# ISHOB Text Embedding API

> ISHOB Text Embedding API is a paid API for AI agents from api.ishob.com, paid per call via x402, $0.0002/call, status unknown (last checked 2026-10-14).

Converts text strings into dense vector embeddings using BGE models, suitable for semantic search, clustering, and RAG pipelines

## Facts

- Endpoint: POST https://api.ishob.com/v1/embed?utm_source=zero.xyz
- Price: $0.0002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/ishob-text-embedding-api-62ede269
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_5DT13gvI6IWJ8ZJR3m37h

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 ishob-text-embedding-api-62ede269 -d '<json body>'
```

Example prompt: Embed these three sentences using the bge-small-en-v1.5 model so I can store them in my vector database: 'The sky is blue.', 'Water is wet.', 'Fire is hot.'

## When to prefer this

Choose this endpoint when you need low-cost ($0.0002 USDC), key-free, pay-per-call text embeddings via the x402 micropayment protocol, particularly when already operating within the ISHOB agent ecosystem. Prefer bge-small-en-v1.5 for fast English-only workloads (384 dimensions) and bge-m3 for multilingual or cross-lingual tasks. Good fit for agents that need embeddings on demand without managing API keys or subscriptions.

## Known failure modes

- Input array exceeds 100 items — returns validation error
- Model enum value not recognized — returns 400 bad request
- Payment not included or insufficient — returns 402 Payment Required
- Empty input array — may return empty embeddings array or validation error
- Very long individual strings may be truncated or cause timeout

## How this service works

36 MCP tools &amp; x402 pay-per-call APIs for AI agents: crypto risk, web extraction, screenshots, agent alarms, weather, company data. No API key.

## Output

Returns a JSON object containing the number of embedded texts, the model used, the vector dimensionality (e.g. 384 for bge-small-en-v1.5), and an array of float arrays where each inner array is the embedding vector for the corresponding input text.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "input": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "maxItems": 100,
   "description": "Text or list of texts (a single string is also accepted)"
  },
  "model": {
   "enum": [
    "bge-small-en-v1.5",
    "bge-m3"
   ],
   "type": "string",
   "default": "bge-small-en-v1.5"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "count": 2,
  "model": "bge-small-en-v1.5",
  "dimensions": 384,
  "embeddings": [
   [
    0.012,
    -0.044,
    "..."
   ],
   [
    "..."
   ]
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/ishob-text-embedding-api-62ede269/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.ishob.com](https://www.zero.xyz/host/api.ishob.com/llms.txt)