We’ve built a search index of billions of webpages to provide real-time, quality information from the web. Now developers have access to the full power of our index, providing the most accurate results in milliseconds.
The Search API (POST /search) returns raw, ranked web results — titles, URLs, snippets, and dates — without LLM processing. Plug these directly into your own models, RAG pipelines, or applications.
from perplexity import Perplexity
client = Perplexity()
search = client.search.create(
query="latest AI developments",
max_results=5,
max_tokens_per_page=2048
)
for result in search.results:
print(result.title, result.url)
Key features
- Raw ranked results — titles, URLs, snippets, dates, and extracted content
- Domain filtering — allowlist or denylist specific domains
- Language filtering — ISO 639-1 language codes
- Date filtering — recency filter or precise date ranges
- Multi-query — pass up to 5 queries in a single request
- $5 per 1,000 requests — no token-based costs
Docs: Search API Quickstart | API Reference