# NetIntel Event Classify

> NetIntel Event Classify is a paid API for AI agents from netintel.dev, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-15).

Classifies whether a given text or topic refers to a specific real-world event (e.g. a dated occurrence) versus a general concept, returning a confidence score and reason.

## Facts

- Endpoint: POST https://netintel.dev/event-classify
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/netintel-event-classify-f48c65de
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_4LDL28vh7oehgO4MwfgCT

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 netintel-event-classify-f48c65de -d '<json body>'
```

Example prompt: Can you classify whether this text is describing a specific real-world event or just a general concept: 'The Federal Reserve emergency rate cut on March 15, 2020'? I want to know if it's an event, why, and how confident you are.

## When to prefer this

Use this endpoint when you need to determine programmatically whether a piece of text or a search query refers to a specific, dated real-world event (news, incident, occurrence) versus a generic topic or concept. Ideal for routing logic in search engines, news classifiers, query understanding systems, or agent pipelines that behave differently for event-driven vs. evergreen content. Prefer it over general-purpose LLM calls for its pay-per-call micropayment model (no subscription), automatic no-charge on failures, and purpose-built confidence scoring.

## Known failure modes

- Input text is missing or empty — returns validation error, not billed
- Upstream AI model failure — returns server error, not billed
- Ambiguous text yields low confidence score (e.g. 0.4) with is_event uncertain
- Rate limits or network timeouts from the underlying model provider
- Text in unsupported language may yield lower accuracy or undefined behavior

## How this service works

Cheap, fast "is this a dateable event?" filter for social and web text — one tiny Haiku call returns is_event, confidence, and a one-line reason, so agents can screen every post for free-ish and only pay for full extraction on the ones that pass. Front-end filter to /event-extract; intentionally minimal output for cost/latency discipline.

## Output

Returns a JSON object with: is_event (boolean indicating if the text describes a specific event), confidence (float 0-1), reason (human-readable explanation), plus a grade (letter A-F), numeric score (0-100), and any findings. Model metadata is included.

## Request schema (JSON Schema)

```json
{
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "type": "object",
 "properties": {
  "input": {
   "type": "object",
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "type": "string",
     "enum": [
      "POST"
     ]
    },
    "bodyType": {
     "type": "string",
     "enum": [
      "json",
      "form-data",
      "text"
     ]
    },
    "body": {
     "type": "object",
     "properties": {
      "text": {
       "type": "string",
       "description": "Caption/post/snippet to classify. Required. Max 10000 words or 50KB."
      },
      "posted_at": {
       "type": "string",
       "description": "Optional ISO-8601 timestamp the content was posted — lets the classifier reject past-event recaps (an event whose only date is in the past relative to posted_at is not dateable)."
      },
      "timezone": {
       "type": "string",
       "description": "Optional IANA timezone (e.g. America/Los_Angeles) for date context."
      }
     },
     "required": [
      "text"
     ]
    }
   },
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "properties": {
      "data": {
       "type": "object",
       "description": "Minimal verdict: is_event (boolean), confidence (0-1), reason (one short line)."
      },
      "meta": {
       "type": "object"
      },
      "score": {
       "type": "number"
      },
      "grade": {
       "type": "string"
      },
      "findings": {
       "type": "array"
      }
     }
    }
   },
   "required": [
    "type"
   ]
  }
 },
 "required": [
  "input"
 ]
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": {
   "reason": "specific dated event",
   "is_event": true,
   "confidence": 0.93
  },
  "meta": {
   "model": "haiku-4.5"
  },
  "grade": "A",
  "score": 100,
  "findings": []
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/netintel-event-classify-f48c65de/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from netintel.dev](https://www.zero.xyz/host/netintel.dev/llms.txt)