# AgentRXI Text Embeddings (BGE-M3)

> AgentRXI Text Embeddings (BGE-M3) is a paid API for AI agents from agentrxi.com, paid per call via x402, $0.003/call, status unknown (last checked 2026-10-15).

Generates multilingual BGE-M3 text embeddings (1024 dimensions) for up to 100 texts per call, optimized for semantic search and RAG pipelines.

## Facts

- Endpoint: GET https://agentrxi.com/v1/embed?utm_source=zero.xyz
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentrxi-text-embeddings-bge-m3-97366569
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_S-j0eXoi-ui0rHemC8g6V

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 agentrxi-text-embeddings-bge-m3-97366569
```

Example prompt: Embed these three sentences for me using BGE-M3 so I can store them in my vector database: 'The sky is blue', 'El cielo es azul', 'Le ciel est bleu'.

## When to prefer this

Choose this endpoint when you need production-ready multilingual embeddings via a simple pay-per-call API without managing GPU infrastructure. BGE-M3's 1024-dimensional output is well-suited for cross-lingual semantic search and RAG. Best when batching up to 100 texts at once to maximize cost efficiency at $0.003 base price.

## Known failure modes

- Input exceeds 100 texts per call — request is rejected
- Individual text too long for model token limit — truncation or error
- Malformed pipe-separated texts field — parsing failure
- Payment not included or insufficient — 402 response
- Empty input texts — returns error or empty array

## 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. Priced by size: $0.003 + 3x the model token cost. Also callable as GET with the same fields as query parameters.

## Output

Returns 1024-dimensional float embedding vectors for each input text, produced by the multilingual BGE-M3 model. Each text maps to one dense vector suitable for cosine similarity, nearest-neighbor search, or storage in a vector database.

## 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/agentrxi-text-embeddings-bge-m3-97366569/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentrxi.com](https://www.zero.xyz/host/agentrxi.com/llms.txt)