# CatalogBot (x402.hydratrader.ai)

> Pay-per-call text / extract / research helpers for agents.
> No API key. Pay USDC on Base via HTTP 402 (x402).

Base: https://x402.hydratrader.ai
Networks: eip155:8453
Asset: USDC (exact scheme)
Catalog version: 1

## Listing

[CatalogBot on x402-list](https://x402-list.com/services/catalogbot?utm_source=badge&utm_medium=referral&utm_campaign=embed)

![CatalogBot listed on x402-list](https://x402-list.com/badge/catalogbot.svg)

## Paid routes

### POST /v1/cheap-errand — $0.01 USDC
Summarize text. Classify sentiment. Rewrite. Extract keywords. Translate. When to use: cheap agent glue / probe steps for buyer-supplied text. Returns JSON for $0.01 per call in USDC on Base via x402. No API key. Local-fast NLP; no login scrape. Success JSON includes next_tasks hints for same-session follow-ups.

### POST /v1/structured-extract — $0.03 USDC
Extract structured JSON. JSON schema extract. Structured extract from pasted text or a public URL into YOUR schema. When to use: turn messy public text into typed JSON with confidence + warnings. $0.03 per call in USDC on Base via x402. No API key. Refuses login/paywall sources.

### POST /v1/research-brief — $0.08 USDC
Research brief. Citations. Summarize research from the public web with key points and caveats. When to use: short cited answers for agent questions (fair-use snippets only — no full-text dumps). $0.08 per call in USDC on Base via x402 (cost-floored). No API key.

## Free discovery

- GET /.well-known/x402
- GET /.well-known/x402.json
- GET /.well-known/skills/hydratrader-x402-catalog/SKILL.md
- GET /SKILL.md
- GET /openapi.json
- GET /v1/openapi.json
- GET /llms.txt
- GET /robots.txt
- GET /terms
- GET /pricing
- GET /health
- GET /ready
- GET /

## Auth

No API key. Unpaid POSTs to paid routes return HTTP 402 Payment Required.
Attach an x402 payment and retry the same request.

## Policy

- public sources only
- no login-walled scrape
- no PII harvesting
- no copyright dumps; fair-use snippets + links only

## Notes

Handlers use local NLP and public HTTP sources (model_hint local-fast).
research-brief may refuse when estimated token cost exceeds the list price floor.