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

# Seedream 4.5

> High-fidelity image generation and editing with up to 14 reference images, strong text rendering, and 2K or 4K output at one flat price.

![Seedream 4.5](https://media.empiriolabs.ai/model-logos/seedream-4-5.png)

[ByteDance](/providers/bytedance) · Image Generation

`POST /v1/images/generations`

High-fidelity image generation and editing with up to 14 reference images, strong text rendering, and 2K or 4K output at one flat price.

## At a glance

| Field               | Value                                                           |
| ------------------- | --------------------------------------------------------------- |
| Model id            | `seedream-4-5`                                                  |
| Model release date  | 2025-12-03                                                      |
| Input modalities    | Text, Image                                                     |
| Output modalities   | Image                                                           |
| Context window      | -                                                               |
| Weight precision    | -                                                               |
| Region              | Malaysia                                                        |
| Features            | editing, text\_rendering, batch\_generation                     |
| Native inference    | No                                                              |
| New                 | No                                                              |
| Supported endpoints | `POST /v1/images/generations`                                   |
| Alternate model ids | `bytedance/seedream-4.5`, `seedream-4.5`, `seedream-4-5-251128` |

## Pricing

| Charge   | Spec      | Rate    |
| -------- | --------- | ------- |
| Standard | per image | \$0.080 |

## Example request

```bash
curl https://api.empiriolabs.ai/v1/images/generations \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "seedream-4-5", "prompt": "a misty forest at dawn", "size": "1024x1024"}'
```

## Parameters

| Parameter         | Type    | Required | Default  | Description                                                                                                                                                                                                |
| ----------------- | ------- | -------- | -------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `prompt`          | string  | yes      | -        | Text prompt. With image attached, becomes an editing instruction. For batch mode, describe each image sequentially.                                                                                        |
| `aspect_ratio`    | enum    | no       | `"auto"` | Auto lets the model choose dimensions within the selected resolution tier. Explicit ratios use the preset size for that tier. · Allowed: `auto`, `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3`, `21:9` |
| `quality`         | enum    | no       | `"2K"`   | Output resolution tier. Every tier bills at the same flat per-image rate. · Allowed: `2K`, `4K`                                                                                                            |
| `use_custom_size` | boolean | no       | false    | Use custom\_width and custom\_height instead of preset aspect\_ratio and quality.                                                                                                                          |
| `custom_width`    | number  | no       | -        | Pixels. Total area must be in \[3.69MP, 16.78MP]; aspect must be in \[1:16, 16:1]. Only when use\_custom\_size=true. · Range: 1440 – 6240                                                                  |
| `custom_height`   | number  | no       | -        | Pixels. Total area must be in \[3.69MP, 16.78MP]; aspect must be in \[1:16, 16:1]. Only when use\_custom\_size=true. · Range: 1440 – 6240                                                                  |
| `image`           | array   | no       | -        | Up to 14 reference image URLs for editing. Triggers image-edit mode.                                                                                                                                       |
| `images`          | array   | no       | -        | Alias for image. Use this for multiple uploaded image references.                                                                                                                                          |
| `batch_enabled`   | boolean | no       | false    | Generate a cohesive set of related images from a single prompt.                                                                                                                                            |
| `max_images`      | number  | no       | `4`      | Batch mode only. Maximum images in the set; the model decides actual count. You are billed only for images returned. · Range: 1 – 15                                                                       |
| `watermark`       | boolean | no       | false    | When enabled, the generated image includes an AI-generated provenance watermark. EmpirioLabs does not add a separate watermark.                                                                            |
| `response_format` | enum    | no       | `"url"`  | Return signed image URLs by default, or include base64 image data when b64\_json is requested. · Allowed: `url`, `b64_json`                                                                                |

## Notes

Text-to-image, single-reference editing, and multi-reference generation from up to 14 input images, plus batch sets of up to 15 related images. Every size bills at the same flat per-image rate, and input reference images are free.

**Output**

* 2K or 4K tiers, or an explicit size between 3.69MP and 16.78MP total pixels. JPEG output.

**Batch mode**

* sequential\_image\_generation auto generates a cohesive set; you are billed only for images actually returned.

**Content safety**

* Generated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed.

---

*Machine-readable schema:* `GET https://api.empiriolabs.ai/v1/models/seedream-4-5`.