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

# Create Embeddings

> Create text embeddings with VoidAI using a string or array of strings and a supported embedding model.

`POST https://api.voidai.app/v1/embeddings`

Requires [authentication](/authentication) and a model that advertises `/v1/embeddings`.

| Field | Type | Description |
| - | - | - |
| `model` | string, required | Exact embedding model ID, such as `text-embedding-3-small`. |
| `input` | string or array of strings, required | Text to embed. Token-ID arrays are not accepted by this gateway schema. |
| `encoding_format` | string | `float` or `base64`, subject to provider support. |
| `dimensions` | number | Requested dimensions where supported by the model. |

```bash theme={null}
curl https://api.voidai.app/v1/embeddings \
  -H "Authorization: Bearer $VOIDAI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"model":"text-embedding-3-small","input":"Text to embed"}'
```

The response contains a `data` array with each embedding and its input `index`, plus `model` and token `usage`. Check [current model pricing](https://voidai.app/models); do not assume a universal fixed embedding cost.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.