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

# Embeddings

> Create vector embeddings with the OpenAI-compatible API.

<Info>
  Base URL: `https://api.freemodel.app/v1`
</Info>

Create numerical vector representations for text.

## Create embeddings

`POST /embeddings`

Choose an embedding-capable model from [`GET /v1/models`](/api-reference/list-models). The example uses `<embedding-model-id>` to avoid assuming model availability for every account.

```bash theme={null}
curl https://api.freemodel.app/v1/embeddings \
  -H "Authorization: Bearer sk-xxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<embedding-model-id>",
    "input": "FreeModel provides a unified AI API."
  }'
```

```json Response theme={null}
{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0123, -0.0456, 0.0789]
    }
  ],
  "model": "<embedding-model-id>",
  "usage": {
    "prompt_tokens": 8,
    "total_tokens": 8
  }
}
```

## Request body

| Field             | Type            | Required | Description                                           |
| ----------------- | --------------- | -------- | ----------------------------------------------------- |
| `model`           | string          | Yes      | An embedding model ID returned for your API key.      |
| `input`           | string or array | Yes      | One text input or an array of text inputs.            |
| `encoding_format` | string          | No       | Output encoding when supported by the selected model. |

<Note>
  Do not mix vectors from different embedding models in the same similarity index.
</Note>