New search benchmark leader

Search, Rebuilt for AI Agents
_

A unified search API purpose-built for AIs, access structured real-time content from the web and proprietary sources.

Developers

Simple API, powerful results

Integrate in minutes, supported by all agent frameworks

npm install @valyu/ai-sdk

// npm install @valyu/ai-sdk
import { generateText, stepCountIs } from "ai";
import { webSearch } from "@valyu/ai-sdk";
import { openai } from "@ai-sdk/openai";

const { text } = await generateText({
  model: openai('gpt-5'),
  prompt: 'What are the latest developments in AI agents?',
  tools: {
    webSearch: webSearch(),
  },
  stopWhen: stepCountIs(3),
});

console.log(text);

// Other specialized search tools available:
// - financeSearch - Stock prices, earnings, SEC filings
// - paperSearch - arXiv, PubMed, bioRxiv articles
// - patentSearch - USPTO full-text patent search
// - economicsSearch - BLS, FRED, World Bank data

Learn More

The most accurate search API for AI — production-ready, reliable, and built with years of research.

Web Search

Full-text search across the web beyond simple links. Get back structured content.

Proprietary Content

Search paywalled content, academic research, reports across knowledge work domains.

Multi-modal

Search across text, images, tables, code, and other data modalities.

Pay-per-use

Only pay for retrievals and usage, with cost effective pricing.

Web Search

Full-text search across the web beyond simple links. Get back structured content.

Proprietary Content

Search paywalled content, academic research, reports across knowledge work domains.

Multi-modal

Search across text, images, tables, code, and other data modalities.

Pay-per-use

Only pay for retrievals and usage, with cost effective pricing.

SoTA across several benchmarks

FreshQA

About the benchmark

FreshQA is updated roughly every week, contains 600 time-sensitive questions that assess how effectively APIs handle recent and evolving information. The benchmark is critical for use cases such as news summarization, event tracking, and trend monitoring. Our evaluation used the Aug 27th test set, the most recent release available at the time of testing.

Evaluation

FreshQA was evaluated by comparing four search solutions (Valyu, Parallel, Google, Exa) on time-sensitive queries. Valyu achieved the highest performance at 79.0% accuracy, significantly outperforming others.

Try our Everything Demo App →

Content Owners

Rev Share Partner Programme

Content distribution is evolving. Millions of agents and LLMs are now retrieving and using content. We meter it, attribute it, and turn usage into revenue with attribution.

Lean More