Skip to content

fix: stop ranking for "how many parameters does GPT have" - #196

Merged
brunobuddy merged 3 commits into
mainfrom
seo/model-params-disambiguation
Aug 4, 2026
Merged

fix: stop ranking for "how many parameters does GPT have"#196
brunobuddy merged 3 commits into
mainfrom
seo/model-params-disambiguation

Conversation

@brunobuddy

Copy link
Copy Markdown
Member

💭 Why

Google is matching the site against weight-count queries ("how many parameters is haiku 4.5", "gpt-3.5 parameters") instead of the API-settings audience it serves. The site was optimized for the wrong sense: titles, H1s and the model FAQ all matched the count phrasing exactly, while the disambiguating wording only appeared in body copy.

✨ What changed

  • Every title and H1 now says "API parameters" (model, provider, home, glossary).
  • Title fallbacks shed the site name and provider prefix first, never "API".
  • Model FAQ no longer asks "how many parameters does X accept". That sat in FAQPage JSON-LD as a claim to answer count queries.
  • Dataset JSON-LD gained keywords and an about pointing at a DefinedTerm for the API-parameter sense.
  • New page at /model-parameters-vs-api-parameters absorbs the count intent, with its own FAQPage.
  • llms.txt and the usage guide state the distinction up front, for AI answer engines.
  • README tagline updated to match.

👤 For users

Someone landing from a weight-count query gets a line under the H1 telling them it's a different number, with a link to a page that answers them honestly.

📝 Notes

The absorber page is the mechanism, not a courtesy explainer. Without one target for the count sense, Google keeps attaching it to all 242 model pages.
Track it in GSC: filter Queries by parameters, regex-exclude api|temperature|top_p|max_tokens|setting, and watch that share fall over 8-12 weeks.
Follow-up: the concept DefinedTerm could carry sameAs to Wikipedia/Wikidata entities for both senses. Left out until the URLs are verified.

Search results were pulling the site into weight-count queries
("how many parameters is haiku 4.5") instead of the API-settings
audience it serves. Titles, H1s and the model FAQ all matched the
count phrasing exactly.

Every page title and H1 now says "API parameters". The model FAQ no
longer asks "how many parameters does X accept", which sat in FAQPage
JSON-LD as a claim to answer count queries. Dataset JSON-LD gained
keywords and an about pointing at a DefinedTerm for the API-parameter
sense.

Adds /model-parameters-vs-api-parameters to absorb the count intent so
the 200+ model pages stop competing for it. llms.txt states the
distinction up front for AI answer engines.
@vercel

vercel Bot commented Aug 4, 2026

Copy link
Copy Markdown

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated (UTC)
modelparams.dev Ready Ready Preview Aug 4, 2026 6:14pm

Request Review

@github-actions github-actions Bot added site Website code or tooling meta Repo docs, CI, and config labels Aug 4, 2026
Every interior page already separates page and brand with a middot.
The homepage was the only one using an em dash.
@brunobuddy
brunobuddy merged commit 35e05a5 into main Aug 4, 2026
12 checks passed
@brunobuddy
brunobuddy deleted the seo/model-params-disambiguation branch August 4, 2026 18:16
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

meta Repo docs, CI, and config site Website code or tooling

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant