# What is llms-full.txt?

> llms-full.txt is the full-content companion to llms.txt. Learn when to publish one, how it differs, and how big sites like Anthropic and Vercel use both.

If llms.txt is the table of contents, llms-full.txt is the whole book. The 2026 best practice is to publish both.

## The two-file pattern

llms.txt gives a model a compact, linked overview — it has to fetch each link to read more. llms-full.txt embeds the complete content of those pages directly in a single file, so a model can ingest everything in one request with no extra fetches.

## When to publish llms-full.txt

  - You have documentation that benefits from being read in full (APIs, SDKs, guides).

  - You want agents to work offline-ish, without crawling dozens of pages.

  - You already maintain Markdown sources you can concatenate.

## Don't forget per-page .md versions

The spec also suggests offering a clean Markdown version of each page at the same URL, either with `.md` appended (`page.html.md`) or with the extension replaced (`page.md`) — spec v2 allows both. For directory URLs, append `index.html.md` / `index.md`. That gives models a parse-friendly copy of any single page.

## Who does this

The llms.txt + llms-full.txt pairing is used by Anthropic, Vercel, and other documentation-heavy projects: the index for orientation, the full dump for deep ingestion.

## Check yours

Our [validator](/) reports whether a sibling llms-full.txt exists when you check a domain. New to the format? Start with [how to create an llms.txt file](/guide/how-to-create-llms-txt).