Agent-readable docs index: /llms.txt. Full docs in one file: /llms-full.txt. Download /docs.zip to grep all markdown files locally.
/api/v1/markets/{id}/similarGET
Find semantically similar markets using AI embeddings
Authorization
bearerAuth *Bearer <token>
Session token from the app, or an API key (the ak_ prefix), sent as a Bearer token or an ?api_key= query parameter.. Token in: header
Query Parameters
min_similarity?number
Minimum cosine similarity a result must reach.
Default: 0.38Min: 0Max: 1
platform?"kalshi" | "polymarket" | "gemini"
Restrict ranked neighbors to this venue (kalshi, polymarket, polymarket-us, or gemini).
page?integer
Page number
Default: 1Min: 1
per_page?integer
Items per page
Default: 100Min: 1Max: 500
Response
200 · Paginated similar markets
data?object[]
Show item properties
market_id?string
similarity?number
description?stringnull
platform?stringnull
latest_price?numbernull
question?stringnull
The market's question.
meta?object
Show properties
total?integernull
Total number of records matching the request across every page, not just the current one. null on an uncounted list; page using has_next. A relevance-ranked search is uncounted, and a searched events list stays uncounted even with sort. A searched markets list with sort returns a total over the ranked matches (at most 10,000).
page?integer
The 1-based page number this response covers.
per_page?integer
Maximum number of items on a page. The last page may hold fewer.
total_pages?integernull
Total number of pages available at the current per_page. null whenever total is null; page using has_next.
has_next?boolean
True when a page exists after this one.
has_prev?boolean
True when this is not the first page.
total_capped?boolean
True when total and total_pages reflect the server's counting ceiling rather than the exact matched count: the real set is at least total large. Render such totals as a lower bound (for example "10,000+"). Omitted when the count is exact. A sorted markets search that fills the 10,000-candidate ceiling sets this flag.
403 · The organization has no paid plan, so the realtime read scopes are refused. Distinct from a 429, which means a plan's budget ran out: nothing here resets on a timer, and the request succeeds only once the organization holds a plan.
error *string
Human-readable reason the request was refused.
status *integer
HTTP status code, repeated in the body.
upgrade_url?string (uri)
Page listing the plans and their request allowances, for buying access. Absent when no plan is available for purchase.
429 · The organization's minute or UTC-day request budget is exhausted, or the organization has reached its cap on requests running at the same time (`limit: "concurrency"`). Wait `Retry-After` seconds before retrying; for a concurrency 429, reduce parallelism.
error *"rate_limited"
Always rate_limited. Branch on this to detect a throttled request.
limit *"rpm" | "daily" | "concurrency"
Which limit was hit: rpm for the per-minute cap, daily for the daily one, or concurrency for the cap on requests running at the same time.
message *string
Human-readable explanation naming the limit that was exceeded.
upgrade_url?string (uri)
Page listing the plans and their request allowances, for buying a larger budget. Absent when no plan is available for purchase.
Request example
curl -X GET "https://api.adjacent.markets/api/v1/markets/<id>/similar" \
  -H "Authorization: Bearer <token>"
Response example
{
  "data": [
    {
      "market_id": "kalshi:KXNBA-26-NYK",
      "similarity": 0.91,
      "platform": "kalshi",
      "question": "Will the New York win the 2026 Pro Basketball Finals?"
    },
    {
      "market_id": "kalshi:KXNBA-26-BOS",
      "similarity": 0.88,
      "platform": "kalshi",
      "question": "Will the Boston win the 2026 Pro Basketball Finals?"
    }
  ],
  "meta": {
    "total": 2,
    "page": 1,
    "per_page": 20,
    "total_pages": 1,
    "has_next": false,
    "has_prev": false
  }
}
Adjacent API
Powered byHolocron