# Multilingual E5 Large

> Multilingual text embeddings (74M+ runs) — 1024-dim vectors across 100 languages including Korean. Pairs with Core.Today customer databases' vector search (knn_vector).

- **Provider**: replicate
- **Model ID**: beautyyuyanli/multilingual-e5-large
- **Category**: embeddings
- **Credits**: 2 per request
- **Pricing Type**: fixed

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `texts` (string, optional): text to embed, formatted as JSON list of strings (e.g. ["hello", "world"]) (Default: `["In the water, fish are swimming.", "Fish swim in the water.", "A book lies open on the table."]`)
- `normalize_embeddings` (boolean, optional): Whether to normalize embeddings. (Default: `True`)
- `batch_size` (integer, optional): Batch size to use when processing text data. (Default: `32`; Range: min: 0)

## Example Request

```json
{
  "model": "beautyyuyanli/multilingual-e5-large",
  "input": {
    "texts": "[\"In the water, fish are swimming.\", \"Fish swim in the water.\", \"A book lies open on the table.\"]",
    "normalize_embeddings": true,
    "batch_size": 32
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "black-forest-labs/flux-schnell",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Output Type

json

## Tags

embeddings, text-embedding, multilingual, e5, vector-search, rag

## Documentation

https://replicate.com/beautyyuyanli/multilingual-e5-large