Agent Evaluate
by vaunt-dispatch-production.up.railway.app in Markets & finance
Ask Vaunt: evidence for or against a proposed trade (asset + LONG/SHORT) from a live real-money trading engine on Hyperliquid — comparable triggers on independent days, mean move and win rate at 4h/24h, favorable/adverse excursion, class base rate, current regime and posture, primary risk. Results only, never entry/stop/target.
https://vaunt-dispatch-production.up.railway.app/agent/x402/evaluate- Price
- $0.5
- per call in USDC
- Uptime
- 100%
- last 30 days
- Response time
- 210 ms
- 356 ms slowest 5%
- Last check
- Passed
- 9 min ago, next in 20 min
Reliability
Status and outage history · Atom feed · Watch with other listings
How to call it
POST https://vaunt-dispatch-production.up.railway.app/agent/x402/evaluate
Each call costs $0.5 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://vaunt-dispatch-production.up.railway.app/agent/x402/evaluate
content-type: application/json
{
"asset": "SOL",
"direction": "LONG",
"horizon_h": 4
}Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
asset | string | Yes | Ticker as listed on Hyperliquid, e.g. SOL, HYPE, BTC, or xyz:NVDA for tokenized equities |
direction | string | Yes | One of: LONG, SHORT. |
horizon_h | integer | No | Evaluation horizon in hours One of: 4, 24. Default: 4. |
Example response
The provider's example. We can't check it without paying.
Example response, 46 lines
{
"asset": "xyz:NVDA",
"basis": [
"110 triggers on 17 days: +0.84% mean, 64% win at 24h; regime BULL aligned",
"Vaunt closed 4 real-money trade(s) on it: 0.87% mean, 75% win"
],
"direction": "LONG",
"evidence": {
"class_base_rate": {
"independent_days": 21,
"mean_24h_pct": 0.8,
"mean_4h_pct": 0.28,
"n": 8723,
"win_4h_pct": 56
},
"comparables": {
"avg_mae_pct": -1.59,
"avg_mfe_pct": 2.6,
"independent_days": 17,
"mean_24h_pct": 0.84,
"mean_4h_pct": 0.23,
"n": 110,
"win_24h_pct": 64,
"win_4h_pct": 61
},
"vaunt_closed_trades_on_asset": {
"mean_return_pct": 0.87,
"n": 4,
"win_pct": 75
}
},
"horizon_h": 24,
"primary_risk": null,
"regime": {
"band": "BULL",
"strength": 0.79
},
"state": {
"day_volume_usd": 50964553,
"dist_200d_pct": 11.3,
"posture": "normal",
"recent_outlier": false
},
"support": "STRONG",
"what_is_not_here": "entry, invalidation and exit geometry — the priced tier"
}Call it from code
The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.5.
curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i -X POST 'https://vaunt-dispatch-production.up.railway.app/agent/x402/evaluate' \
-H 'content-type: application/json' \
--data-raw '{"asset":"SOL","direction":"LONG","horizon_h":4}'
# 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://vaunt-dispatch-production.up.railway.app/agent/x402/evaluate' \
-H 'content-type: application/json' \
--data-raw '{"asset":"SOL","direction":"LONG","horizon_h":4}' \
| 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 $0.5 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.5" });
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 $0.5 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fvaunt-dispatch-production.up.railway.app%2Fagent%2Fx402%2Fevaluate&method=POST
const res = await pay("https://vaunt-dispatch-production.up.railway.app/agent/x402/evaluate", {
method: "POST",
headers: { "content-type": "application/json" },
body: JSON.stringify({
"asset": "SOL",
"direction": "LONG",
"horizon_h": 4
}),
});
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 $0.5 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.5"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))
with x402_requests(client) as session:
res = session.post(
"https://vaunt-dispatch-production.up.railway.app/agent/x402/evaluate",
json={
"asset": "SOL",
"direction": "LONG",
"horizon_h": 4,
},
)
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 |
|---|---|---|---|---|
| 9 min ago | Passed | 402 | 198 ms | $0.5 |
| 4 h ago | Passed | 402 | 203 ms | $0.5 |
| 7 h ago | Passed | 402 | 200 ms | $0.5 |
| 10 h ago | Passed | 402 | 326 ms | $0.5 |
| 13 h ago | Passed | 402 | 201 ms | $0.5 |
Show 10 older checks
| 17 h ago | Passed | 402 | 206 ms | $0.5 |
| 20 h ago | Passed | 402 | 191 ms | $0.5 |
| 23 h ago | Passed | 402 | 205 ms | $0.5 |
| 27 h ago | Passed | 402 | 195 ms | $0.5 |
| 32 h ago | Passed | 402 | 192 ms | $0.5 |
| 37 h ago | Passed | 402 | 263 ms | $0.5 |
| 42 h ago | Passed | 402 | 190 ms | $0.5 |
| 47 h ago | Passed | 402 | 373 ms | $0.5 |
| 2 days ago | Passed | 402 | 257 ms | $0.5 |
| 2 days ago | Passed | 402 | 243 ms | $0.5 |