Signals Backtest
by CRYPTYX in Onchain & crypto
Backtest any signal over up to 365 days. Returns trigger stats, per-day rows, and a 4-horizon performance block (sample size, mean/median return, hit rate, bootstrap CI, statistical significance, reliability grade). Walk-forward OOS read inlined. Runs across 200+ digital assets — BTC, ETH, SOL, top-cap + long-tail coverage.
POST https://cryptyx.ai/api/signals/backtest
Last 30 days
Status and outage history · Atom feed
- Uptime
- 100%
- Response time
- 268 ms typical, 811 ms slowest 5%
- Last check
- 1 h ago
- Next check
- any minute now
How to call it
POST https://cryptyx.ai/api/signals/backtest
Each call costs $0.05 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://cryptyx.ai/api/signals/backtest
content-type: application/json
{
"dryrun": false,
"from": "",
"signal_id": "",
"to": ""
}Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
dryrun | boolean | No | If true, uses signal_dryrun_count() and skips writes to signal_log. Default false. dryrun=true nulls totalTriggerEvents/avgConfidence and omits performance block. |
from | string | Yes | Start date YYYY-MM-DD |
signal_id | string | Yes | Signal registry ID, e.g. TR_MOMO_CONT_14D (uppercased server-side) |
to | string | Yes | End date YYYY-MM-DD. Range must be <=365d and from<=to |
Example response
The provider's example. We can't check it without paying.
Example response, 140 lines
{
"avgConfidence": 0.7314,
"days": [
{
"day": "2025-06-01",
"rows": 0
},
{
"day": "2025-06-02",
"rows": 3
},
{
"day": "2025-06-03",
"rows": 5
}
],
"dryrun": false,
"durationMs": 48213,
"from": "2025-06-01",
"ok": true,
"performance": {
"caveats": [
"No in-sample/out-of-sample split applied. Results above are in-sample only. See `walk_forward` block for the nightly out-of-sample read."
],
"horizons": [
{
"bootstrap_ci_95": [
0.001204,
0.008331
],
"hit_rate": 0.5615,
"horizon": "1d",
"is_reliable": true,
"mean_return": 0.004812,
"median_return": 0.003104,
"sample_size": 187,
"statistical_significance": "significant"
},
{
"bootstrap_ci_95": [
0.008221,
0.034102
],
"hit_rate": 0.5882,
"horizon": "7d",
"is_reliable": true,
"mean_return": 0.02103,
"median_return": 0.01588,
"sample_size": 187,
"statistical_significance": "significant"
},
{
"bootstrap_ci_95": [
0.012003,
0.056012
],
"hit_rate": 0.5989,
"horizon": "14d",
"is_reliable": true,
"mean_return": 0.03414,
"median_return": 0.02211,
"sample_size": 187,
"statistical_significance": "significant"
},
{
"bootstrap_ci_95": [
-0.004021,
0.12614
],
"hit_rate": 0.604,
"horizon": "30d",
"is_reliable": false,
"mean_return": 0.0612,
"median_return": 0.0411,
"sample_size": 187,
"statistical_significance": "not_significant"
}
],
"is_sample_sufficient": true,
"minimum_sample_threshold": 30,
"reliability_grade": "green",
"sample_size": 187
},
"signal_id": "TR_MOMO_CONT_14D",
"to": "2025-12-01",
"totalDays": 184,
"totalTriggerEvents": 187,
"triggerRate": 0.223,
"triggeredDays": 41,
"walk_forward": {
"14d": {
"asof_day": "2026-06-20",
"ic_delta": -0.0453,
"is_hit_rate": 0.572,
"is_ic": 0.0941,
"is_n_obs": 18900,
"is_n_triggers": 612,
"oos_hit_rate": 0.531,
"oos_ic": 0.0488,
"oos_n_obs": 8100,
"oos_n_triggers": 184,
"overfit_ratio": 0.519,
"reliability_grade": "green",
"split_pct": 0.7,
"window_days": 180
},
"30d": {
"asof_day": "2026-06-20",
"ic_delta": -0.0411,
"is_hit_rate": 0.553,
"is_ic": 0.0712,
"is_n_obs": 18900,
"is_n_triggers": 612,
"oos_hit_rate": 0.518,
"oos_ic": 0.0301,
"oos_n_obs": 8100,
"oos_n_triggers": 184,
"overfit_ratio": 0.423,
"reliability_grade": "yellow",
"split_pct": 0.7,
"window_days": 180
},
"7d": {
"asof_day": "2026-06-20",
"ic_delta": -0.0264,
"is_hit_rate": 0.561,
"is_ic": 0.0876,
"is_n_obs": 18900,
"is_n_triggers": 612,
"oos_hit_rate": 0.542,
"oos_ic": 0.0612,
"oos_n_obs": 8100,
"oos_n_triggers": 184,
"overfit_ratio": 0.699,
"reliability_grade": "green",
"split_pct": 0.7,
"window_days": 180
}
}
}Call it from code
The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.05.
curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i -X POST 'https://cryptyx.ai/api/signals/backtest' \
-H 'content-type: application/json' \
--data-raw '{"dryrun":false,"from":"","signal_id":"","to":""}'
# 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://cryptyx.ai/api/signals/backtest' \
-H 'content-type: application/json' \
--data-raw '{"dryrun":false,"from":"","signal_id":"","to":""}' \
| 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 $0.05 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.05" });
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 $0.05 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fcryptyx.ai%2Fapi%2Fsignals%2Fbacktest&method=POST
const res = await pay("https://cryptyx.ai/api/signals/backtest", {
method: "POST",
headers: { "content-type": "application/json" },
body: JSON.stringify({
"dryrun": false,
"from": "",
"signal_id": "",
"to": ""
}),
});
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 $0.05 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.05"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))
with x402_requests(client) as session:
res = session.post(
"https://cryptyx.ai/api/signals/backtest",
json={
"dryrun": False,
"from": "",
"signal_id": "",
"to": "",
},
)
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 |
|---|---|---|---|---|
| 1 h ago | Passed | 402 | 234 ms | $0.05 |
| 6 h ago | Passed | 402 | 209 ms | $0.05 |
| 10 h ago | Passed | 402 | 732 ms | $0.05 |
| 14 h ago | Passed | 402 | 1.2 s | $0.05 |
| 18 h ago | Passed | 402 | 200 ms | $0.05 |
| 22 h ago | Passed | 402 | 389 ms | $0.05 |
| 25 h ago | Passed | 402 | 259 ms | $0.05 |
| 29 h ago | Passed | 402 | 486 ms | $0.05 |
| 33 h ago | Passed | 402 | 268 ms | $0.05 |
| 37 h ago | Passed | 402 | 223 ms | $0.05 |
| 40 h ago | Passed | 402 | 225 ms | $0.05 |
| 44 h ago | Passed | 402 | 202 ms | $0.05 |
| 47 h ago | Passed | 402 | 220 ms | $0.05 |
| 2 days ago | Passed | 402 | 637 ms | $0.05 |
| 2 days ago | Passed | 402 | 353 ms | $0.05 |