# uxus.finance Text Embedding API

> uxus.finance Text Embedding API is a paid API for AI agents from uxus.finance, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Generates a 1024-dimensional jina-embeddings-v3 vector for each input string (up to 64 strings per call), returning embeddings with dimension count and token usage.

## Facts

- Endpoint: POST https://uxus.finance/api/embed
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/uxus-finance-text-embedding-api-f59d2c80
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_g_5sPYUCtLY3_v1o1NrQm

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 uxus-finance-text-embedding-api-f59d2c80 -d '<json body>'
```

Example prompt: Embed these 3 product descriptions into jina-embeddings-v3 vectors so I can store them in my vector database: 'Wireless noise-cancelling headphones', 'Bluetooth over-ear headset with ANC', 'Premium audio headphones with active noise reduction'.

## When to prefer this

Choose this endpoint when you need jina-embeddings-v3 specifically (1024-dim, strong multilingual and retrieval performance), can batch up to 64 strings per call, and want a pay-per-call model via x402/USDC without subscription overhead. Prefer over OpenAI or Cohere embeddings when you want jina's model quality and the x402 micropayment model fits your stack.

## Known failure modes

- Batch exceeds 64 strings — request rejected with error
- Empty input array or null strings — validation error returned
- Input strings too long for model token limit — truncation or error
- Payment failure via x402 protocol — 402 response with payment details
- Network timeout on large batches — partial or no response

## How this service works

Text embeddings for AI agents — no API key, no account, no signup; pay per call in USDC on Base. POST JSON { input: string or string[] (max 64 per call) }. Model is jina-embeddings-v3, 1024 dimensions, retrieval.passage task. Returns { model, embeddings (one vector per input), dimensions, count, usage, latency_ms }. For agents building a vector index or doing semantic search without a Jina or OpenAI key.

## Output

Returns an array of 1024-dimensional float vectors (one per input string), along with the dimension count (1024) and token usage statistics for the batch call.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "input": {
   "type": "string | string[]",
   "description": "Text to embed, or an array of up to 64 strings."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "count": 1,
  "model": "jina-embeddings-v3",
  "usage": {
   "total_tokens": 8
  },
  "dimensions": 1024,
  "embeddings": [
   [
    0.013,
    -0.021,
    0.005
   ]
  ],
  "latency_ms": 300
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/uxus-finance-text-embedding-api-f59d2c80/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from uxus.finance](https://www.zero.xyz/host/uxus.finance/llms.txt)