# Tanship PayAI — Vector Embedding Endpoint

> Tanship PayAI — Vector Embedding Endpoint is a paid API for AI agents from x402.tanship.dev, paid per call via x402, $0.00003/call, status unknown (last checked 2026-09-15).

Generates multilingual vector embeddings (BGE-M3, 1024 dimensions) for text input via a payment-gated x402 API on Base USDC.

## Facts

- Endpoint: POST https://x402.tanship.dev/v1/ai/vector
- Price: $0.00003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/tanship-payai-vector-embedding-endpoint-94dd018b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_pTgZD20WBCFa11JSdBoNp

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 tanship-payai-vector-embedding-endpoint-94dd018b -d '<json body>'
```

Example prompt: Generate a vector embedding for this paragraph using BGE-M3: 'Tanship provides payment-gated AI APIs using the x402 protocol on Base.' I need the 1024-dim embedding for a semantic search index.

## When to prefer this

Choose this endpoint when you need multilingual, high-quality dense text embeddings (BGE-M3, 1024 dims) with micropayment-per-call billing via USDC on Base (x402), particularly for multilingual semantic search, cross-lingual retrieval, or RAG pipelines where you want to pay per use without a subscription. Prefer over OpenAI or Cohere embedding APIs when you need Base USDC micropayment billing or BGE-M3 specifically for strong multilingual coverage.

## Known failure modes

- Missing or invalid x402 USDC payment header → 402 Payment Required
- Malformed request body (missing required 'input' field or wrong bodyType) → 400 Bad Request
- Insufficient USDC balance on Base → payment failure / 402
- Text input too long for model context window → 400 or truncation
- Network/edge AI latency spike → timeout
- Invalid eip155:8453 wallet address → payment rejection

## 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

A 1024-dimensional float vector (BGE-M3 embedding) representing the semantic content of the input text, suitable for cosine similarity, nearest-neighbor search, and storage in vector databases. May also include model metadata.

## 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/tanship-payai-vector-embedding-endpoint-94dd018b/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)