Can I run Sonar Deep Research locally?

No. Perplexity has not released open weights; the model is available through the API only.

What does Sonar Deep Research cost and how much context does it have?

Pricing is $2.00 per million input tokens and $8.00 per million output tokens, with a 128,000-token context window.

How does Sonar Deep Research differ from standard Sonar models?

Standard Sonar models answer with web-grounded responses in a single pass; Deep Research autonomously runs multiple search and evaluation steps before producing a full synthesised report, making it better suited to complex, multi-faceted questions.

Sonar Deep Research

3989°

#llm #perplexity #reasoning #research #summarization

Run this model

Offers / Ads

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

Perplexity | 128,000 token context | $2.00/M input, $8.00/M output. Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers information. This enables comprehensive report generation across domains like finance, technology, health, and current events. Notes on Pricing (SourceOpens in new tab)

Guides for this model

Open weights vs open source vs API-only: what you are actually allowed to do

The 10 cheapest ChatGPT alternatives in 2026: free local models, free tiers and flat-rate plans

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Sonar Deep Research is Perplexity's autonomous research model: give it a complex question and it searches, reads, and evaluates sources across multiple steps before returning a synthesised report. The live-web retrieval sets it apart from static models, making it useful for topics where recency matters. It suits analysts, journalists, and anyone who would otherwise spend an hour tabbing between sources.

Known for

Autonomous multi-step web search with source evaluation built in
Generates comprehensive reports, not just short answers
Covers finance, health, technology, and current events well
Refines its search strategy mid-task as new information surfaces

Watch out for

Closed weights, API-only: you cannot run this locally or inspect the model.
Output costs $8.00 per million tokens; long research reports add up fast.
128k context is solid but not in the long-context tier; very large document sets may not fit.

Best for

Research

Summaries

Reasoning

Prompts to try

Competitive landscape report

Research the current competitive landscape for solid-state battery manufacturers. Identify the five leading companies, summarise their technology approaches, funding status, and projected commercialisation timelines. Cite your sources and note where the evidence is thin or contested.

Policy change impact analysis

Investigate recent changes to US pharmaceutical drug pricing policy in 2025. Explain what changed, which drugs or manufacturers are most affected, and what analysts are saying about downstream effects on patients and insurers. Synthesise across multiple sources.

Emerging technology deep dive

Give me a research report on the current state of neuromorphic computing. Cover the main hardware approaches, which organisations are leading, where it outperforms conventional chips, and what the realistic obstacles to mainstream adoption are.

Compare with

Gemma 2 27B
Open-weights model
8,192 token context · $0.65/M input, $0.65/M output
Sonar Pro Search
API-only model
200,000 token context · $3.00/M input, $15.00/M output
Sonar Pro
API-only model
200,000 token context · $3.00/M input, $15.00/M output
Sonar Reasoning Pro
API-only model
128,000 token context · $2.00/M input, $8.00/M output

More text models from perplexity

Questions people ask

Can I run Sonar Deep Research locally?: No. Perplexity has not released open weights; the model is available through the API only.
What does Sonar Deep Research cost and how much context does it have?: Pricing is $2.00 per million input tokens and $8.00 per million output tokens, with a 128,000-token context window.
How does Sonar Deep Research differ from standard Sonar models?: Standard Sonar models answer with web-grounded responses in a single pass; Deep Research autonomously runs multiple search and evaluation steps before producing a full synthesised report, making it better suited to complex, multi-faceted questions.

Captain's verdict
If you need a thorough, sourced research report and do not want to do the legwork yourself, this is the most direct route to one.

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Not this creator?

Get your own badge

How this score adds up

This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

Similar Models

AI Models for Image, Video & Text Generation

Sonar Deep Research is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.

More Text / LLM models llm perplexity reasoning research summarization

Browse by Model Family