# ZeroReader BGE Small EN v1.5 Embedding

> ZeroReader BGE Small EN v1.5 Embedding is a paid API for AI agents from api.zeroreader.com, paid per call via x402, $0.001/call, status unknown (last checked 2026-10-03).

Generates fast, lightweight English text embeddings using the BGE Small EN v1.5 model, returning dense float vectors for semantic similarity and retrieval tasks.

## Facts

- Endpoint: POST https://api.zeroreader.com/v1/ai/embed-bge-small?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-03
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/zeroreader-bge-small-en-v1-5-embedding-716f1fc0
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Hdj_Oe7dHdhtOYwxX8iVp

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 zeroreader-bge-small-en-v1-5-embedding-716f1fc0 -d '<json body>'
```

Example prompt: Can you embed this text using a fast, lightweight English model — 'The latest AI breakthroughs are reshaping the tech industry' — and give me back the vector?

## When to prefer this

Choose this endpoint when you need fast, cost-efficient English text embeddings and latency or throughput matters more than maximum quality. Prefer the BGE Large EN v1.5 sibling when embedding quality is paramount. Use this model for high-volume RAG chunking, real-time semantic search, or resource-constrained pipelines where the small model's speed advantage is valuable.

## Known failure modes

- Empty or missing 'text' field returns a 400 validation error
- Input text exceeding model token limit may be truncated or return an error
- Network timeout for very large batches of strings
- Payment failure via x402 protocol results in 402 response blocking the call
- Non-English text may produce lower-quality embeddings due to model training scope

## How this service works

BGE Small EN v1.5 — Fast, lightweight English embeddings.

## Output

Returns a JSON object with an 'object' field set to 'list' and a 'data' array containing embedding objects, each with an index, object type 'embedding', and a dense float array representing the semantic vector of the input text.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "oneOf": [
    {
     "type": "string"
    },
    {
     "type": "array",
     "items": {
      "type": "string"
     }
    }
   ]
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "data": [
  {
   "index": 0,
   "object": "embedding",
   "embedding": [
    0.1,
    0.2,
    0.3
   ]
  }
 ],
 "object": "list"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/zeroreader-bge-small-en-v1-5-embedding-716f1fc0/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.zeroreader.com](https://www.zero.xyz/host/api.zeroreader.com/llms.txt)