Skip to main content
Valyu spans specialised and proprietary data sources across academic, financial, scientific, governmental, and specialised domains - plus web search. We index both open-access repositories and premium proprietary sources, continuously updated. Want a source added? Email contact@valyu.ai.

How access works

  • Web search and open academic sources (arXiv, PubMed) are on every plan, including pay-as-you-go. Specialised and proprietary sources unlock as you move up plans, which also lowers your cost per credit - see pricing.
  • During your free trial, every source is available. Need a source above your plan? Request access to specific datasets without upgrading.
  • Access mode. Every dataset is either Search + Answer + DeepResearch (callable via /v1/search) or DeepResearch only (served only inside a research task). The tables below carry an Access column where they mix.
DeepResearch-only sources can’t be called via /v1/search. Passing a DeepResearch only id to included_sources on Search or Answer returns no results. To use them, run a DeepResearch task (POST /v1/deepresearch/tasks) with the topic in the query. Whole families are DeepResearch-only: transportation, environment, automotive, compliance & sanctions, and pulse signals, plus specific datasets called out below.

Available datasets

Use included_sources to target specific datasets, or let Valyu auto-select the most relevant sources for your query.

Research & Academic Search + Answer + DeepResearch

Healthcare & Life Sciences Mixed access

Chemistry & Drug Discovery Search + Answer + DeepResearch

Genomics Search + Answer + DeepResearch

NCBI genomic databases covering sequences, variants, and biological metadata.
Genomics covers 19 NCBI databases in total, including GEO, taxonomy, structure, SRA, BioSample, assembly, BioProject, dbGaP, dbVar, MedGen, GTR, and more. Use the genomics preset in included_sources to search across them.

Financial Markets Search + Answer + DeepResearch

Company Fundamentals Search + Answer + DeepResearch

SEC filings cover the full filing universe including 10-K, 10-Q, 8-K, S-4, DEF 14A, Form 10, SC TO-T, and SC 14D9 - all Search + Answer + DeepResearch. The following investment-research sources are DeepResearch only (not callable via /v1/search): short-seller reports (valyu/valyu-short-seller-reports), buyside letters and pitches (valyu/valyu-buyside-letters-pitches), semiconductor-industry news (valyu/valyu-semiconductor-industry-news), congressional research / CRS (valyu/valyu-congressional-research), legal-regulatory news (valyu/valyu-legal-regulatory-news), and FDIC BankFind (valyu/valyu-fdic-bankfind). Use them via a DeepResearch task.

Economic Data Search + Answer + DeepResearch

Prediction Markets Search + Answer + DeepResearch

Transportation DeepResearch only

These sources are available through DeepResearch, not the Search/Answer API. Run a DeepResearch task with your transportation question in the query.

Patents & IP Search + Answer + DeepResearch

US Congressional Research Service / CRS (valyu/valyu-congressional-research) and legal & regulatory news (valyu/valyu-legal-regulatory-news) are DeepResearch only - see the Company Fundamentals note above.

Physics Search + Answer + DeepResearch

Cybersecurity Search + Answer + DeepResearch

Compliance & Sanctions DeepResearch only

These sources are available through DeepResearch, not the Search/Answer API. Run a DeepResearch task and name the lists you need in the query (e.g. “screen this entity against OFAC SDN, UN, and UK HMT sanctions”).

Automotive DeepResearch only

NHTSA vehicle safety and identification data.
These sources are available through DeepResearch, not the Search/Answer API. Run a DeepResearch task with your vehicle, recall, or complaint question in the query.

Environment DeepResearch only

These sources are available through DeepResearch, not the Search/Answer API. Run a DeepResearch task with your weather, air-quality, disaster, or geocoding question in the query.

Pulse signals DeepResearch only

High-frequency leading indicators.
These sources are available through DeepResearch, not the Search/Answer API. Run a DeepResearch task and name the signal in the query (e.g. “PyPI and npm download trends for vector-database clients over the last 12 months”).

Coming soon

Flight tracking and aviation data, additional economic data (trade, housing, regional indicators), pharmaceutical pipelines, and private company data (startup profiles, valuations, funding rounds). Contact contact@valyu.ai for specific domain requirements or custom data partnerships.