# Oblique Markets Keyword & Named-Entity Extractor

> Oblique Markets Keyword & Named-Entity Extractor is a paid API for AI agents from api.oblique.markets, paid per call via x402, $0.004/call, status unknown (last checked 2026-09-14).

Extracts and ranks keywords and named entities from input text, returning clean validated JSON arrays with one automatic retry on parse failure

## Facts

- Endpoint: POST https://api.oblique.markets/api/v1/paid/keyword-extract
- Price: $0.004/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/oblique-markets-keyword-named-entity-extractor-44ad56a5
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_MCONxYVbd0lUvNUTaXj6Y

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 oblique-markets-keyword-named-entity-extractor-44ad56a5 -d '<json body>'
```

Example prompt: Pull out the ranked keywords and named entities from this article text and give me clean JSON arrays: 'OpenAI and Google DeepMind are racing to deploy large language models, with Sam Altman announcing GPT-5 at a San Francisco event last Tuesday.'

## When to prefer this

Choose this endpoint when you need structured, ranked keyword and named-entity output from arbitrary text in a single low-latency call with guaranteed valid JSON output (including automatic retry). It is especially useful when downstream systems consume JSON arrays directly and cannot tolerate malformed responses. Prefer it over general-purpose LLM prompts for extraction when you need reliability and consistent structure, and over heavyweight NLP pipelines when you want a simple pay-per-call API with no infrastructure overhead.

## Known failure modes

- Input text too short or empty — may return empty arrays
- Text in unsupported language may yield poor extraction quality
- Parse validation failure after one retry — returns error if JSON still invalid
- Payment not settled — x402 payment required before response is returned
- Very long documents may be truncated or time out

## How this service works

Use when an agent needs keyword extract. Returns Ranked keyword and named-entity extraction from text, returned as clean JSON arrays — parse-validated with one automatic retry. $0.004.

## Output

A JSON object containing two arrays: a ranked list of keywords extracted from the input text (ordered by relevance/salience), and a list of named entities (people, organizations, locations, etc.) identified in the text. The response is parse-validated and automatically retried once if the JSON is malformed.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "Text to analyze; truncated to 8,000 characters"
  },
  "max_keywords": {
   "type": "integer"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "model": "inclusionai/ling-3.0-flash",
  "entities": [
   "Coinbase",
   "Base",
   "USDC"
  ],
  "keywords": [
   "x402 protocol",
   "machine payments",
   "stablecoin settlement",
   "API monetization",
   "agent commerce"
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/oblique-markets-keyword-named-entity-extractor-44ad56a5/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.oblique.markets](https://www.zero.xyz/host/api.oblique.markets/llms.txt)