---
source_url: "https://docs.valyu.ai/overview"
title: "Valyu Documentation - AI Search API for Agents & RAG"
mirrored_at: 2026-08-29T01:31:44.309Z
host: docs.valyu.ai
cited_in_42a: true
mirror_canonical: "https://index.42a.ai/docs.valyu.ai/overview"
---

> **Original source:** https://docs.valyu.ai/overview

Valyu is search built for AI knowledge work. Most search APIs cover the open web; agents working in finance, life sciences, legal, and research need sources general web search doesn’t serve well. Valyu gives your agent one API for both - web search alongside deep, full-text retrieval across specialised sources like SEC filings, clinical trials, patents, journals, and market data - and many more.

## What you get

-   **Real-time web search** - the latest from across the internet.
-   **Specialised & proprietary sources** - academic papers, SEC filings, clinical trials, patents, drug discovery, economic data, and many more.
-   **Financial data** - stock prices, fundamentals, and market metrics.
-   **Intelligent ranking** - only the most relevant results, ready to feed an LLM.
-   **Transparent pricing** - pay per retrieval, no subscription required to start.

## How Valyu fits your stack

One API key, four building blocks, one retrieval layer underneath - your agent reaches the web and proprietary sources through the same interface.

Start with **Search** for retrieval you control, or hand the whole task to **DeepResearch** and get back a cited report.

## Get started

## Integrations

## Benchmarks

We outperform Google, Parallel, and Exa on SimpleQA and FreshQA, and across domain-specific benchmarks in finance, healthcare, and economics.

![FreshQA benchmark results comparing Valyu against Google, Parallel, and Exa](https://4ealzrotsszllxtz.public.blob.vercel-storage.com/freshqa_valyu-1400x871.png)

FreshQA: Valyu vs Google, Parallel, and Exa on 600 time-sensitive queries.

**Benchmark**

**Valyu**

**Parallel**

**Exa**

**Google**

**FreshQA** (600 time-sensitive queries)

79 %

52 %

24 %

39 %

([valyu.ai](https://www.valyu.ai/blogs/benchmarking-search-apis-for-ai-agents?utm_source=chatgpt.com "Benchmarking Search APIs for AI Agents | Valyu | Valyu"))

**SimpleQA** (4,326 factual questions)

94 %

93 %

91 %

38 %

([valyu.ai](https://www.valyu.ai/blogs/benchmarking-search-apis-for-ai-agents?utm_source=chatgpt.com "Benchmarking Search APIs for AI Agents | Valyu | Valyu"))

**Finance** (120 finance questions)

73 %

67 %

63 %

55 %

([valyu.ai](https://www.valyu.ai/blogs/benchmarking-search-apis-for-ai-agents?utm_source=chatgpt.com "Benchmarking Search APIs for AI Agents | Valyu | Valyu"))

**Economics** (100 economics questions)

73 %

52 %

45 %

43 %

([valyu.ai](https://www.valyu.ai/blogs/benchmarking-search-apis-for-ai-agents?utm_source=chatgpt.com "Benchmarking Search APIs for AI Agents | Valyu | Valyu"))

**MedAgent** (562 complex medical queries)

48 %

42 %

44 %

45 %

([valyu.ai](https://www.valyu.ai/blogs/benchmarking-search-apis-for-ai-agents?utm_source=chatgpt.com "Benchmarking Search APIs for AI Agents | Valyu | Valyu"))

Read the full breakdown in our [benchmarking blog post](https://www.valyu.ai/blogs/benchmarking-search-apis-for-ai-agents).