# ExchangeRebel Batch Toxicity Scorer

> ExchangeRebel Batch Toxicity Scorer is a paid API for AI agents from exchangerebel.com, paid per call via x402, $0.25/call, status unknown (last checked 2026-11-21).

Scores up to 100 comments at once for toxicity using the Detoxify engine, returning Perspective API-compatible comments:analyze shaped results per item

## Facts

- Endpoint: GET https://exchangerebel.com/toll/toxicity/analyze/batch?utm_source=zero.xyz
- Price: $0.25/call
- Payment: x402
- Status: unknown
- Last checked: 2026-11-21
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/exchangerebel-batch-toxicity-scorer-382a521b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_x2MKIcnPK62p6kxtALyRA

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 exchangerebel-batch-toxicity-scorer-382a521b
```

Example prompt: Can you run toxicity scoring on these 50 user comments from our forum and give me back a Perspective-compatible score for each one so I can flag the harmful ones?

## When to prefer this

Choose this endpoint when you need to score multiple comments in a single call (up to 100) and want Perspective API-compatible output shapes without paying Google Perspective API rates. Ideal for agents doing bulk content moderation, dataset cleaning, or real-time community safety checks where batching reduces latency and cost compared to single-comment endpoints. Prefer this over single-comment endpoints when processing more than a handful of texts at once.

## Known failure modes

- Batch exceeds 100 comments — API likely returns an error or truncates
- Empty input array — returns error or empty results
- Malformed comment text (non-string values) — may cause per-item errors
- Payment not completed — 402 response blocking the request
- Network timeout for very large batches of long comments
- Non-English text may produce less reliable toxicity scores from Detoxify engine

## How this service works

Perspective-compatible toxicity scoring — batch of up to 100 comments, comments:analyze shape per item (Detoxify engine; compatible shape, not Google Perspective scores)

## Output

Returns a Perspective API-compatible comments:analyze shaped response for each submitted comment, including per-attribute toxicity probability scores (e.g. TOXICITY, SEVERE_TOXICITY, INSULT, THREAT) produced by the Detoxify engine — one result object per input comment, up to 100 items per batch call.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object"
    }
   }
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/exchangerebel-batch-toxicity-scorer-382a521b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from exchangerebel.com](https://www.zero.xyz/host/exchangerebel.com/llms.txt)
