# x402.tanship.dev Multilingual Text Embeddings

> x402.tanship.dev Multilingual Text Embeddings is a paid API for AI agents from x402.tanship.dev, paid per call via x402, $0.002/call, status unknown (last checked 2026-09-13).

Generates 1024-dimensional multilingual text embeddings using the BGE-M3 model via edge AI

## Facts

- Endpoint: POST https://x402.tanship.dev/v1/ai/embeddings
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/x402-tanship-dev-multilingual-text-embeddings-62787422
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_nhhyiHSq5ITx_Io-N3tLP

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 x402-tanship-dev-multilingual-text-embeddings-62787422 -d '<json body>'
```

Example prompt: Turn this paragraph into a 1024-dimensional BGE-M3 embedding so I can store it in my vector database: 'The quick brown fox jumps over the lazy dog.'

## When to prefer this

Choose this endpoint when you need high-quality multilingual text embeddings (1024 dims) from the BGE-M3 model without running your own GPU infrastructure. It is ideal for RAG pipelines, semantic search, and cross-lingual similarity tasks where language coverage matters. Prefer it over OpenAI embeddings when you want a pay-per-call USDC micropayment model via x402 with no monthly subscription, or when BGE-M3's multilingual capabilities are specifically required.

## Known failure modes

- Empty or missing 'input' body returns a 400/422 validation error
- Oversized input text exceeding model context window may be truncated or rejected
- Network timeouts at edge node under high load
- Invalid bodyType enum value causes schema validation failure
- Non-UTF-8 encoded text may cause processing errors

## How this service works

Payment-gated AI and browser automation API using the x402 protocol. All /v1/* endpoints require USDC payment on Base (eip155:8453) via x402 v2 exact scheme.

## Output

Returns a 1024-dimensional float vector (BGE-M3 embedding) representing the semantic content of the input text, suitable for cosine similarity, vector database storage, or downstream ML tasks.

## 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",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "properties": {}
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/x402-tanship-dev-multilingual-text-embeddings-62787422/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402.tanship.dev](https://www.zero.xyz/host/x402.tanship.dev/llms.txt)