Sonar Pro
4934°
Run this model
Offers / Ads
Perplexity | 200,000 token context | $3.00/M input, $15.00/M output. Note: Sonar Pro pricing includes Perplexity search pricing. See details hereOpens in new tab For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like double the number of citations per search as Sonar on average. Plus, with a larger context window, it can handle longer and more nuanced searches and follow-up questions.
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
Captain's notes
Notes from 2026-10-13
Sonar Pro is Perplexity's advanced search-augmented language model, built for multi-step research queries that need real-time web results and detailed citations. It doubles the citation count of the base Sonar model and brings a 200,000-token context window, making it practical for long, iterative research sessions. It suits developers and enterprises who need grounded, sourced answers rather than a general-purpose chat model.
Known for
- Real-time web search baked in, not bolted on as an afterthought
- Roughly double the citations per search compared to standard Sonar
- 200,000-token context handles long threads and follow-up chains
- Designed for multi-step, in-depth queries rather than single-turn chat
- Vision support alongside text
Watch out for
- Pricing covers both model tokens and Perplexity search costs combined; output at $15/M adds up fast.
- Closed API only — no weights to download, no local deployment.
- Not a general coding or reasoning model; the search layer is the point, not raw capability.
Best for
Prompts to try
Deep multi-step research
I'm researching the current state of solid-state battery commercialization. Start with who the leading manufacturers are, then follow up on their announced production timelines, and finally summarize the main technical obstacles still blocking mass-market adoption. Cite your sources throughout.
Competitive landscape snapshot
Give me a detailed comparison of the three largest cloud hyperscalers' current AI infrastructure offerings — compute, storage, and managed model services. I want recent pricing where available, key differences, and which workloads each is best suited for.
Iterative policy analysis
Walk me through the current regulatory status of autonomous vehicle deployment in the US, EU, and China. Then follow up: where have rules changed in the last twelve months, and what do industry groups say are the remaining sticking points? Cite specific sources for each jurisdiction.
Compare with
- Sonar Pro SearchAPI-only model200,000 token context · $3.00/M input, $15.00/M output
- Sonar Reasoning ProAPI-only model128,000 token context · $2.00/M input, $8.00/M output
- Step 5 PreviewOpen-weights model1,048,576 token context · $1.00/M input, $2.70/M output
- Seed 2.0 proOpen-weights model256,000 token context · $0.50/M input, $3.00/M output
More text models from perplexity
Questions people ask
- Can I run Sonar Pro locally?
- No. Sonar Pro is a closed API product from Perplexity; the weights are not published and there is no local deployment option.
- What does Sonar Pro actually cost, and how big is the context?
- Input is $3.00 per million tokens and output is $15.00 per million tokens; that pricing bundles Perplexity's search costs. The context window is 200,000 tokens.
- How does Sonar Pro differ from the base Sonar model?
- Sonar Pro handles more complex, multi-step queries, provides roughly double the citations per search on average, and offers a larger context window for longer research threads.
Captain's verdictIf you need a model that searches the web, cites its sources, and can chase a research thread across many follow-ups, Sonar Pro is purpose-built for exactly that.
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.
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.
Sonar Pro 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.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153