# Agent Hub Text Embeddings (BGE-M3 Multilingual)

> Agent Hub Text Embeddings (BGE-M3 Multilingual) is a paid API for AI agents from agents.torbrooknews.com, paid per call via x402, $0.002/call, status unknown (last checked 2026-10-13).

Generates multilingual text embeddings using BGE-M3 (1024-dimensional vectors) for semantic search and RAG pipelines, accepting up to 100 texts per call at a flat per-call price.

## Facts

- Endpoint: GET https://agents.torbrooknews.com/v1/embed?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-hub-text-embeddings-bge-m3-multilingual-4e6c9f5f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_qlN7PLudxH0ltZcGMD6ks

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 agent-hub-text-embeddings-bge-m3-multilingual-4e6c9f5f
```

Example prompt: Can you generate BGE-M3 embeddings for these three sentences so I can index them in my vector database: 'The cat sat on the mat', 'Le chat est sur le tapis', 'El gato está en la alfombra'?

## When to prefer this

Choose this endpoint when you need multilingual, high-quality dense embeddings (BGE-M3, 1024-dim) for semantic search or RAG without managing your own embedding infrastructure. Ideal for batches of up to 100 texts at a flat $0.002 per call — extremely cost-efficient for bulk embedding. Prefer over OpenAI embeddings when multilingual coverage and open-weight reproducibility matter.

## Known failure modes

- More than 100 texts submitted in a single call — exceeds batch limit
- Empty or missing 'texts'/'text' query parameter — returns error
- Payment not included or insufficient USDC — 402 Payment Required response
- Extremely long individual texts may be truncated or rejected
- Pipe character used within text content may cause incorrect splitting of batch

## How this service works

Text embeddings for semantic search and RAG (BGE-M3, multilingual, 1024 dimensions). Up to 100 texts per call, one flat price. Also callable as GET with the same fields as query parameters.

## Output

Returns 1024-dimensional dense float vectors (BGE-M3 embeddings) for each input text, suitable for semantic similarity, nearest-neighbor search, and retrieval-augmented generation workflows. One vector is returned per input text, preserving input order.

## 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"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "properties": {
      "text": {
       "type": "string"
      },
      "texts": {
       "type": "string",
       "description": "Up to 100 texts; separate items with |"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-hub-text-embeddings-bge-m3-multilingual-4e6c9f5f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agents.torbrooknews.com](https://www.zero.xyz/host/agents.torbrooknews.com/llms.txt)