# format.openverbs.com – Format Detection

> format.openverbs.com – Format Detection is a paid API for AI agents from format.openverbs.com, paid per call via x402, $0.004/call, status unknown (last checked 2026-09-14).

Detects and identifies the structured format(s) of an unknown document, returning a scored list of all plausible formats plus a best-guess winner.

## Facts

- Endpoint: POST https://format.openverbs.com/v1/detect
- Price: $0.004/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/format-openverbs-com-format-detection-e9202556
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ZAZkorHDfQGXs2vVa6nnG

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 format-openverbs-com-format-detection-e9202556 -d '<json body>'
```

Example prompt: I have a raw document and I'm not sure if it's YAML, TOML, or JSON — can you sniff its format and tell me every plausible match with a confidence score, plus the best guess?

## When to prefer this

Use this endpoint when you receive an unknown document and need to determine its format before parsing or transcoding it — especially when formats could overlap (e.g. JSON vs JSON5 vs JSONC, or CSV vs TSV). Prefer this over guessing or hardcoding a parser when input provenance is unreliable.

## Known failure modes

- Empty or too-short input string rejected (minLength:1 enforced)
- Input exceeding 1,000,000 characters rejected
- Completely unstructured or binary data may yield low confidence scores across all formats with no strong best guess
- Payment failure via x402 protocol results in 402 response before detection runs

## How this service works

Sniff which structured format an unknown document is. Because formats overlap, returns every plausible format with a 0–1 score plus the best guess — honest about ambiguity rather than pretending certainty.

## Output

Returns a list of all plausible detected formats, each with a 0–1 confidence score, plus a single best-guess format. Designed to surface ambiguity honestly rather than forcing a single answer when multiple formats are plausible.

## Request schema (JSON Schema)

```json
{
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "type": "object",
 "properties": {
  "input": {
   "type": "object",
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "type": "string",
     "enum": [
      "POST"
     ]
    },
    "bodyType": {
     "type": "string",
     "enum": [
      "json",
      "form-data",
      "text"
     ]
    },
    "body": {
     "type": "object",
     "properties": {
      "data": {
       "type": "string",
       "minLength": 1,
       "maxLength": 1000000,
       "description": "The document whose format should be detected."
      }
     },
     "required": [
      "data"
     ],
     "additionalProperties": false
    }
   },
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "additionalProperties": false
  }
 },
 "required": [
  "input"
 ]
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/format-openverbs-com-format-detection-e9202556/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from format.openverbs.com](https://www.zero.xyz/host/format.openverbs.com/llms.txt)