APIs for AI agents
Search + content extraction in one platform. Web, research, and financial data and clean page content, in a single call.
Search, built for AI agents.
Try Search API →The open web alongside licensed datasets — arXiv, PubMed, full-text SEC filings, live market data, clinical trials, patents and economic indicators.
Extract content from any URL.
Try Contents API →Turn pages into clean, structured data — markdown, JSON, summaries or screenshots.
Three lines to power your agent.
No pipelines to wire up. No parsing. No cleanup.
Read the docs →from valyu import Valyu
valyu = Valyu(api_key="$VALYU_API_KEY")
response = valyu.search(
"Phase 3 melanoma immunotherapy trials"
)
for result in response.results:
print(result.title)
print(result.url)
print(result.content)State-of-the-art across research benchmarks.
DRACO is Perplexity's open expert-rubric benchmark of 100 long-form deep research tasks across 10 professional knowledge-work domains, including finance, medicine, academic research, law, and technology. Each output is graded by a per-criterion judge against a domain-expert rubric. We ran every commercially available deep research API end-to-end against the same 100 questions. Every search and research API was tested on its highest publicly-available compute tier. Parallel (Ultra8x), You(.)com Research (exhaustive), Tavily (pro), Exa (deep-reasoning), and Perplexity Deep Research (Opus 4.6). Valyu was run on Heavy mode; we offer a higher Max tier but did not use it here, since Max is more expensive per task than the field.
Cost vs accuracy across deep research APIs
