> ## Documentation Index
> Fetch the complete documentation index at: https://docs.kymaapi.com/llms.txt
> Use this file to discover all available pages before exploring further.

# BGE Base EN v1.5

> 768-dimension English embeddings — half the vector of bge-large-en at the same per-million rate, so an index built on it is half the storage and half the comparison cost. Retrieval quality gives up little on short chunks, which is what the 512-token window enforces anyway.

## Overview

768-dimension English embeddings — half the vector of bge-large-en at the same per-million rate, so an index built on it is half the storage and half the comparison cost. Retrieval quality gives up little on short chunks, which is what the 512-token window enforces anyway.

## Specs

| Field | Value |
| - | - |
| Model ID | `bge-base-en` |
| Best for | English retrieval where index size matters |
| Context window | 512 |
| Input modalities | Text |
| Output modalities | Text |
| Speed | Fast |
| Cost band | Cheap |
| Release stage | Stable |

## Pricing

| | Per 1M tokens |
| - | :-: |
| Input | \$0.00675 |
| Output | \$0.00 |

## Example

```python theme={null}
from openai import OpenAI

client = OpenAI(base_url="https://kymaapi.com/v1", api_key="kyma-...")

response = client.embeddings.create(
    model="bge-base-en",
    input=["first document", "second document"],
)
```

## Agent query example

Ask the API which models fit, instead of hardcoding an id:

```bash theme={null}
curl "https://kymaapi.com/v1/models?recommended_for=search-documents&quality_tier=strong"
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.