Search, answers and research
Perplexity
Made by Perplexity AI
An answer engine that cites its sources — the safest of these for anything factual.
What it is
Perplexity searches live sources and answers with citations attached. That single design decision makes it far safer than a plain chatbot for anything you'd be embarrassed to get wrong: an employer's actual funding position, a salary range, who really said the thing in the headline.
Use it as a research assistant, not an oracle. The right habit is to read the answer, then click at least one citation and check the source says what the summary claims.
The free plan gives limited daily searches on basic models, which is enough for interview prep. Pro and Max raise the limits and add stronger models.
Follow the citations. It sometimes summarizes a source more confidently than the source does.
Published price
- FreeLimited daily searches, basic models$0/month
- Pro$17/month billed annually$20/month
- Max$167/month billed annually$200/month
Source: Perplexity's pricing page · Last checked 17 September 2026
Benchmarks
The published figures for Perplexity, copied exactly as their sources give them and checked 17 September 2026. Each one names the test, who ran it and when, and says when the number comes from the maker rather than an independent tester.
- SimpleQA (F-score)85.8
factual accuracy on short questions with one checkable answer · tested: Perplexity Sonar Pro
Perplexity's own Sonar Pro announcement · 21 January 2025 · maker's own figures
The maker's own figure. It is the number they lead with, and no independent tester has published a comparable SimpleQA run for Sonar Pro.
- MMLU80.1%
broad multiple-choice general knowledge · tested: Perplexity Sonar
TPS Report · model released 27 January 2025 · independent
- HumanEval72.5%
small Python programming problems solved correctly · tested: Perplexity Sonar
TPS Report · model released 27 January 2025 · independent
- GPQA48.0%
graduate-level science questions · tested: Perplexity Sonar
TPS Report · model released 27 January 2025 · independent
- SciCode22.9%
scientific coding problems solved correctly · tested: Perplexity Sonar
Benchmark List · 21 July 2026 · independent
Perplexity benchmarks its Sonar models rather than the search product you use in the browser, so read these as a floor, not a ceiling. The headline factuality figure is Perplexity's own, from the Sonar Pro launch post.
Figures copied from the sources above, checked 17 September 2026.
Where to read today's numbers
Scores move, so these are the boards that keep them current.
- Vals AI benchmarksIndependent
Independent evaluations on real professional tasks — law, finance, tax, medicine — rather than vendor demos.
- Search and answer-quality researchIndependent
Independent evaluations of retrieval-based answering; treat search leaderboards as directional.
- LMArena leaderboardIndependent
Ranks models by blind head-to-head votes from the public. Good for a feel for general quality, weak on specialist work.
How it performs, in my experience
Cites its sources on every answer, which makes it far safer than a plain chatbot for anything factual.
Free value
4 / 5
How much you get without paying.
Performance
5 / 5
How well it does its main job.
Range of uses
4 / 5
How many different jobs it suits.
Cites its sources, which makes it the one to use for anything factual. These scores are my own judgment, not a measurement — the benchmark links above are the independent version.
Prompting it from this site
Endpoint wired, waiting on a key
Sonar Pro searches the live web and answers with sources. Runs through OpenRouter once a key is saved.
Use it for
- Researching an employer before an interview
- Checking a salary range
- Finding the original source of a claim
Running it yourself
The software is local, the model isn't
Perplexity's own models and its search index are closed and hosted. What you can do locally is call its API from your own code.
What you need first
- Python 3.8+ or Node.js 18+
- A paid Perplexity API key
Step by step
1.Install any OpenAI-compatible client
pip install openai2.Set your key
export PERPLEXITY_API_KEY=pplx-...3.Point the client at their endpoint
python -c "import os;from openai import OpenAI;c=OpenAI(api_key=os.environ['PERPLEXITY_API_KEY'],base_url='https://api.perplexity.ai');print(c.chat.completions.create(model='sonar-pro',messages=[{'role':'user','content':'hello'}]).choices[0].message.content)"
The searching is what you're paying for. A local model can't replace it, because the index isn't public.