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

# Embeddings

> Create one or more text embeddings through the OpenAI-compatible AI Gateway route.

## Endpoint

```text theme={null}
POST https://api.inquantum.ai/v1/embeddings
```

## Request

| Field             | Type                | Required | Description                                                       |
| ----------------- | ------------------- | -------- | ----------------------------------------------------------------- |
| `model`           | string              | Yes      | Embedding model. A provider prefix selects a provider explicitly. |
| `input`           | string or string\[] | Yes      | One input string or a batch of strings.                           |
| `encoding_format` | string              | No       | Output encoding supported by the selected model.                  |
| `dimensions`      | integer             | No       | Requested dimensions for models that support it.                  |
| `user`            | string              | No       | End-user identifier stored with request attribution.              |

```bash theme={null}
curl https://api.inquantum.ai/v1/embeddings \
  -H "Authorization: Bearer $PLANCK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-small",
    "input": ["first document", "second document"]
  }'
```

## Response

```json theme={null}
{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [0.0123, -0.0456],
      "index": 0
    }
  ],
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 4,
    "total_tokens": 4
  }
}
```

See the [Embeddings guide](/gateway/embeddings) for SDK examples, routing, billing, and tracking.