# Delx Schema Inference

> Delx Schema Inference is a paid API for AI agents from api.delx.ai, paid per call via x402, $0.003/call, status unknown (last checked 2026-09-16).

Infers field types and nullability from a bounded array of JSON records, returning a deterministic machine-readable schema summary.

## Facts

- Endpoint: POST https://api.delx.ai/api/v1/x402/schema-inference
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/delx-schema-inference-2d18163f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_EeNGRVTlo4dBfc_luzQXC

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 delx-schema-inference-2d18163f -d '<json body>'
```

Example prompt: Infer the field types and nullability from these JSON records before I push them to the pipeline: [{"user_id": 1, "email": "a@example.com", "score": null}, {"user_id": 2, "email": "b@example.com", "score": 4.5}].

## When to prefer this

Use this endpoint when you need a fast, stateless, deterministic schema profile of a bounded JSON record set as a preflight step — especially inside enterprise agent workflows before data ingestion, policy enforcement, or integration decisions. Prefer it over general-purpose LLM schema guessing when you need machine-readable, reproducible type and nullability output with no data retention and a low fixed cost.

## Known failure modes

- Empty records array returns no field data or an error indicating insufficient input
- Non-array input for records field causes a validation error
- Extremely heterogeneous fields with conflicting types may result in ambiguous or union-type annotations
- Payment failure via x402 prevents execution and returns a 402 response
- Malformed JSON in records causes a parse error response

## How this service works

Infer observed field types and nullability from bounded JSON records. Use it as a bounded preflight or analysis step inside an enterprise agent workflow before data, policy, integration, security, or commercial decisions reach production. Returns deterministic machine-readable JSON for $0.003 USDC via x402 on Base. Execution is first-party, local-only, stateless, memory-only, and has no paid upstream or input retention. Results are advisory; the caller remains responsible for authorization and…

## Output

Returns a deterministic machine-readable JSON object describing each observed field name, its inferred type (e.g. string, number, boolean, null), and whether it is nullable, based on the bounded set of input records provided.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "records": {
   "type": "array",
   "description": "Input field: records."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "fields": {
   "id": {
    "types": {
     "int": 2
    },
    "nullable": false
   },
   "active": {
    "types": {
     "bool": 2
    },
    "nullable": false
   }
  },
  "schema": "delx/util-schema-inference/v1",
  "advisory": "Inference describes observed samples; it is not a validation contract.",
  "record_count": 2
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/delx-schema-inference-2d18163f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.delx.ai](https://www.zero.xyz/host/api.delx.ai/llms.txt)