical details.
User reviews
Real, verified reviews from the community shape this model's rating.
Loading reviews…
Other Sonar models
Sibling versions in the Sonar family from Perplexity.
Similar models
Other language models worth comparing.