Semantic Rank
by NetIntel in Search & web
Semantic similarity ranking — send a query plus up to 100 candidate texts, get the candidates back ranked by semantic similarity with scores. No vectors, no cosine math, no embedding model to manage: one call, one price, ranked results. Flat $0.02 per call in USDC via x402, no API key. For RAG retrieval, FAQ matching, and search result ordering.
https://netintel.dev/semantic/rank- Price
- $0.02
- per call in USDC
- Uptime
- 100%
- last 30 days
- Response time
- 265 ms
- 462 ms slowest 5%
- Last check
- Passed
- 4 h ago, next any minute now
Reliability
Status and outage history · Atom feed · Watch with other listings
How to call it
POST https://netintel.dev/semantic/rank
Each call costs $0.02 in USDC on Base, paid with the request over x402.
Run a free test callOne unpaid request, the way an agent sends it. You see the payment challenge it gets back. Nothing is charged.
Example request
From the listing.
POST https://netintel.dev/semantic/rank
content-type: application/json
{
"candidates": [
"Use the Forgot Password link to recover your account.",
"Refunds are accepted within 30 days.",
"Our offices open at 9:00 AM."
],
"query": "How do I reset my password?",
"top_k": 2
}Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
candidates | array of string | Yes | 1-100 candidate strings to rank (64000 chars total on the default model). |
min_score | number | No | Drop results scoring below this (-1 to 1). Optional. |
model | string | No | text-embedding-3-small (default) or text-embedding-3-large |
query | string | Yes | The text to rank candidates against. |
top_k | number | No | Return only the best N results. Optional. |
Example response
The provider's example. We can't check it without paying.
{
"dimensions": 1536,
"method": "embedding_similarity",
"model": "text-embedding-3-small",
"normalized": true,
"provider": "openai",
"results": [
{
"index": 0,
"score": 0.5361,
"text": "Use the Forgot Password link to recover your account."
},
{
"index": 1,
"score": 0.1399,
"text": "Refunds are accepted within 30 days."
}
],
"usage": {
"prompt_tokens": 36
}
}Call it from code
The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.02.
curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i -X POST 'https://netintel.dev/semantic/rank' \
-H 'content-type: application/json' \
--data-raw '{"candidates":["Use the Forgot Password link to recover your account.","Refunds are accepted within 30 days.","Our offices open at 9:00 AM."],"query":"How do I reset my password?","top_k":2}'
# x402 v2 sends the challenge base64-encoded in the PAYMENT-REQUIRED header (v1 sends it in the body).
# To read the header:
curl -sS -g -o /dev/null -D - -X POST 'https://netintel.dev/semantic/rank' \
-H 'content-type: application/json' \
--data-raw '{"candidates":["Use the Forgot Password link to recover your account.","Refunds are accepted within 30 days.","Our offices open at 9:00 AM."],"query":"How do I reset my password?","top_k":2}' \
| grep -i '^payment-required:' | cut -d' ' -f2 | tr -d '\r' | base64 --decodeJavaScript: pay and call
// npm i @x402/fetch @x402/evm viem
import { wrapFetchWithPayment, x402Client } from "@x402/fetch";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";
// Pays at most $0.02 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.02" });
registerExactEvmScheme(client, { signer: privateKeyToAccount(process.env.EVM_PRIVATE_KEY) });
const pay = wrapFetchWithPayment(fetch, client);
// Not sure it's safe to pay? ToolVet checks it first for $0.005. Pay for that from a separate
// client: this one is capped at $0.02 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fnetintel.dev%2Fsemantic%2Frank&method=POST
const res = await pay("https://netintel.dev/semantic/rank", {
method: "POST",
headers: { "content-type": "application/json" },
body: JSON.stringify({
"candidates": [
"Use the Forgot Password link to recover your account.",
"Refunds are accepted within 30 days.",
"Our offices open at 9:00 AM."
],
"query": "How do I reset my password?",
"top_k": 2
}),
});
console.log(res.status, await res.text());Python: pay and call
# pip install "x402[requests,evm]"
import os
from eth_account import Account
from x402 import x402ClientSync
from x402.http.clients import x402_requests
from x402.mechanisms.evm import EthAccountSigner
from x402.mechanisms.evm.exact.register import register_exact_evm_client
# Pays at most $0.02 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.02"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))
with x402_requests(client) as session:
res = session.post(
"https://netintel.dev/semantic/rank",
json={
"candidates": [
"Use the Forgot Password link to recover your account.",
"Refunds are accepted within 30 days.",
"Our offices open at 9:00 AM.",
],
"query": "How do I reset my password?",
"top_k": 2,
},
)
print(res.status_code, res.text)Security scan
No findings
We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.
Recent checks
| When | Result | HTTP | Time | Price |
|---|---|---|---|---|
| 4 h ago | Passed | 402 | 462 ms | $0.02 |
| 8 h ago | Passed | 402 | 296 ms | $0.02 |
| 13 h ago | Passed | 402 | 516 ms | $0.02 |
| 17 h ago | Passed | 402 | 284 ms | $0.02 |
| 21 h ago | Passed | 402 | 334 ms | $0.02 |
Show 10 older checks
| 25 h ago | Passed | 402 | 326 ms | $0.02 |
| 30 h ago | Passed | 402 | 265 ms | $0.02 |
| 34 h ago | Passed | 402 | 202 ms | $0.02 |
| 38 h ago | Passed | 402 | 323 ms | $0.02 |
| 42 h ago | Passed | 402 | 281 ms | $0.02 |
| 47 h ago | Passed | 402 | 261 ms | $0.02 |
| 2 days ago | Passed | 402 | 352 ms | $0.02 |
| 2 days ago | Passed | 402 | 317 ms | $0.02 |
| 2 days ago | Passed | 402 | 187 ms | $0.02 |
| 3 days ago | Passed | 402 | 184 ms | $0.02 |