# Seedream 4.5 MCP and API by ByteDance | FlyMy.AI

> ByteDance Seedream 4.5 creates images from a prompt and edits your pictures while keeping the subject, at sizes up to 3072x4096.

Page: https://flymy.ai/mcp/models/bytedance-seedream-4-5/

MCP / Models / Image generation

# Seedream 4.5 MCP: images and edits up to 4K with no API key

ByteDance Seedream 4.5 creates images from a prompt and edits your pictures while keeping the subject, at sizes up to 3072x4096. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

[Use Seedream 4.5](https://flymy.ai/mcp/models/bytedance-seedream-4-5/#start) [Inputs and price](https://flymy.ai/mcp/models/bytedance-seedream-4-5/#inputs)

No API key, $0.04 / run, Text and image to image, ByteDance, Commercial use

$ YOUR NEXT RUN

Claude Code, Codex, Cursor, Any agent

## Use Seedream 4.5 in your assistant

Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.

```
Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/bytedance-seedream-4-5.md. Help me connect the FlyMy.AI MCP to this assistant, then run Seedream 4.5 (flymyai/bytedance-seedream-4_5) for this task: Generate an product photo of a pair of running shoes over a wet city street at night with Seedream 4.5.
```

[Open FlyMy.AI](https://app.flymy.ai/new-agent) [Download brief](https://flymy.ai/mcp/models/bytedance-seedream-4-5.md)

## What Seedream 4.5 does

Seedream 4.5 is ByteDance's model for generation and reference-preserving edits: swap a background, add or remove objects or change an outfit while the person or product stays recognizable. Send a prompt alone, or add up to 14 images (image, image1 to image13). sequential_image_generation set to auto returns a related set of images, and optimize_prompt_mode picks the standard or the fast prompt rewrite.

## Seedream 4.5 inputs

Every input of `flymyai/bytedance-seedream-4_5` as its live schema lists them. Returns `image` (file).

| Input | Type, values and default |
|---|---|
| [#](https://flymy.ai/mcp/models/bytedance-seedream-4-5/#input-prompt) `prompt` | string required |
| [#](https://flymy.ai/mcp/models/bytedance-seedream-4-5/#input-image) `image, image1 to image13` | file optional Allowed: image file, as a URL or upload |
| [#](https://flymy.ai/mcp/models/bytedance-seedream-4-5/#input-size) `size` | string optional Allowed: 2048x2048, 2304x1728, 1728x2304, 2560x1440, 1440x2560, 2496x1664, 1664x2496, 3024x1296, 3072x4096 |
| [#](https://flymy.ai/mcp/models/bytedance-seedream-4-5/#input-watermark) `watermark` | boolean optional Default: `false` |
| [#](https://flymy.ai/mcp/models/bytedance-seedream-4-5/#input-sequential_image_generation) `sequential_image_generation` | string optional Allowed: auto, disabled Default: `disabled` |
| [#](https://flymy.ai/mcp/models/bytedance-seedream-4-5/#input-optimize_prompt_mode) `optimize_prompt_mode` | string optional Allowed: standard, fast Default: `standard` |

## Ask your agent

Requests to paste as they are, once the FlyMy.AI MCP is connected.

**“Generate an product photo of a pair of running shoes over a wet city street at night with Seedream 4.5.”** runs `flymyai/bytedance-seedream-4_5`

**“Make three versions of a poster for a spring sale with 30% off with Seedream 4.5 and send me the links.”** runs `flymyai/bytedance-seedream-4_5`

**“Use Seedream 4.5 to place the product from the photo I attach on a snowy cabin window sill.”** runs `flymyai/bytedance-seedream-4_5`

## Seedream 4.5 price

$0.04 per run. A run at the default settings costs $0.04. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

[See usage pricing →](https://flymy.ai/pricing/)

## Call Seedream 4.5 from code

The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.

### From an agent, through the MCP

The agent calls `get_model_schema`, then `run_model` with:

```
{
  "endpoint_id": "flymyai/bytedance-seedream-4_5",
  "input": {
    "prompt": "A ceramic mug on a sunlit kitchen counter, product photo"
  }
}
```

### From your code, over HTTP

Form fields, not JSON; files go as uploads or public URLs. The answer is a `prediction_id`; read the result at `https://api.flymy.ai/api/v1/flymyai/bytedance-seedream-4_5/predict/async/result/?request_id=<prediction_id>`.

```
curl -X POST https://api.flymy.ai/api/v1/flymyai/bytedance-seedream-4_5/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=A ceramic mug on a sunlit kitchen counter, product photo'
```

## Questions about Seedream 4.5

**Do I need a ByteDance API key for Seedream 4.5?**

No. Seedream 4.5 runs on FlyMy.AI's account, so you need no ByteDance key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

**How much does Seedream 4.5 cost?**

$0.04 per run. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-09.

**How do I use Seedream 4.5 in Claude Code, Codex or Cursor?**

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Generate an product photo of a pair of running shoes over a wet city street at night with Seedream 4.5." Your agent reads the inputs with get_model_schema and runs flymyai/bytedance-seedream-4_5 with run_model.

**What does Seedream 4.5 need as input?**

Seedream 4.5 requires prompt; it also takes 18 optional inputs, each listed on this page with its allowed values and default.

**Can I call Seedream 4.5 from my own code?**

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/bytedance-seedream-4_5/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.

## More image generation models

Text to image: product shots, ads, posters and illustrations from a prompt, many with reference images.

### Seedream 5.0 Pro

ByteDance's precise 5.0 tier for product shots and layouts, blending up to 10 reference images.

Text and image to image / from $0.045 / run

Link: https://flymy.ai/mcp/models/bytedance-seedream-5-0-pro/

### Seedream 5.0 Lite

The quick tier of Seedream 5.0, with better prompt following and in-image text than 4.5.

Text and image to image / $0.035 / run

Link: https://flymy.ai/mcp/models/bytedance-seedream-5-0-lite/

### Seedream 4.0

The earlier Seedream: prompt-only images or edits of up to two pictures, at 2K sizes.

Text and image to image / $0.03 / run

Link: https://flymy.ai/mcp/models/bytedance-seedream/

### GPT Image 2.6

OpenAI's current default image model: faster than 2.5, with text that stays readable.

Text to image / from $0.009 / run

Link: https://flymy.ai/mcp/models/gpt-image-2-6/

### GPT Image 2.6 Sunburst

The precision tier of 2.6 for packaging, campaigns and detailed illustration.

Text to image / from $0.009 / run

Link: https://flymy.ai/mcp/models/gpt-image-2-6-sunburst/

### Nano Banana 2.1

Gemini's newest image model: 14 references, up to 4K, with adjustable thinking.

Text and image to image / from $0.0336 / image

Link: https://flymy.ai/mcp/models/nano-banana-2-1/

## Go to the source

[Seedream 4.5 in the playground →](https://app.flymy.ai/models/flymyai/bytedance-seedream-4_5), [Model endpoints in the docs →](https://docs.flymy.ai/api/models-endpoints), [Image generation guide →](https://docs.flymy.ai/guides/generate-images), [Every model on FlyMy.AI →](https://flymy.ai/mcp/models/), [Every MCP in the catalog →](https://flymy.ai/mcp/#catalog), [Usage pricing →](https://flymy.ai/pricing/)

From the FlyMy.AI model catalog of 2026-11-09: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.

---

For agents: the FlyMyAI operating guide (sign up, connect, run models, tools and agents) is https://flymy.ai/skill.md, and https://flymy.ai/llms.txt lists the other pages and the documentation.