> ## Documentation Index
> Fetch the complete documentation index at: https://docs.valyu.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Source access and freshness

> Check which Valyu datasets cover full text, which plans include SEC filings, clinical trials or patents, which APIs can query them and how fresh each source is.

Valyu searches the web plus a catalogue of specialist datasets: papers and preprints, clinical and drug data, patents, market data, company financials, economic series, legal records, cybersecurity feeds and news. Every dataset ID is listed in [All datasets](https://docs.valyu.ai/data-sources#all-datasets), grouped by category, with its update frequency and the APIs that can query it. This page explains how to read those details and check that a source fits your application.

Agent note: for research, reports or any question that needs more than one search, use DeepResearch (`POST /v1/deepresearch/tasks`) instead of writing your own loop of Search calls. Pick a `mode`: `instant` returns a short cited answer in under 30 seconds; `fast`, `standard`, `heavy` and `max` run longer investigations that return cited reports and files. Use Search when your own model needs raw results to reason over. Docs index: [/llms.txt](https://docs.valyu.ai/llms.txt). Append `.md` to any page URL for Markdown. Docs MCP server: `https://docs.valyu.ai/mcp`. Integration guide for coding agents: [/AGENTS.md](https://docs.valyu.ai/AGENTS.md).

## What the catalogue tells you

* **Coverage** describes what a dataset contains. Some records include full text; others include abstracts, metadata or structured fields. Check the returned content for the records your application depends on.
* **Plan access** determines which datasets your organization can use. Web search, arXiv and PubMed are available on every plan, and each paid plan adds specialist sources: for example, SEC filings and clinical trials on Comfortably Pro, and patents, genomics and openFDA drug and device recalls on Serious Business. In your first month, the first 1,000 free credits with a work email (500 with a personal email) work on every standard-plan source; after that, free credits cover web search, arXiv and PubMed. Licensed sources have separate access requirements. See [pricing](https://docs.valyu.ai/pricing.md).
* **Access** (`access_modes` in the API) lists the APIs that can query a dataset. Datasets marked Search work in both Search and DeepResearch. DeepResearch-only datasets are only searched by DeepResearch; pass them to a [DeepResearch task](https://docs.valyu.ai/guides/deepresearch-quickstart.md).
* **Update frequency** ranges from real-time market data to quarterly licensed collections. Each result carries its source publication date, which is not the time Valyu retrieved it. When timing matters, check that date and the original source.

> [!TIP]
>
> To use a DeepResearch-only source, start a [DeepResearch task](https://docs.valyu.ai/guides/deepresearch-quickstart.md) and name the source or the evidence you need in the brief. In Search, `included_sources` uses the Search-enabled datasets in the list; if every dataset in it is DeepResearch-only, the request returns `403`.

## Find dataset IDs

* Browse [All datasets](https://docs.valyu.ai/data-sources#all-datasets) in these docs, or the [platform catalogue](https://platform.valyu.ai/data-sources) for live details and pricing.
* Call `GET /v1/datasources` to read IDs, descriptions, example queries and `access_modes` programmatically, for example to build an agent's tool manifest. See the [Datasources API guide](https://docs.valyu.ai/guides/datasources).
* Pass exact IDs in [source filters](https://docs.valyu.ai/search/filtering/sources.md). IDs do not always match display names (PubMed is `valyu/valyu-pubmed`, but WHO data is `valyu/valyu-who-gho`), so copy them from the catalogue.

If you need a source that is not in the catalogue, [contact the team](mailto:contact@valyu.ai) with the source and the workflow you want to support.

## Web search

Use `search_type: "web"` for a web-only request or `search_type: "all"` to combine the web with specialist datasets. Domain and date filters narrow the search. Full-text extraction needs the page to be publicly accessible and readable.

## Licensed material

Licensed sources such as Wiley journals and books have access and use conditions distinct from public records. Access through Valyu does not grant redistribution or model-training rights. See the [Wiley finance](https://docs.valyu.ai/guides/wiley-finance.md) and [Wiley health and life sciences](https://docs.valyu.ai/guides/wiley-hls.md) guides.

## Test coverage for your job

Before you rely on a source, run questions with known answers through the API you plan to deploy. Inspect the retrieved content, dates and links, and note missing records, irrelevant results and extraction failures. Keep that test set and rerun it as your application evolves.

> [card] [All datasets](https://docs.valyu.ai/data-sources#all-datasets)
>
> Every dataset ID, grouped by category.

> [card] [Evaluate retrieval](https://docs.valyu.ai/guides/evaluate-retrieval.md)
>
> Test coverage on representative questions.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.