# Inference402 Keyword Extraction

> Inference402 Keyword Extraction is a paid API for AI agents from inference402.worlddata402.workers.dev, paid per call via x402, $0.002/call, status unknown (last checked 2026-10-19).

Extracts the most relevant keywords from a given text using Llama 3.1 8B, billed per-call via USDC on Base with no API key required.

## Facts

- Endpoint: GET https://inference402.worlddata402.workers.dev/v1/keywords?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-19
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/inference402-keyword-extraction-d909c9db
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Y_DaBB91U3atyI6PXIlH5

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 inference402-keyword-extraction-d909c9db
```

Example prompt: Pull the most important keywords from this text: 'Ethereum layer-2 networks like Base are enabling fast, low-cost micropayments using USDC stablecoins, making pay-per-request AI inference economically viable for autonomous agents.'

## When to prefer this

Choose this endpoint when you need lightweight, cost-effective keyword extraction without API key registration or monthly subscriptions — ideal for agents that process text on-demand and pay only per call via USDC on Base. Best for short-to-medium texts (under 8000 chars) where speed matters and you want a simple keywords array output rather than a full NLP pipeline.

## Known failure modes

- Text exceeds 8000 character limit — request rejected or truncated
- Payment not received or insufficient USDC balance — 402 response with payment details
- Empty or missing 'text' parameter — likely returns an error or empty keywords array
- Model inference timeout on very complex or dense text — may return 5xx error
- Malformed GET request — 400 bad request

## How this service works

Pay-per-call AI inference for agents: chat (Llama 3.3 70B / 3.1 8B), structured JSON, summarize, translate (incl. Egyptian Arabic), extract, classify, sentiment, keywords, rewrite, embeddings, moderation, vision and speech-to-text. USDC on Base mainnet over x402. No API key, no account.

## Output

Returns a JSON object containing a 'keywords' array of the most relevant terms and phrases extracted from the input text, along with a 'model' field identifying the Llama 3.1 8B FP8 model used for inference.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "maxLength": 8000
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "model": "@cf/meta/llama-3.1-8b-instruct-fp8",
  "keywords": [
   "x402",
   "AI agents",
   "USDC",
   "Base",
   "Ethereum L2",
   "Coinbase",
   "pay per request"
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/inference402-keyword-extraction-d909c9db/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from inference402.worlddata402.workers.dev](https://www.zero.xyz/host/inference402.worlddata402.workers.dev/llms.txt)