# Sift Web Tools Text Classifier

> Sift Web Tools Text Classifier is a paid API for AI agents from sift.srv1996466.hstgr.cloud, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-20).

Analyzes text (up to 4000 chars) for language, sentiment, emotions, topics, toxicity, and optionally sorts it into user-defined labels

## Facts

- Endpoint: GET https://sift.srv1996466.hstgr.cloud/v1/classify?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-20
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/sift-web-tools-text-classifier-68a98212
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_UMTC1moa2o0lzUBYWUOxI

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 sift-web-tools-text-classifier-68a98212
```

Example prompt: Can you analyze this customer review for sentiment, emotions, and toxicity, and also classify it as either 'complaint', 'praise', or 'suggestion'? Here's the text: 'The delivery was shockingly late and no one bothered to notify me — absolutely unacceptable service.'

## When to prefer this

Choose this endpoint when you need a combined multi-signal text analysis in a single call — sentiment score, emotions, topics, toxicity, language detection, and a summary — especially when you also want to sort text into your own custom label taxonomy. It is well-suited for content moderation, customer feedback triage, and brand monitoring pipelines where multiple NLP signals are needed simultaneously without chaining multiple API calls.

## Known failure modes

- Text exceeds 4000 characters — the endpoint may truncate or reject the input
- Missing required 'text' query parameter — returns an error
- Ambiguous or very short text may yield low-confidence or generic sentiment scores
- Malformed labels parameter (not comma-separated) may be ignored or cause unexpected results
- Non-English text may have reduced accuracy for emotion and topic detection

## How this service works

Sentiment, emotions, topics and toxicity of text, optionally sorted into your own labels. Analyses up to 4000 characters: language, sentiment and score (-1 to 1), up to 3 emotions, topics, toxicity and a one-line summary. Pass labels=a,b,c to sort the text into your own categories with a score for each.

## Output

A JSON object containing: detected language, overall sentiment label (positive/negative/neutral), a numeric sentiment score from -1 to 1, up to 3 emotions present in the text, relevant topics, a toxicity level (e.g. none/mild/high), a one-line summary, and if labels were provided, a score for each custom label indicating how well the text fits that category.

## 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",
      "HEAD",
      "DELETE"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "text"
     ],
     "properties": {
      "text": {
       "type": "string",
       "description": "Text to analyse (max 4000 chars)"
      },
      "labels": {
       "type": "string",
       "description": "Optional comma-separated labels"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "label": "complaint",
  "language": "English",
  "toxicity": "none",
  "sentiment": "negative",
  "sentiment_score": -0.7
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/sift-web-tools-text-classifier-68a98212/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from sift.srv1996466.hstgr.cloud](https://www.zero.xyz/host/sift.srv1996466.hstgr.cloud/llms.txt)