Company Peers API: The most similar public companies to any ticker or CIK — SEC XBRL
The most similar public companies to any ticker or CIK — same-industry candidates ranked by log-scale asset/revenue distance and margin from the full SEC XBRL corpus, each peer row carrying the numbers behind the ranking. One call replaces corpus loading and similarity modeling.
$0.05 per call — pay with prepaid card credits (Authorization: Bearer ck_live_…, packs from $1) or with USDC over x402: call it, get 402 with the price, retry signed. Failed calls are never charged.
How do you call it?
GET /v1/peers/similar — product id
peers_similar. Over MCP, call answerpool_get with
product_id=peers_similar.
curl "https://answerpool.io/v1/peers/similar?ticker=AAPL"
# with a prepaid credit key
curl -H "Authorization: Bearer ck_live_..." "https://answerpool.io/v1/peers/similar?ticker=AAPL"Live call: https://answerpool.io/v1/peers/similar?ticker=AAPL · JSON sample: /v1/samples/peers_similar
What does the answer look like?
A representative response, the same static sample served at /v1/samples/peers_similar.
as_of | 2026-09-02T21:00:00Z |
|---|---|
target.cik | 0000320193 |
target.ticker | AAPL |
target.name | Apple Inc. |
target.sic | 3571 |
target.sic_description | Electronic Computers |
target.assets_usd | 365000000000.0 |
target.revenue_usd | 400000000000.0 |
target.margin | 0.25 |
frame_year | 2025 |
candidates_in_industry | 42 |
count | 1 |
refresh_after | 2026-09-17T11:15:00.000Z |
peers
| cik | ticker | name | assets_usd | revenue_usd | net_income_usd | margin | distance | similarity |
|---|---|---|---|---|---|---|---|---|
| 0001045810 | NVDA | NVIDIA CORP | 111000000000.0 | 130000000000.0 | 72000000000.0 | 0.55 | 1.3072 | 0.4334 |
The same sample as raw JSON
{
"as_of": "2026-09-02T21:00:00Z",
"target": {
"cik": "0000320193",
"ticker": "AAPL",
"name": "Apple Inc.",
"sic": "3571",
"sic_description": "Electronic Computers",
"assets_usd": 365000000000.0,
"revenue_usd": 400000000000.0,
"margin": 0.25
},
"frame_year": 2025,
"candidates_in_industry": 42,
"count": 1,
"peers": [
{
"cik": "0001045810",
"ticker": "NVDA",
"name": "NVIDIA CORP",
"assets_usd": 111000000000.0,
"revenue_usd": 130000000000.0,
"net_income_usd": 72000000000.0,
"margin": 0.55,
"distance": 1.3072,
"similarity": 0.4334
}
],
"refresh_after": "2026-09-17T11:15:00.000Z"
}How fresh is it, and where does the data come from?
The fastest source behind this answer can change every 15 minutes, so every response carries a refresh_after timestamp — right now it would be 2026-09-17T11:15:00.000Z. Schedule the next call on that value rather than on a guess.
- SEC EDGAR (US federal public domain) — upstream:
https://efts.sec.gov
Method version 0.1.0 ·
serving cache 1 day ·
every response carries a result_id you can resolve at
/v1/provenance.
When should you use it?
You need a comparable set — valuation context, benchmarking, screening.
What you skip building
- XBRL corpus loading
- frames API joins
- similarity model construction
- SIC lookups
When should you not use it?
Cross-industry similarity or product-market competition — candidates come from the SEC industry (SIC) code.
Where else can you find this?
- Catalog entry (JSON, free)
- OpenAPI schema — input and output types, prices, the 402 flow
- llms.txt — every product in one plain-text document