exa/contents
Extract full page contents for a set of URLs. Fetch full page text, summaries, and metadata for a list of URLs with cached instant results or live crawl fallback.
Example output — click Run to generate your own
API README
Exa Contents
Extract clean, LLM-ready content from any URL — handles JavaScript-rendered pages, PDFs, and complex layouts automatically.
Highlights
Three content modes — Get full text (markdown), key highlights (extractive excerpts), or LLM-generated summaries. Combine freely in a single request.
Token-efficient highlights — Return only the most relevant excerpts (10x fewer tokens than full text). Ideal for agent workflows and RAG pipelines.
Subpage crawling — Automatically discover and extract content from linked pages within a site. Target specific sections with keywords.
Content freshness control — Choose between cached content (fast) or live crawl (fresh) with max_age_hours.
Pricing
| Component | Price |
|---|---|
| Per URL extracted | $0.003 |
| Summary (per URL) | +$0.001 |
When to Use
| ✅ Good fit | ❌ Consider alternatives |
|---|---|
| Extracting article content for RAG | Large-scale web crawling (use dedicated crawlers) |
| Reading documentation pages | Real-time monitoring |
| Structured data extraction from pages | Image/video content extraction |
| Research & fact-checking from known URLs | Search discovery (use exa/search instead) |
| Pulling content from PDFs | Sites requiring authentication |
Technical Specs
| Spec | Value |
|---|---|
| Input | Array of URLs (up to 100) |
| Output | Text (markdown), highlights, summary per URL |
| Content types | HTML, JS-rendered pages, PDFs |
| Freshness | Configurable cache vs livecrawl |
| Subpage crawl | Up to 50 linked pages per URL |
| Execution | Sync (direct response) |
| Provider | Exa (api.exa.ai) |