> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.empiriolabs.ai/models/skylark-embedding-vision/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.empiriolabs.ai/_mcp/server.

# Skylark Embedding Vision

> Multimodal embedding that fuses text, images, and video into one 1024 or 2048 dimension vector for cross-modal search and retrieval.

![Skylark Embedding Vision](https://media.empiriolabs.ai/model-logos/skylark-embedding-vision.png)

[ByteDance](/providers/bytedance) · Embeddings

`POST /v1/embeddings`

Multimodal embedding that fuses text, images, and video into one 1024 or 2048 dimension vector for cross-modal search and retrieval.

## At a glance

| Field               | Value                                                                                             |
| ------------------- | ------------------------------------------------------------------------------------------------- |
| Model id            | `skylark-embedding-vision`                                                                        |
| Model release date  | 2025-06-28                                                                                        |
| Input modalities    | Text, Image, Video                                                                                |
| Output modalities   | Embedding                                                                                         |
| Context window      | 8K                                                                                                |
| Weight precision    | -                                                                                                 |
| Region              | Malaysia                                                                                          |
| Features            | multimodal, fused vectors                                                                         |
| Native inference    | No                                                                                                |
| New                 | No                                                                                                |
| Supported endpoints | `POST /v1/embeddings`                                                                             |
| Alternate model ids | `byteplus/skylark-embedding-vision`, `skylark-embedding-vision-250615`, `doubao-embedding-vision` |

## Pricing

| Charge              | Spec          | Rate   |
| ------------------- | ------------- | ------ |
| Text input          | per 1M tokens | \$0.25 |
| Image / video input | per 1M tokens | \$0.65 |

## Example request

```bash
curl https://api.empiriolabs.ai/v1/embeddings \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "skylark-embedding-vision", "input": [{"type":"text","text":"Embed me."},{"type":"image","url":"https://media.empiriolabs.ai/example.jpg"}]}'
```

## Parameters

| Parameter         | Type   | Required | Default   | Description                                                                                                                                       |
| ----------------- | ------ | -------- | --------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
| `input`           | string | yes      | -         | Text to embed, an array of up to 16 strings (one embedding each), or an array of text, image\_url, and video\_url parts fused into one embedding. |
| `dimensions`      | enum   | no       | `"2048"`  | Output vector dimensionality. · Allowed: `1024`, `2048`                                                                                           |
| `encoding_format` | enum   | no       | `"float"` | Embedding encoding of the response. · Allowed: `float`, `base64`                                                                                  |
| `instructions`    | string | no       | -         | Optional retrieval instruction that conditions the embedding, such as a query-side or corpus-side template.                                       |

## Notes

**Output**

* One fused vector per request across all input items (text, image, and video combine into a single embedding). Choose 1024 or 2048 dimensions.
* An array of plain strings returns one embedding per string, up to 16 per request.

**Per-input limits**

* Text: up to 8,000 tokens per item.
* Image: JPEG, PNG, WEBP, BMP, or TIFF, sides over 14 px, up to 36MP.
* Video: MP4, AVI, or MOV, up to 50 MB; audio tracks are ignored.

**Retrieval**

* An optional instructions field conditions the embedding for the query or corpus side. Apply L2 normalization before cosine or dot-product comparison.

---

*Machine-readable schema:* `GET https://api.empiriolabs.ai/v1/models/skylark-embedding-vision`.

> Multimodal embedding that fuses text, images, and video into one 1024 or 2048 dimension vector for cross-modal search and retrieval.