# Tempest AI Keyword Extraction

> Tempest AI Keyword Extraction is a paid API for AI agents from tumpest.vercel.app, paid per call via x402, $0.15/call, status unknown (last checked 2026-09-14).

Extracts a specified number of relevant keywords from a given text using AI

## Facts

- Endpoint: POST https://tumpest.vercel.app/api/keywords
- Price: $0.15/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/tempest-ai-keyword-extraction-959da8e3
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_aNyP934LsbnEgDhxblkDA

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 tempest-ai-keyword-extraction-959da8e3 -d '<json body>'
```

Example prompt: Pull out the top 10 keywords from this blog post: 'Artificial intelligence is transforming healthcare by enabling faster diagnoses, personalized treatment plans, and predictive analytics that help doctors intervene before conditions worsen.'

## When to prefer this

Use this endpoint when you need AI-powered keyword extraction from arbitrary text and want a pay-per-call model with no subscription. Ideal for pipelines that need to tag, categorize, or index content by topic, or for SEO workflows extracting terms from articles.

## Known failure modes

- Missing required 'text' field returns validation error
- Empty or very short text may yield fewer keywords than requested
- Count parameter exceeding reasonable limits may be capped or ignored
- Payment failure (402) if USDC balance is insufficient
- Network timeout on very long text inputs

## How this service works

Compose, rewrite, translate, and refine content at scale. 25 AI-powered endpoints. Pay-per-call with USDC on Tempo.

## Output

Returns a JSON object with a success boolean and a data object containing the extracted keywords from the provided text, up to the requested count.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "text"
 ],
 "properties": {
  "text": {
   "type": "string",
   "description": "Text to extract keywords from"
  },
  "count": {
   "type": "number",
   "description": "Number of keywords"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "data": {
   "type": "object"
  },
  "success": {
   "type": "boolean"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/tempest-ai-keyword-extraction-959da8e3/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from tumpest.vercel.app](https://www.zero.xyz/host/tumpest.vercel.app/llms.txt)