# Agents Trust Inspect

> Agents Trust Inspect is a paid API for AI agents from api.agents-trust.com, paid per call via x402, $0.001/call, status unknown (last checked 2026-10-29).

Inspect a single API endpoint URL and get back its pricing, reliability score, delivery evidence, risk flags, and payment metadata before paying to call it.

## Facts

- Endpoint: GET https://api.agents-trust.com/inspect?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-29
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agents-trust-inspect-cfe9947e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_UURGKuW08rE82csJ1jk9j

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 agents-trust-inspect-cfe9947e
```

Example prompt: Before my agent calls https://api.some-provider.com/generate-image, can you inspect that endpoint to get its price range, trust score, risk flags, and delivery evidence so I know it's safe to pay for?

## When to prefer this

Use this endpoint when an AI agent needs to validate an x402-priced or paid API URL before spending funds — especially when the provider is unfamiliar, the risk level is unknown, or delivery evidence is required. Prefer this over the search endpoint when you already have a specific URL and want detailed trust and pricing metadata for that exact endpoint rather than discovering new options.

## Known failure modes

- Credential-bearing or private URLs are rejected before payment
- Malformed URLs are rejected before payment
- Unknown or uncrawled endpoints may return null scores and empty evidence
- Endpoint may return canonical vs exact match types affecting reliability of data
- Stale probe data indicated by high probe_age_hours when endpoint hasn't been recently tested

## How this service works

Find paid APIs for a task and check an endpoint before paying. Agents Trust returns API URLs, pricing, reliability, delivery evidence and risk flags.

## Output

A structured JSON object containing the canonical URL, endpoint ID, service name, description, price range (min/max USD), payment networks, payment offers, catalog listings, live status, last probe timestamp, probe freshness, composite evidence score, seller trust tier and provider score, delivery verification details, evidence provenance, and risk flags — giving an agent everything needed to decide whether to pay and call the endpoint.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "url"
 ],
 "properties": {
  "url": {
   "type": "string",
   "description": "One absolute public HTTPS endpoint URL, supplied exactly once. Credential-bearing, private and malformed URLs are rejected before payment. Host case, default port, fragment and an empty query are folded. Paths and trailing slashes remain distinct."
  },
  "view": {
   "enum": [
    "legacy",
    "compact",
    "evidence"
   ],
   "type": "string",
   "description": "Response view: legacy, compact or evidence."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "oneOf": [
  {
   "type": "object",
   "required": [
    "schema_version",
    "generated_at",
    "lookup",
    "endpoint",
    "meta"
   ],
   "properties": {
    "meta": {
     "type": "object",
     "required": [
      "notes"
     ],
     "properties": {
      "notes": {
       "type": "array",
       "items": {
        "type": "string"
       }
      }
     }
    },
    "lookup": {
     "type": "object",
     "required": [
      "requested_url",
      "canonical_url",
      "match_type"
     ],
     "properties": {
      "match_type": {
       "enum": [
        "exact",
        "canonical"
       ]
      },
      "canonical_url": {
       "type": "string"
      },
      "requested_url": {
       "type": "string"
      }
     }
    },
    "endpoint": {
     "type": "object",
     "required": [
      "endpoint_id",
      "url",
      "service_name",
      "description",
      "description_truncated",
      "description_evidence",
      "category",
      "category_scope",
      "price",
      "networks",
      "payment_offers",
      "payment_offers_truncated",
      "catalog_listings",
      "has_output_schema",
      "output_schema_url",
      "invocation",
      "is_live",
      "last_probe_at",
      "probe_age_hours",
      "probe_freshness",
      "score",
      "seller",
      "delivery_verification",
      "evidence_provenance",
      "risk_flags",
      "as_of",
      "evidence_as_of"
     ],
     "properties": {
      "url": {
       "type": "string"
      },
      "as_of": {
       "type": [
        "string",
        "null"
       ],
       "description": "Legacy UTC timestamp without a zone. Prefer the RFC 3339 freshness and evidence timestamps."
      },
      "price": {
       "type": "object",
       "required": [
        "min_usd",
        "max_usd"
       ],
       "properties": {
        "max_usd": {
         "type": [
          "number",
          "null"
         ]
        },
        "min_usd": {
         "type": [
          "number",
          "null"
         ]
        }
       }
      },
      "score": {
       "type": "object",
       "properties": {
        "endpoint": {
         "type": [
          "number",
          "null"
         ],
         "description": "Composite evidence score, 0–1; null when unmeasured."
        }
       }
      },
      "seller": {
       "type": "object",
       "required": [
        "trust_tier",
        "provider_score",
        "model_version"
       ],
       "properties": {
        "trust_tier
… (truncated)
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agents-trust-inspect-cfe9947e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.agents-trust.com](https://www.zero.xyz/host/api.agents-trust.com/llms.txt)