# Agent Factory Embedding API

> Agent Factory Embedding API is a paid API for AI agents from d1x8xrm7jrzkbs.cloudfront.net, paid per call via x402, $0.002/call, status unknown (last checked 2026-09-15).

Generates vector embeddings for one or more text inputs using Amazon Bedrock inference, billed per-request in USDC via the x402 protocol on Base.

## Facts

- Endpoint: POST https://d1x8xrm7jrzkbs.cloudfront.net/v1/embed
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-factory-embedding-api-e5d3c301
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_nI-QlY_3EuWAIiF1NWdxT

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 agent-factory-embedding-api-e5d3c301 -d '<json body>'
```

Example prompt: Embed this text for me using Agent Factory's Bedrock embedding API: 'The quick brown fox jumps over the lazy dog' — I need the vector to index it in my semantic search system.

## When to prefer this

Choose this endpoint when you need pay-as-you-go text embeddings without managing your own Bedrock account or API keys, particularly in agent workflows where crypto micropayments (USDC on Base via x402) are acceptable or preferred. It is especially suitable for AI agents that need embeddings on-demand without subscription overhead, or for pipelines already integrated with the x402 payment protocol.

## Known failure modes

- Empty or missing text input returns a validation error
- Texts array exceeding model token limits may be truncated or rejected
- Payment failure or insufficient USDC balance causes 402 response before processing
- CloudFront timeout for very large batches of texts
- Model unavailability on Amazon Bedrock returns a 503 or provider error

## How this service works

Pay-per-request datasets and Amazon Bedrock inference for AI agents, settled in USDC over the x402 protocol on Base.

## Output

Returns a JSON object containing the model name used for embedding, the vector dimensionality, and an array of embedding vectors (each a float array) corresponding to each input text — one embedding per text provided.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "A single text to embed"
  },
  "texts": {
   "type": "array",
   "description": "Multiple texts to embed"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "model": {
   "type": "string"
  },
  "dimensions": {
   "type": "number"
  },
  "embeddings": {
   "type": "array",
   "items": {
    "type": "array",
    "items": {
     "type": "number"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-factory-embedding-api-e5d3c301/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from d1x8xrm7jrzkbs.cloudfront.net](https://www.zero.xyz/host/d1x8xrm7jrzkbs.cloudfront.net/llms.txt)