Forecast Bnb

Last 30 days

Uptime

100%

Response time

185 ms typical, 185 ms slowest 5%

Last check

1 h ago

Next check

any minute now

How to call it

# See the payment challenge (nothing is charged)
curl -i -X GET "https://kronossignals.com/api/v1/forecast/bnb?horizon=1h"

import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { ExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client().register(
  "eip155:8453",
  new ExactEvmScheme(privateKeyToAccount(process.env.AGENT_KEY)),
);
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? Preflight it first for $0.005:
// GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fkronossignals.com%2Fapi%2Fv1%2Fforecast%2Fbnb
const res = await pay("https://kronossignals.com/api/v1/forecast/bnb?horizon=1h");
console.log(await res.json());

Example input

{
  "horizon": "1h"
}

Example output

{
  "accuracy_note": "Kronos-base model (switched from composite 2026-07-10), run hourly; when no recent run exists this route serves the composite heuristic (see model_type). Per-asset served accuracy is published live at /api/stats (beta_accuracy.per_asset); no fixed figure is quoted because one would go stale.",
  "asset": "BNB-USD",
  "beta": false,
  "cache_age_seconds": 180,
  "cached": true,
  "disclaimer": "Kronos-base ML forecast for BNB-USD, run hourly; the composite heuristic serves when no recent run exists. Informational only, not financial advice.",
  "forecast": {
    "confidence": 0.25,
    "expected_close": null,
    "horizon_bars": 20,
    "pred_volatility": null,
    "quantiles": null,
    "range_high": 612,
    "range_low": 588,
    "up_prob": 0.5
  },
  "generated_at": "2026-01-01T00:00:00.000Z",
  "horizon": "1h",
  "model": "kronos-base-60path-t1-v2",
  "model_type": "kronos_ml",
  "price": {
    "atr": 8,
    "close": 600
  },
  "source": "Kronos-base (cached, 60-path MC)"
}

Security scan

• No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks