OpenRouter

llms.txt exists

llms.txt found at 2 locations; using https://openrouter.ai/docs/llms.txt as canonical

llms.txt follows the standard structure

llms.txt follows the proposed structure (H1, blockquote, heading-delimited link sections)

llms.txt fits in an agent's context

llms.txt is 35,697 characters (under 50,000 threshold)

llms.txt links work

All 15 same-origin sampled links resolve (204 total links)

llms.txt links point to Markdown

15/15 same-origin sampled links point to markdown content (100%)

Pages point agents to llms.txt

llms.txt directive found in HTML of all 15 sampled pages, near the top of content

Markdown pages point agents to llms.txt

llms.txt directive found in markdown of all 15 sampled pages, near the top of content

Pages are available as Markdown

15/15 sampled pages support .md URLs (100%)

Server returns Markdown when asked

15/15 sampled pages support content negotiation (100%)

Content is in the HTML without JavaScript

All 15 sampled pages contain server-rendered content

Markdown pages fit in context

All 15 pages under 50K chars (median 11K, max 24K)

HTML pages fit in context

All 15 sampled pages under 50K chars (median 512K HTML → 19K markdown (97% boilerplate))

Content starts near the top

Content starts within first 10% on all 15 sampled pages (median 1%)

Tabs don't bloat the page

No tabbed content detected across 15 sampled pages

Headings inside tabs name their variant

No tabbed content found; header quality check not applicable

Code blocks are well-formed

All 67 code fences properly closed across 17 pages

Missing pages return a real 404

All 15 sampled pages return proper error codes for bad URLs

Redirects stay on the same host

No redirects detected across 15 sampled pages

Markdown matches the HTML page

3 of 15 pages have minor content differences between markdown and HTML

llms.txt covers the whole site

llms.txt covers 100% of 525 sitemap doc pages; 3 llms.txt links not in sitemap (may indicate stale links or incomplete sitemap)

Cache headers allow timely updates

All 17 endpoints have appropriate cache headers

Gated docs offer another way in

All docs pages are publicly accessible; no alternative access paths needed

Docs are readable without logging in

All 15 sampled pages are publicly accessible

Crawlers and AI assistants may read the docs

robots.txt lets Googlebot, Bingbot, OAI-SearchBot, PerplexityBot, Claude-SearchBot and Claude-User read the docs.

Sitemap lists the docs pages

The sitemap at https://openrouter.ai/sitemap.xml lists 242 of the 266 docs pages found through llms.txt and page links.

Pages say when they were last changed

11 of 15 sampled pages state when they were last changed, and 4 more have a date only in the sitemap.

Links and section anchors work

All 38 links and 15 section anchors checked on the sampled pages work. 2 more could not be verified (timeouts or blocked requests) and are not counted.

Sitemap entries still exist

All 10 sitemap entries sampled still exist.

Endpoints in the docs exist in the API spec

1 of 2 endpoints mentioned in the docs are not in https://openrouter.ai/openapi.json.

Deprecated operations are marked as such

The sampled pages do not use any of the 3 operations https://openrouter.ai/openapi.json marks deprecated.