# ZeroReader BGE Large EN v1.5 Embedding API

> ZeroReader BGE Large EN v1.5 Embedding API is a paid API for AI agents from api.zeroreader.com, paid per call via x402, $0.002/call, status unknown (last checked 2026-10-03).

Generates high-quality English text embeddings using the BGE Large EN v1.5 model, returning dense vector representations of input text or arrays of texts.

## Facts

- Endpoint: POST https://api.zeroreader.com/v1/ai/embed-bge-large?utm_source=zero.xyz
- Price: $0.002/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-large-en-v1-5-embedding-api-45bbd14f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_v7Af54yM6-PNJHez7CcKP

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-large-en-v1-5-embedding-api-45bbd14f -d '<json body>'
```

Example prompt: Generate BGE Large EN v1.5 embeddings for this text: 'Retrieval-augmented generation improves factual accuracy in large language models by grounding responses in external knowledge.'

## When to prefer this

Prefer this endpoint when you need high-quality, large-scale English text embeddings specifically from the BGE Large EN v1.5 model, which is known for strong performance on English retrieval and semantic similarity benchmarks. Choose this over smaller models (e.g. Qwen3 Embedding 0.6B) when embedding quality and recall matter more than speed or cost. Use when building English-language RAG pipelines, semantic search indexes, or clustering tasks requiring dense vector representations.

## Known failure modes

- Empty or missing 'text' field returns a 400 validation error
- Oversized input text exceeding model token limit causes truncation or error
- Invalid input type (non-string, non-array) returns a schema validation error
- Network timeout on very large batch arrays
- Payment failure via x402 protocol results in 402 response before processing

## How this service works

BGE Large EN v1.5 — High-quality English embeddings.

## Output

Returns a JSON object with a 'data' array containing embedding objects. Each object includes an index, object type ('embedding'), and an 'embedding' field with a dense float array (high-dimensional vector) representing the semantic content of the input text. Also returns an 'object' field set to 'list'.

## 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-large-en-v1-5-embedding-api-45bbd14f/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)