# Agent Data Bench – JSON Schema Inference

> Agent Data Bench – JSON Schema Inference is a paid API for AI agents from x402.deepsense.stream, paid per call via x402, $0.002/call, status unknown (last checked 2026-10-20).

Infers a JSON Schema (draft 2020-12) from an example JSON value, detecting nested objects, arrays, required keys, integer vs number, and common string formats.

## Facts

- Endpoint: GET https://x402.deepsense.stream/api/v1/json/schema?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-20
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-data-bench-json-schema-inference-c5617e8e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_mvDA5pTKWW07VQxYvKWia

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability agent-data-bench-json-schema-inference-c5617e8e
```

Example prompt: Can you infer a JSON Schema (draft 2020-12) from this example JSON for me? I want to know the types, required keys, and any detected string formats like dates or emails: {"id": "123e4567-e89b-12d3-a456-426614174000", "email": "user@example.com", "score": 42, "createdAt": "2024-01-15", "tags": ["a", "b"]}

## When to prefer this

Choose this endpoint when you need to automatically derive a formal JSON Schema (draft 2020-12) from an example JSON value, especially for building tool definitions, structured-output contracts, or validation schemas for AI agents. It is particularly valuable when the JSON contains mixed types, nested objects, arrays, or string values that may encode formats like dates, UUIDs, or emails — all of which it detects automatically. Prefer it over hand-writing schemas or using general-purpose LLM inference when you need a standards-compliant, deterministic schema with accurate required-key detection.

## Known failure modes

- Invalid or malformed JSON input returns an error response
- Missing 'value' parameter results in a bad request error
- Extremely deeply nested JSON may have reduced format detection accuracy
- Very large JSON payloads may time out or be rejected
- Ambiguous values (e.g. a string that looks like multiple formats) may produce conservative type annotations

## How this service works

Infer a JSON Schema (draft 2020-12) from an example JSON value: nested objects, arrays, required keys, integer vs number, and string formats (date, date-time, email, uri, uuid). Useful for tool definitions and structured-output contracts.

## Output

A JSON Schema (draft 2020-12) document describing the structure of the input JSON value, including: inferred types for each field (string, integer, number, boolean, null, object, array), required key lists, nested object schemas, array item schemas, and string format annotations (date, date-time, email, uri, uuid) where detected.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "value": {
   "description": "Any JSON value to infer a schema from"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-data-bench-json-schema-inference-c5617e8e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402.deepsense.stream](https://www.zero.xyz/host/x402.deepsense.stream/llms.txt)