content ranking api // decisioning infrastructure

Rank every article, video, and post
the moment it lands.

The ranking layer between your catalog and the surface a user reads or watches. Gortex orders every item, articles, video, and UGC alike, and fills sponsored slots in one call, so your team ships product instead of retuning a ranking engine.

request access → view the simulation

# 01 / the problem

Content ranking is never finished, it drifts with taste.

What earns a view this month gets stale the next. Taste moves, fresh items outdate old ones by the hour, and every new format, short video today, something else tomorrow, needs its own tuning. The team that ships the ranking keeps re-shipping it, on the request path, forever.

01 taste drifts constantly

Engagement signals decay as audience taste shifts. A model that ranked well last quarter quietly stops ranking well, and someone has to notice and retrain it.

02 freshness on every view

Recency has to be scored on the request path. Every freshness signal you add is latency you pay on every content view, for every user.

03 new formats need new tuning

Each format you add, long video, shorts, UGC, arrives with its own engagement dynamics, then has to be reconciled into one ranked surface by hand.

04 sponsored slots bolted on later

Monetized placements get built as a second system, then reconciled with organic ranking release after release, with no record of why a slot went where.

# 02 / how it works

One endpoint ranks the content and places sponsored slots in the same response.

You send a recipient, a surface, and the candidate items you already retrieved, whatever the format. Gortex returns the engagement order and the sponsored placements together, inside one sub-200ms p99 budget, with a decision id you can audit later.

your retrieval

you gather the candidates: articles, video, clips, and user posts.

gortex decides

rank the items for engagement and resolve sponsored slots against that order, in one call.

your surface

render the ranked content with sponsored slots already placed and priced.

01 you keep retrieval

Gortex ranks the items you bring, in any mix of formats. No data migration, no re-platforming.

02 ranking and monetization in one call

Engagement order and sponsored slots resolve against each other, so a paid item only takes a slot when the placement fits the ranked content around it.

03 every decision is traceable

Each response carries a decision id and a trace id. The reason an item ranked where it did is recorded, not reconstructed.

04 seven typed sdks

Generated from one OpenAPI 3.1 spec, so contract drift across languages is mechanically impossible.

# 03 / the call

One request. Ranked content and its sponsored slots.

POST /v1/decide
200 OK · 74ms
 // Rank a content feed and fill its sponsored slots.
$ curl api.gortex.ai/v1/decide \
  -H "Authorization: Bearer $GORTEX_KEY" \
  -d '{
    "recipient": { "id": "u_8120" },
    "context":   { "surface": "content_feed" },
    "items":     [ /* 200 candidate items: articles, video, ugc */ ]
  }'

{
  "ranked":      [ /* ordered item IDs */ ],
  "sponsored":   [{ "slot": 3, "price": 0.42 }],
  "decision_id": "d_01HXZ3M",
  "trace_id":    "t_01HXZ3N"
} 

# 04 / questions

Content ranking, answered plainly.

What is a content ranking API?

An endpoint that takes your candidate content items, articles, video, and UGC, and returns them in the order a given user should see them. Gortex places sponsored slots in the same response, so engagement ranking and monetization resolve together.

Does content ranking work across articles, video, and UGC in one call?

Yes. You pass mixed-format candidates and Gortex ranks them for the same user against one objective, then fills sponsored slots against that order. Formats do not each need their own ranking system.

How fast is a content ranking call?

Ranking and sponsored placement resolve inside one sub-200ms p99 budget, on the request path, so you can call it on every content view.

# 05 / start

See a content ranking decision, live.

The private beta is by invitation. Tell us the content you rank and the formats you carry, and we will get you a key.

request access → view the simulation read the anatomy read the guide

Rank every article, video, and post the moment it lands.