Skip to content

Perplexity settings guide

Perplexity AI · AI Search · Real-time Web

Search / ResearchFree tier
Token burn
Low burn

Token-efficient; free tiers go a long way. Last reviewed September 2026; plans and model names change often, so check the tool's own pricing page before you buy.

1

Use Perplexity when you need current information with sources; open the citations for anything you will rely on.

2

Ask follow-ups in the same thread so it narrows the search instead of starting over.

3

Use Pro Search for multi-step questions that need several searches combined.

4

Organise ongoing research in Spaces so threads and files for one project stay together.

5

Share a thread link when a colleague needs to see the sources, not just your summary.

6

For API work, pick the model by need: Sonar ($1 in / $1 out per million tokens) for quick answers, Sonar Pro ($3 / $15) for harder questions, Sonar Deep Research for reports (docs.perplexity.ai, September 2026).

7

Request fees on the API scale with search context size (low, medium, high); use low for simple lookups.

API cost estimate

Monthly cost at list prices (September 2026), before and after a token cut you choose.

Now
$0.48
₹40
After a 25% cut
$0.36
₹30
Saved per month
$0.12
₹10

Assumes about 600 input and 200 output tokens per request (low burn). Excludes caching discounts, search or request fees and taxes. Check the vendor's pricing page before budgeting.

Reveaxa guide reference: RVX-T-perplexity