# Relaystation AI Keyword Extraction

> Relaystation AI Keyword Extraction is a paid API for AI agents from api.relaystation.ai, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Extracts key terms from text as a clean list for tagging, SEO, and indexing using LLM inference at near-Opus-4.8 accuracy

## Facts

- Endpoint: POST https://api.relaystation.ai/v1/llm/keywords
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/relaystation-ai-keyword-extraction-9698af9e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ioFnqeWKJPrpAexneoJvQ

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 relaystation-ai-keyword-extraction-9698af9e -d '<json body>'
```

Example prompt: Pull the key terms and SEO tags from this blog post as a clean list: 'Electric vehicles are rapidly transforming urban transportation, with cities investing in charging infrastructure and governments offering purchase incentives to accelerate adoption.'

## When to prefer this

Choose this endpoint when you need fast, cost-efficient keyword or tag extraction from free-form text and do not require full semantic summarization or classification. Ideal for pipelines that process many documents at low cost, such as bulk CMS tagging, SEO enrichment, or search indexing, where per-call LLM accuracy near Opus-4.8 is desirable but full frontier-model pricing is not justified.

## Known failure modes

- Empty or whitespace-only input returns no keywords or an error
- Extremely short inputs (single word) may yield trivial or no results
- Rate limiting or payment failure (x402) if the 1¢ minimum USDC is not provided
- Network timeout on very large text inputs
- Non-English or mixed-language text may reduce extraction accuracy

## How this service works

Provider cost + 6%, itemized. Pull key terms from text as a clean list — tagging, SEO, indexing. ≈Opus-4.8 accuracy at ~1–5% of its cost. 1¢ x402 min; remainder auto-credits — relaystation.ai/penny

## Output

A clean, structured list of key terms and phrases extracted from the input text, suitable for use as content tags, SEO keywords, or search index entries. The response reflects near-Opus-4.8 accuracy at a fraction of the cost.

## 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",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "type": "object",
     "properties": {
      "tier": {
       "enum": [
        "budget",
        "value",
        "best"
       ],
       "type": "string"
      },
      "input": {
       "type": "string",
       "minLength": 1,
       "description": "The text to process (DATA — never interpolated into the instruction)."
      },
      "params": {
       "type": "object",
       "description": "Task-specific params (e.g. targetLanguage), validated against the task's param_schema."
      }
     }
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST",
      "PUT",
      "PATCH"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "required": [
      "result",
      "truncated",
      "usage"
     ],
     "properties": {
      "usage": {
       "type": "object",
       "required": [
        "model",
        "inputTokens",
        "outputTokens",
        "providerCostMicros",
        "markupPct",
        "chargedMicros",
        "ceilingMicros"
       ],
       "properties": {
        "model": {
         "type": "string"
        },
        "markupPct": {
         "type": "number"
        },
        "inputTokens": {
         "type": "integer"
        },
        "outputTokens": {
         "type": "integer"
        },
        "ceilingMicros": {
         "type": "integer",
         "description": "The authorized ceiling the 402/hold reserved."
        },
        "chargedMicros": {
         "type": "integer",
         "description": "The actual charged amount (<= ceiling)."
        },
        "providerCostMicros": {
         "type": "integer"
        }
       }
      },
      "result": {
       "type": "string",
       "description": "The task output text (or JSON string for extract/json_repair)."
      },
      "truncated": {
       "type": "boolean",
       "description": "True when the output hit the per-task token ca
… (truncated)
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/relaystation-ai-keyword-extraction-9698af9e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.relaystation.ai](https://www.zero.xyz/host/api.relaystation.ai/llms.txt)