# Agents Trust API Recommender

> Agents Trust API Recommender is a paid API for AI agents from api.agents-trust.ai, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-23).

Ranks and recommends candidate x402 paid APIs for a given task, with live challenge checks, pricing, reliability, and risk flags

## Facts

- Endpoint: GET https://api.agents-trust.ai/recommend?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-23
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agents-trust-api-recommender-0508d89a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Z-iX1znYLTTo1zOVgakCc

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-api-recommender-0508d89a
```

Example prompt: I need to find the best paid x402 API for getting live weather forecasts — can you recommend up to 3 options ranked by reliability, show me their prices, and make sure they pass a live payment challenge right now?

## When to prefer this

Choose this endpoint when an AI agent needs to dynamically discover and route to the best available x402 paid API for a given task, rather than hardcoding a specific provider. Especially useful when comparing multiple API candidates by price, reliability, and live availability before committing a payment. Prefer this over manual API registries when you need real-time challenge verification and risk flagging.

## Known failure modes

- Missing or too-short 'need' parameter returns validation error
- live=0 is unsupported and will error
- Invalid CAIP-2 chain format returns a pattern mismatch error
- Insufficient evidence for a task may return fewer results than requested limit
- 0.01 USDC payment challenge failure results in no response delivered
- max_price_usd filtering may yield zero results if threshold is too low

## How this service works

Which x402 API should I call? Agents Trust Recommend ranks candidate paid APIs for a task: agent API recommendations, x402 endpoint discovery, API search and marketplace search. Returns URLs, API pricing, reliability, live challenge checks, paid delivery evidence and risk flags. Tasks: weather forecast, web search, stock prices. Fee: 0.01 USDC on Base or Solana. Evidence tiers are provisional, not an endorsement.

## Output

A ranked list of up to 5 candidate paid API endpoints (URLs) matching the requested task, each annotated with pricing, reliability scores, live payment challenge results, paid delivery evidence tiers, and risk flags. Response also includes metadata such as schema version, generation timestamp, task interpretation, and the selected view format.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "http://json-schema.org/draft-07/schema#",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method",
    "queryParams"
   ],
   "properties": {
    "type": {
     "const": "http"
    },
    "method": {
     "const": "GET"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "need"
     ],
     "properties": {
      "live": {
       "enum": [
        1
       ],
       "type": "integer",
       "default": 1,
       "description": "Every returned endpoint must answer a payment challenge during this request. live=0 is unsupported."
      },
      "need": {
       "type": "string",
       "maxLength": 300,
       "minLength": 2,
       "description": "A phrase describing the required work, with at least two letters or digits. The limit counts Unicode characters in the original input, including whitespace. Accepted text is normalized without truncation and embedded for semantic retrieval."
      },
      "view": {
       "enum": [
        "legacy",
        "compact",
        "evidence",
        "debug"
       ],
       "type": "string",
       "default": "legacy",
       "description": "Legacy preserves successful-response fields and types. The other views use recommend.v2. Compact includes routing facts, evidence adds measurements, and debug adds bounded retrieval diagnostics."
      },
      "chain": {
       "type": "string",
       "pattern": "^[a-z0-9-]{2,16}:[A-Za-z0-9_=-]{1,64}$",
       "description": "Provider payment network in CAIP-2 form, such as eip155:8453. This does not identify the blockchain analyzed by the service."
      },
      "limit": {
       "type": "integer",
       "default": 3,
       "maximum": 5,
       "minimum": 1,
       "description": "Maximum number of picks. Fewer results are returned when evidence is insufficient."
      },
      "max_price_usd": {
       "type": "number",
       "minimum": 0,
       "description": "Maximum nominal USD price of the selected provider offer. Separate from the 0.01 USDC recommendation fee. The provider challenge at call time is authoritative."
      }
     },
     "additionalProperties": false
    }
   }
  },
  "output": {
   "type": "object",
   "properties": {
    "type": {
     "const": "json"
    },
    "example": {
     "type": "object",
     "anyOf": [
      {
       "properties": {
        "meta": {},
        "picks": {}
       }
      },
      {
       "properties": {
… (truncated)
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agents-trust-api-recommender-0508d89a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.agents-trust.ai](https://www.zero.xyz/host/api.agents-trust.ai/llms.txt)