# AgentRXI Text Embeddings (BGE-M3, Multilingual)

> AgentRXI Text Embeddings (BGE-M3, Multilingual) 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 OpenAI-compatible text embeddings using the BGE-M3 model (1024 dimensions, 100+ languages) for up to 100 texts per call, payable per-request via x402.

## Facts

- Endpoint: GET https://agentrxi.com/v1/embeddings?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-multilingual-1ff189c5
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ZgKaKArAFTXKbVO7Os6n8

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-multilingual-1ff189c5
```

Example prompt: Generate an embedding vector for the text 'quantum entanglement is a phenomenon in quantum physics' using the BGE-M3 model, returning the result as a float array.

## When to prefer this

Choose this endpoint when you need OpenAI-compatible embeddings without an OpenAI API key, want multilingual support across 100+ languages with BGE-M3, need to batch up to 100 texts in a single call at a flat per-request price, or are building a pay-per-use agent pipeline using x402 micropayments. Prefer over OpenAI embeddings when cost predictability per call matters more than per-token billing, or when BGE-M3's multilingual strength is needed.

## Known failure modes

- Missing required 'input' parameter returns a 400 error
- Providing more than 100 input strings may be rejected or truncated
- Invalid encoding_format value returns an error
- Payment failure via x402 results in 402 Payment Required response
- Very long texts may exceed token limits and fail
- Model parameter is silently ignored (always uses bge-m3)

## 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://agentrxi.com/v1 and pay per request with x402. Priced by size and model: $0.003 + 3x the model token cost (bge-m3 is cheapest). Also callable as GET with the same fields as query parameters.

## Output

Returns an OpenAI-compatible JSON response with an array of embedding objects, each containing the embedding vector (as float array or base64-encoded string), the index of the input text, and the object type. Also includes a usage field with prompt_token_count and total_token_count. Fully compatible with OpenAI SDK parsing.

## 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/agentrxi-text-embeddings-bge-m3-multilingual-1ff189c5/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)