Perplexity launches Search API offering web-scale indexed search & public developer access

Perplexity has announced the launch of its Search API, giving developers access to the same index of hundreds of billions of web pages that powers its answer engine. This API is designed to offer a credible alternative to Google's dominance in developer-facing search infrastructure by making public a web-scale retrieval stack previously out of reach. The Search API is available through the new API Platform with software development kits for Python and TypeScript, and is targeted at startups, enterprises, and agent builders seeking robust search capabilities.

The API includes regional targeting by ISO country code, date range filters, and domain allowlists or denylists of up to 20 entries. An academic mode prioritizes scholarly sources, while multi-query requests allow up to five queries at once. Developers can set results per call between one and 20, and adjust content extraction with a max_tokens_per_page setting, defaulting to 1024 tokens. Responses return title, URL, snippet, publication date, and last updated fields.

Pricing is $5 per 1,000 requests with no token-based fees, and rate limits scale with usage tiers linked to total spend. An open evaluation framework is provided for quality comparisons, and the platform integrates Search with Sonar chat models to deliver grounded generative answers.