# AI Rook Market Sentiment Classifier

> AI Rook Market Sentiment Classifier is a paid API for AI agents from agents.ai-rook.com, paid per call via x402, $0.025/call, status unknown (last checked 2026-09-14).

Classifies market sentiment (bullish, bearish, or neutral) with confidence scores for trading context

## Facts

- Endpoint: GET https://agents.ai-rook.com/api/classify
- Price: $0.025/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/ai-rook-market-sentiment-classifier-81a4d313
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_jll0IPTfc5KZ0P8hQ641_

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 ai-rook-market-sentiment-classifier-81a4d313
```

Example prompt: Classify this market note as bullish, bearish, or neutral and give me the confidence score: 'BTC breaking above 70k resistance with strong volume and positive CVD divergence.'

## When to prefer this

Use this endpoint when you need a structured, scored sentiment label (bullish/bearish/neutral) with per-class probabilities for trading or market-analysis workflows. Prefer it over generic NLP sentiment APIs when the context is specifically crypto/trading signal classification and when you want confidence scores alongside the label. It is pay-per-call with no API key required, making it suitable for agent-driven automation via x402 on Base.

## Known failure modes

- Missing or empty input text returns 400 error
- Ambiguous or non-market-related text may yield low-confidence neutral classification
- Payment failure (insufficient USDC balance on Base mainnet) returns 402
- Rate limiting or node congestion may cause delays in on-chain payment confirmation

## How this service works

Classify text into user-defined categories. Supports single-label and multi-label. MiniMax M2.7 inference.

## Output

Returns a JSON object with a top-level sentiment label ('bullish', 'bearish', or 'neutral'), a confidence score (0-1 float), and a breakdown of all three class probabilities (all_scores object with bearish, bullish, and neutral keys). Example: {label:'bullish', all_scores:{bearish:0.03, bullish:0.94, neutral:0.03}, confidence:0.94}.

## Request schema (JSON Schema)

```json
{
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/ai-rook-market-sentiment-classifier-81a4d313/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agents.ai-rook.com](https://www.zero.xyz/host/agents.ai-rook.com/llms.txt)