# AgentUtility Text Embedding API

> AgentUtility Text Embedding API is a paid API for AI agents from x402.agentutility.ai, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-14).

Converts 1–100 text strings into semantic embedding vectors using Venice-hosted models (Gemini, BGE-M3, or OpenAI-compatible), paid per call via x402/USDC.

## Facts

- Endpoint: POST https://x402.agentutility.ai/text-embedding
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentutility-text-embedding-api-235b6cb9
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_SqNRR3gRWUPcLMEF34553

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 agentutility-text-embedding-api-235b6cb9 -d '<json body>'
```

Example prompt: Embed these 5 product descriptions into semantic vectors using the default Gemini embedding model so I can store them in my vector database: 'wireless headphones with noise cancellation', 'ergonomic office chair', 'stainless steel water bottle', 'portable phone charger', 'mechanical keyboard with RGB lighting'.

## When to prefer this

Choose this endpoint when you need on-demand text embeddings from Venice-hosted models (especially Gemini embedding-2-preview or BGE-M3) paid per call with USDC via x402, without managing API keys or subscriptions. Prefer it for agentic workflows where payment is automated, batch sizes are under 100, and you want model-tier flexibility (newest Gemini, fast BGE-M3, or OpenAI-compatible dimensions).

## Known failure modes

- Input exceeds 100 strings — batch size limit exceeded
- Payment failure via x402/USDC — insufficient balance or payment not confirmed
- Invalid or unsupported model name passed — falls back to error or default
- Empty string or null input in batch — may cause partial or full failure
- Rate limiting if too many calls in short succession

## How this service works

Embeds 1 to 100 strings into semantic vectors via Venice. Tier shorthand: 'default' → gemini-embedding-2-preview (newest, recommended), 'fast' → text-embedding-bge-m3, 'openai-compat' → text-embedding-3-small. You can also pass a full Venice embedding model name. Returns a list of vectors aligned with input order. Use it for text embedding, vector embedding, Venice embeddings, Gemini embeddings, or BGE-M3.

## Output

Returns an ordered list of float vectors, one per input string, aligned positionally with the input array. Each vector encodes the semantic meaning of its corresponding string in the embedding space of the chosen model (Gemini embedding-2-preview, BGE-M3, or text-embedding-3-small).

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "tier": "default",
  "count": 2,
  "model": "gemini-embedding-2-preview",
  "usage": {
   "total_tokens": 6,
   "prompt_tokens": 6
  },
  "source": "venice",
  "dimensions": 1024,
  "embeddings": [
   [
    0.0231,
    -0.142,
    0.0011,
    0.083,
    0.071
   ],
   [
    0.0193,
    -0.151,
    0.0072,
    0.078,
    0.062
   ]
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentutility-text-embedding-api-235b6cb9/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402.agentutility.ai](https://www.zero.xyz/host/x402.agentutility.ai/llms.txt)