Perplexity Launches Context API to Extract Web Content in Target Formats
Perplexity has launched the Context API, which extracts useful content from lists of webpages and returns it in a target format, making it suitable for various AI agent frameworks. Aravind Srinivas says it outperforms other solutions in performance, latency, and cost. According to the cited official information, each call can read up to 10 URLs and return .md, HTML, links, and webpage snippets. It provides usable content for 92.3% of URLs, with 87.9% fact recall and 80.3% content precision, at a price of $1/1000 URLs fetched.
Why read this
AI score 63
The original source also provides webpage retrieval limits, content availability rates, and pricing, which can be used to evaluate the cost and quality of integrating the API into agent workflows.
Topics
View original postPerplexity Context API is live. Context API reads up to 10 URLs per call and returns clean .md, HTML, links, and snippets per page. It returns usable content for 92.3% of URLs, 87.9% fact recall, and 80.3% content precision at $1/1000 URLs fetched. https://t.co/9hoEcePh1B https://t.co/OJ5gvRdq2B
View original
Perplexity Context API is live. Context API reads up to 10 URLs per call and returns clean .md, HTML, links, and snippets per page. It returns usable content for 92.3% of URLs, 87.9% fact recall, and 80.3% content precision at $1/1000 URLs fetched. https://t.co/9hoEcePh1B https://t.co/OJ5gvRdq2B
Body
Introducing Perplexity Context API: allows you to fetch useful content from a list of webpages in whatever target format you seek. Usable inside any agentic harness. Outperforms anything else out there on performance, latency, and costs.
AI Trends