# Agent Hub BGE-M3 Embeddings

> Agent Hub BGE-M3 Embeddings 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 dimensions) via an OpenAI-compatible /v1/embeddings endpoint, supporting up to 100 inputs per call with no API key required.

## Facts

- Endpoint: GET https://agents.torbrooknews.com/v1/embeddings?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-bge-m3-embeddings-e0ac2ee7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_9G7H2tXh1lEL6rnL2qcKd

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-bge-m3-embeddings-e0ac2ee7
```

Example prompt: Embed the following paragraph using bge-m3 so I can store it in my vector database: 'The quick brown fox jumps over the lazy dog.' Return the float vector.

## When to prefer this

Choose this endpoint when you need OpenAI SDK-compatible embeddings without managing an API key, need multilingual support across 100+ languages, want a flat per-call price, or need to embed up to 100 texts in a single call using bge-m3's 1024-dimensional vectors. Prefer this over OpenAI's own embeddings endpoint when cost predictability per call matters or when you want to avoid OpenAI account dependency for a self-contained agent workflow.

## Known failure modes

- Missing required 'input' parameter returns a 400/422 validation error
- Submitting more than 100 strings in a single call may exceed limits and return an error
- Payment failure via x402 protocol results in a 402 Payment Required response
- Invalid encoding_format value may return a 400 error
- Network or upstream model unavailability may return a 500 or 503 error

## How this service works

OpenAI-compatible embeddings endpoint (bge-m3, 1024 dimensions, 100+ languages): same request and response shape as OpenAI /v1/embeddings, including encoding_format base64. Up to 100 inputs per call, flat price, no API key: point any OpenAI SDK at https://agents.torbrooknews.com/v1 and pay per request with x402. Also callable as GET with the same fields as query parameters.

## Output

Returns an OpenAI-compatible embeddings response object containing a list of embedding objects, each with an index, the embedding vector (as a float array or base64 string depending on encoding_format), and a usage field with prompt_token_count and total_token_count. Vectors are 1024-dimensional from bge-m3.

## 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",
     "required": [
      "input"
     ],
     "properties": {
      "input": {
       "type": "string",
       "description": "Text to embed (POST also accepts an array of up to 100 strings)"
      },
      "model": {
       "type": "string",
       "description": "Ignored; always bge-m3"
      },
      "encoding_format": {
       "type": "string",
       "description": "float (default) | base64"
      }
     }
    }
   },
   "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-bge-m3-embeddings-e0ac2ee7/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)