# Embeddings API — Text Embeddings

Source: https://ofox.io/docs/api/openai/embeddings

Convert text into vector representations for semantic search, clustering, classification, and other use cases.

## Endpoint

```http
POST https://api.ofox.io/v1/embeddings
```

## Request Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `model` | string | ✅ | Embedding model, e.g. `openai/text-embedding-3-small` |
| `input` | string \| string[] | ✅ | Text to embed (single or batch) |
| `encoding_format` | string | — | Output format: `float` (default) or `base64` |
| `dimensions` | number | — | Output vector dimensions (supported by some models) |

## Request Examples

**cURL**

```bash filename="Terminal"
curl https://api.ofox.io/v1/embeddings \
  -H "Authorization: Bearer $OFOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/text-embedding-3-small",
    "input": "OfoxAI is an LLM Gateway"
  }'
```

**Python**

```python filename="embedding.py" showLineNumbers
from openai import OpenAI

client = OpenAI(
    base_url="https://api.ofox.io/v1",
    api_key="<your OFOXAI_API_KEY>"
)

response = client.embeddings.create(
    model="openai/text-embedding-3-small",
    input="OfoxAI is an LLM Gateway"
)

embedding = response.data[0].embedding
print(f"Vector dimensions: {len(embedding)}")
```

**TypeScript**

```typescript filename="embedding.ts" showLineNumbers
import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://api.ofox.io/v1',
  apiKey: '<your OFOXAI_API_KEY>'
})

const response = await client.embeddings.create({
  model: 'openai/text-embedding-3-small',
  input: 'OfoxAI is an LLM Gateway'
})

console.log(`Vector dimensions: ${response.data[0].embedding.length}`)
```

## Response Format

```json
{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0023, -0.0091, 0.0156, ...]
    }
  ],
  "model": "openai/text-embedding-3-small",
  "usage": {
    "prompt_tokens": 8,
    "total_tokens": 8
  }
}
```

## Available Models

| Model | Dimensions | Description |
|-------|------------|-------------|
| `openai/text-embedding-3-small` | 1536 | Cost-effective |
| `openai/text-embedding-3-large` | 3072 | Highest accuracy |
| `qwen/text-embedding-v4` | 1024 | Optimized for Chinese, Qwen embedding model |