# Multilingual E5 Large

> 1024-dimension embeddings trained on 94 languages, and the most-cited multilingual retrieval baseline outside BGE. Pick it against bge-m3 when the corpus is short-chunk and the comparison is cross-language recall rather than window size.

Human version: https://kymaapi.com/models/multilingual-e5-large
Live JSON: `GET https://kymaapi.com/v1/models` (no auth required)

## Facts

- **Model ID**: `multilingual-e5-large` — pass this as `model` in the request body
- **Creator**: Microsoft
- **Released**: 2024-02-08
- **Context window**: 1K tokens
- **Price**: $0.0135 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": "multilingual-e5-large", "messages": [{"role": "user", "content": "Hello"}]}'
```

## See also

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