serp.fast

Valyu

AI-native search and retrieval API for LLMs and agents, querying the open web plus proprietary sources like arXiv, PubMed, SEC filings, and financial data.

Nathan Kessler
By Nathan KesslerUpdated

Each tool is evaluated against our methodology using public docs, vendor demos, and hands-on testing.

AI search APIs are the infrastructure layer that gives large language models access to current web information. Unlike traditional search engines, these APIs return semantically relevant, structured results optimized for retrieval-augmented generation (RAG) and AI agent workflows. They are used by AI products that need to answer questions about the real world beyond their training data.

Visit Valyu →See pricing →

Some links on this page are affiliate links. We earn a commission if you sign up – at no additional cost to you. Our editorial assessment is independent and never paid. How we review.

Features

✓JS Rendering
✓Structured Output
–Open Source
–Self-Hosted Option
Pricing:FreemiumSee pricing →

Editorial assessment

Valyu is an AI-native search and retrieval API built for LLMs and agents rather than human readers. It markets itself around "DeepSearch" and exposes four documented endpoints: Search (web plus proprietary sources), Contents (URL extraction), Answer (grounded question answering), and DeepResearch (an async agent that returns a cited report). Results come back as structured, markdown-formatted content shaped for model context windows instead of ranked links. The differentiator versus peers like Exa and Tavily is breadth of specialized sources: alongside web search it queries arXiv, PubMed, full-text SEC filings, clinical trials, patents, and financial and market data. The Contents endpoint can do full Chrome rendering for JavaScript-heavy pages, though that is one extraction option rather than the core product. The honest caveat is maturity and scale. Valyu is early-stage: a small team with UK roots (the legal entity is VALYU.NETWORK LTD, founded out of UCL) and a San Francisco footprint, having pivoted from an earlier data-licensing and web3 identity to the current search API. The GitHub org (github.com/valyuAI) is genuinely active with frequent pushes, and a16z named Valyu alongside Tavily in its "Search Wars Episode 2" piece, but there are no public customer case studies and no reliably confirmed funding figure (aggregator numbers conflict and could not be verified against a primary source, so we list none). The benchmark wins Valyu publishes on FreshQA, SimpleQA, and finance and medical retrieval are its own first-party claims and have not been independently reproduced. Worth evaluating if you are building agents that need depth in finance, academic, or regulatory sources and want LLM-ready output from a single API. For broad, proven general-web recall at production scale, the more established peers in this category still have the longer track record. Note it is hosted only with API-key auth (no self-hosting), and only the client SDKs are open source.

How Valyu compares

Exa

Exa retrieves through neural embeddings over its own web index, where Valyu adds proprietary and specialized sources like SEC filings, PubMed, and patents on top of web search.

Tavily

Tavily has far broader LLM-framework adoption and general-web coverage today, while Valyu pitches deeper finance, academic, and regulatory sources for domain-heavy agents.

Seltz

Seltz runs its own Rust-built crawler and index and is currently US-news-first, whereas Valyu layers retrieval over the open web plus proprietary databases.

See full Valyu alternatives comparison →

Frequently asked questions

How much does Valyu cost?

Valyu is freemium. New accounts get $10 in free credits ($20 with a work email) with no credit card required. Beyond that, pricing is usage-based and metered by source type per 1,000 retrievals: open sources like arXiv and PubMed around $0.50, web search around $1.50, financial and market data around $8, and proprietary databases around $30 to $50. The Answer API adds roughly $12 per million tokens for AI processing, and DeepResearch tasks are fixed-price by tier (Fast $0.10, Standard $0.50, Heavy $2.50, Max $15). Named monthly plans and a custom Enterprise tier also exist. Prices shift over time, so confirm current rates on the pricing page.

Is Valyu open source?

No. The core search and retrieval engine is proprietary and hosted only, reached through api.valyu.ai with an API key. The valyuAI GitHub organization publishes open-source client SDKs and integration tooling (Python, JavaScript, a CLI, and an MCP server, several MIT-licensed), but you cannot self-host the retrieval engine on your own infrastructure.

How does Valyu compare to Exa?

Both are AI-native search APIs that return LLM-ready content rather than ranked links. Exa retrieves through neural embeddings and is well suited to semantic discovery and find-similar workloads, with a longer track record and broader proven general-web coverage. Valyu's pitch is breadth of specialized sources, querying arXiv, PubMed, SEC filings, clinical trials, patents, and financial data alongside the web, plus an async DeepResearch agent. Choose Exa for mature semantic discovery; consider Valyu when domain depth in finance, academic, or regulatory data matters.

What can the Valyu API do?

Valyu exposes four documented endpoints: Search (web plus proprietary and specialized sources), Contents (URL extraction, with optional full Chrome rendering for JavaScript-heavy pages), Answer (grounded question answering), and DeepResearch (an async agent that returns a cited report). It offers Python and JavaScript/TypeScript SDKs, a REST interface, and an MCP server, with integrations for LangChain, LlamaIndex, Haystack, and others.

Where is Valyu based and is it well funded?

Valyu was founded out of University College London and operates as the UK entity VALYU.NETWORK LTD, with a San Francisco footprint as well. It is early-stage with a small team and went through a16z crypto's CSX Spring 2024 accelerator under its earlier data-licensing identity. No funding amount is reliably public: aggregator figures conflict and could not be verified against a primary source, so treat any specific funding number as unconfirmed.

Weekly briefing – tool launches, legal shifts, market data.

Visit

Valyu

Visit →