A Markdown file at yoursite.com/llms.txt that describes the site for large language models: a short summary and a list of the most important pages with one-line descriptions.

Does Google use llms.txt?

Google has not said it uses llms.txt for ranking or AI Overviews. Treat it as a helpful extra for AI tools, not as an SEO factor.

Do ChatGPT or Claude read llms.txt?

Some AI tools and agents read it when they visit a site, and developer tools use it widely. Support varies by product and changes over time, so do not rely on it alone.

Is llms.txt the same as robots.txt?

No. robots.txt tells crawlers what they may access. llms.txt tells AI tools what the site is about and where the key information lives.

How much does it cost to add?

At Kinto llms.txt is generated automatically with every website at no extra cost. For an existing site it is a small task.

llms.txt explained: should your website have one

llms.txt is a small text file that has been getting a lot of attention since AI assistants started answering questions people used to type into search. If you run a business website in Armenia, you have probably seen it mentioned and wondered whether you need one. Short answer: it does not hurt, it takes little time, and it should not be your first priority.

What llms.txt is

It is a plain Markdown file placed at the root of your site, for example yoursite.am/llms.txt. It was proposed in 2024 as a way to give language models a clean summary of a website, without menus, scripts and pop-ups getting in the way.

A typical file has:

The name of the business as a heading.
A one or two sentence summary: what you do, where, for whom.
Sections with links to key pages, each with a short description.
Optionally, a link to a longer version (often called llms-full.txt) with the full text of key pages.

Price and timeline infographic: robots.txt, sitemap.xml and llms.txt: who reads what — robots.txt, sitemap.xml and llms.txt: who reads what

A simple example

# Kinto
> Web studio in Yerevan: websites, landing pages, online stores, Telegram bots and AI assistants. Requests from sites arrive in Telegram.

## Services
- [Website development](https://kinto.am/en/website-development/): multi-page sites from $1,800
- [Telegram bots](https://kinto.am/en/telegram-bot/): bots for bookings and orders from $500

## Pricing
- [Pricing](https://kinto.am/en/pricing/): prices and timelines

That is the whole idea. No special syntax beyond normal Markdown.

How it differs from robots.txt and sitemap.xml

File	Who reads it	What it says
robots.txt	Search and AI crawlers	Which parts of the site they may access
sitemap.xml	Search engines	The full list of URLs and when they changed
llms.txt	AI tools and agents	What the site is about and which pages matter

They work together. llms.txt does not grant or block access; that is still the job of robots.txt.

Who actually uses it

This is where honesty matters. llms.txt is a community proposal, not an official web standard. Some AI tools, coding assistants and agents read it when they visit a site. Large AI search products have not publicly committed to using it as a ranking or citation signal. Google has said that normal SEO practices are what matter for its AI features.

So treat llms.txt as a low-cost extra, not as a way to "get into ChatGPT".

What actually gets you cited by AI

AI assistants pick sources that answer the question clearly. The things that matter more than llms.txt:

Clear facts on the page: prices, timelines, address, what is included.
Short summaries at the top of pages that can be quoted as they are.
FAQ blocks with direct answers.
Structured data: Organization, LocalBusiness, FAQPage.
Open access for AI crawlers in robots.txt, if you want to be cited.
Mentions elsewhere: directories, maps, social profiles with the same details.

We cover this in more depth in how to get cited by ChatGPT and FAQ blocks for SEO.

Common mistakes with llms.txt

Copying the whole site into it. The short file should stay short; full text belongs in a separate llms-full.txt if you need it.
Forgetting to update it. Old prices or removed pages in llms.txt confuse AI tools more than having no file at all.
Blocking AI crawlers in robots.txt at the same time. If crawlers cannot access the site, the file does little.
Writing it for search engines. Keyword stuffing does not help. Write it as a clear summary for a reader.

Should a small business add one

Our view:

New website: yes, include it. It costs nothing extra when generated together with the site.
Existing site with good content: worth adding if it takes an hour.
Site with thin content: fix the content first. A neat llms.txt pointing to empty pages does not help anyone.

How Kinto handles it

Every site we build gets llms.txt and llms-full.txt in each language version, generated from the same content as the pages, so they never go out of date. robots.txt is open for the main AI crawlers unless you ask otherwise. All of this is part of the standard build.

What	Price at Kinto
Landing page with llms.txt, schema, FAQ	from $700, about 6 days
Website with sections, same setup	from $1,800, about 12 days
Additional languages	from $600
Analytics setup	from $500

Next step

If you want your site to be clear for both people and AI tools, write to @kinto_am on Telegram or leave a request on the website development page. We reply within 15 minutes, 10:00 to 20:00 Yerevan time.

Updated: 2026-10-15

llms.txt explained