# 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.

Human version: https://kymaapi.com/models/bge-base-en
Live JSON: `GET https://kymaapi.com/v1/models` (no auth required)

## Facts

- **Model ID**: `bge-base-en` — pass this as `model` in the request body
- **Creator**: Baai
- **Released**: 2023-09-12
- **Context window**: 1K tokens
- **Price**: $0.00675 in / $0.00 out per 1M, cached input 10%
- **Capabilities**: tools, caching

## Call it

```bash
curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer $KYMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "bge-base-en", "messages": [{"role": "user", "content": "Hello"}]}'
```

## See also

- All models: https://kymaapi.com/models.md
- Pricing: https://kymaapi.com/pricing.md
- Other models by Baai: https://kymaapi.com/models?q=Baai