# Delx Commerce CSV Schema Inferrer

> Delx Commerce CSV Schema Inferrer is a paid API for AI agents from commerce.delx.ai, paid per call via x402, $0.001/call, status unknown (last checked 2026-10-01).

Infers column names and data types from a raw CSV text sample, returning a structured schema description.

## Facts

- Endpoint: POST https://commerce.delx.ai/api/v1/x402/csv-schema-infer?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-01
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/delx-commerce-csv-schema-inferrer-2e98fd66
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_uF3oPquiSdDA2sLMJ24OG

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-commerce-csv-schema-inferrer-2e98fd66 -d '<json body>'
```

Example prompt: Can you look at this CSV sample and tell me what each column is named and what data type it holds — like whether it's a number, string, date, etc.? Here's the data: 'id,name,score\n1,Alice,9.5\n2,Bob,8.2'

## When to prefer this

Choose this endpoint when you need a fast, cheap ($0.001 USDC), no-signup schema inference from raw CSV text — especially in agent pipelines where you need to programmatically understand tabular data structure before loading, validating, or transforming it. Prefer this over manual parsing or heavier data profiling tools when a lightweight dtype hint per column is sufficient.

## Known failure modes

- Malformed or empty CSV input returns an error or empty columns array
- Ambiguous columns with mixed types may receive a generic dtype_hint like 'string'
- Very short samples (single row) may produce inaccurate dtype hints
- Non-UTF-8 encoded CSV text may cause parsing failures
- Missing column headers may result in auto-generated column names

## How this service works

Pay-per-result APIs for agents. No signup. Exact price. Verifiable delivery. USDC on Base + Solana via x402.

## Output

A JSON object with a schema identifier and an array of column descriptors, each containing the column name and a dtype_hint (e.g. 'number', 'string', 'boolean', 'date') inferred from the CSV sample provided.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "csv": {
   "type": "string",
   "description": "CSV text sample"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "schema": "delx/util-csv-schema-infer/v1",
  "columns": [
   {
    "name": "a",
    "dtype_hint": "number"
   },
   {
    "name": "b",
    "dtype_hint": "string"
   }
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/delx-commerce-csv-schema-inferrer-2e98fd66/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from commerce.delx.ai](https://www.zero.xyz/host/commerce.delx.ai/llms.txt)