78trust / 100
Validate Json
by JSON Schema Validator in AI models & inference
x402 APIPassing, checked 8 min ago
Validate a JSON value against a JSON Schema and coerce common LLM-output mistakes (numbers as strings, stringified booleans, scalars where arrays are expected, missing defaults, extra properties). Returns the coerced value plus a structured error report. Built for cleaning up LLM tool-call arguments and structured outputs. POST a JSON body like: {"schema":{"type":"object","required":["name","age"],"properties":{"name":{"type":"string"},"age":{"type":"integer"}}},"data":{"name":"Ada","age":"36"}}
POST https://keyronne.com/api/validate-json
Last 30 days
All checks passedSome failedAll failedNot checked
- Uptime
- 100%
- Response time
- 156 ms typical, 258 ms slowest 5%
- Last check
- 8 min ago
- Next check
- in 25 min
How to call it
# See the payment challenge (nothing is charged)
curl -i -X POST "https://keyronne.com/api/validate-json" \
-H "content-type: application/json" \
-d '{"data":{"age":"36","name":"Ada"},"schema":{"properties":{"age":{"type":"integer"},"name":{"type":"string"}},"required":["name","age"],"type":"object"}}'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 $0.005:
// GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fkeyronne.com%2Fapi%2Fvalidate-json
const res = await pay("https://keyronne.com/api/validate-json", {
method: "POST",
headers: { "content-type": "application/json" },
body: JSON.stringify({"data":{"age":"36","name":"Ada"},"schema":{"properties":{"age":{"type":"integer"},"name":{"type":"string"}},"required":["name","age"],"type":"object"}}),
});
console.log(await res.json());Example input
{
"data": {
"age": "36",
"name": "Ada"
},
"schema": {
"properties": {
"age": {
"type": "integer"
},
"name": {
"type": "string"
}
},
"required": [
"name",
"age"
],
"type": "object"
}
}Example output
{
"errors": [],
"valid": true,
"value": {
"age": 36,
"name": "Ada"
},
"warnings": [
{
"message": "coerced string \"36\" to integer",
"path": "$.age"
}
]
}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 |
|---|---|---|---|---|
| 8 min ago | Passed | 402 | 65 ms | $0.001 |
| 4 h ago | Passed | 402 | 209 ms | $0.001 |
| 7 h ago | Passed | 402 | 156 ms | $0.001 |
| 11 h ago | Passed | 402 | 164 ms | $0.001 |
| 15 h ago | Passed | 402 | 231 ms | $0.001 |
| 18 h ago | Passed | 402 | 48 ms | $0.001 |
| 22 h ago | Passed | 402 | 258 ms | $0.001 |
| 25 h ago | Passed | 402 | 174 ms | $0.001 |
| 29 h ago | Passed | 402 | 141 ms | $0.001 |
| 33 h ago | Passed | 402 | 152 ms | $0.001 |
| 36 h ago | Passed | 402 | 52 ms | $0.001 |
| 41 h ago | Passed | 402 | 298 ms | $0.001 |