# Catalog Intent Rank Lite

> Catalog Intent Rank Lite is a paid API for AI agents from api.delx.ai, paid per call via x402, $0.001/call, status unknown (last checked 2026-09-13).

Ranks candidate tool names by token overlap with a natural-language query, returning deterministic relevance scores for offline intent-to-SKU routing.

## Facts

- Endpoint: POST https://api.delx.ai/api/v1/x402/catalog-intent-rank
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/catalog-intent-rank-lite-3949232b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_jrvDxkYmi8xOuuMSxDCmB

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 catalog-intent-rank-lite-3949232b -d '<json body>'
```

Example prompt: I have these candidate tool names — ['url-health-check', 'gas-budget-check', 'black-scholes-delta', 'catalog-intent-rank'] — and a user just said 'I want to check if a website is reachable'. Can you rank those tool names by how well they match that intent using token overlap scoring?

## When to prefer this

Choose this endpoint when you need a fast, cheap, deterministic, offline-safe method to rank tool or SKU names against a natural language query without requiring API keys, live data feeds, or ML model inference. Ideal for agent routing pipelines that need reproducible results at $0.001 per call, especially when ranking a small set of candidate names without needing semantic embeddings or vector search.

## Known failure modes

- Missing 'query' field returns a validation error
- Empty or null 'candidates' array results in an empty or error response
- Extremely short or stopword-only queries may produce near-zero scores for all candidates
- Payment failure via x402 protocol prevents access
- Very long candidate lists may degrade latency slightly but remain deterministic

## How this service works

Rank candidate tool names by token overlap with a query. Call when routing a natural-language intent to top SKU names offline. Returns ranked tool_name scores as deterministic JSON for $0.001 USDC via x402 on Base. First-party local math only—no RPC, live market feed, API keys, storage, or mediagen. Advisory only; the caller owns capital, risk, and production controls.

## Output

Returns a deterministic JSON object containing the candidate tool names ranked and scored by token overlap with the input query, from most to least relevant. No external calls or randomness — output is fully reproducible given the same inputs.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "query": {
   "type": "string",
   "description": "Natural language intent query"
  },
  "candidates": {
   "type": "array",
   "description": "Candidate tool_name list"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "ranked": [
   {
    "score": 1,
    "tool_name": "util_kelly_binary"
   },
   {
    "score": 0,
    "tool_name": "util_dns_lookup"
   },
   {
    "score": 0,
    "tool_name": "util_gwei_to_wei"
   }
  ],
  "schema": "delx/util-catalog-intent-rank/v1"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/catalog-intent-rank-lite-3949232b/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)