Seedream 4.5 API

Use Seedream 4.5 API to generate and edit high-resolution images (up to 4K) with strong text rendering and multi-image consistency for ads, landing pages, and social creatives.

Looking for the latest? Seedream 5.0 adds Deep Thinking and real-time Web Search. Try Seedream 5.0 API →

Model Type:

✓Seedream 4.5

Price: $0.031(~ 2.25 credits) per image

Highest stability with guaranteed 99.9% uptime. Recommended for production environments.

Use the same API endpoint for all versions. Only the model parameter differs.

Prompt

724 (suggested: 2,000)

Input Images

Upload reference images

Click to upload or drag and drop

Supported formats: JPG, JPEG, PNG, WEBP
Maximum file size: 10MB; Maximum files: 10

Size

Quality

Count

For multiple images, describe variations in your prompt

History

Max 20 items

0 running · 0 completed

Your generation history will appear here

Seedream 4.5 API for 4K social visuals

Plug Seedream 4.5 API into your product or workflow via evolink.ai to run image generation and image editing tasks on demand. The API supports a unified request structure — `model + prompt + optional size / n / image_urls / callback_url` — making it suitable for automated creative pipelines across different use cases.

Pricing

Model	Mode	Price
Seedream 4.5	Image Generation (All Sizes)	$0.031/ image(2.25 Credits)

Seedream 4.5

Image Generation (All Sizes)

Price:

$0.031/ image

(2.25 Credits)

If it's down, we automatically use the next cheapest available—ensuring 99.9% uptime at the best possible price.

What Seedream 4.5 API gives you

From simple prompts to 4K lifestyle shots

Use short prompts with optional reference images to generate still images for ads, landing pages, and social content. When higher resolution is required, Seedream 4.5 API supports 2K and 4K outputs, as well as custom pixel sizes within the documented range.Results are returned asynchronously, allowing teams to review, select, and store generated assets in downstream systems.

Generate your first scene

Edit multiple photos with perfect consistency

Seedream 4.5 API supports multi-image input through `image_urls`, enabling the same instruction to be applied across a set of reference images in one request. This pattern is commonly used for product galleries, campaign-wide visual updates, and batch edits where the same transformation logic is applied to multiple inputs. Actual results depend on prompt design and input images, and should be reviewed before use.

Try multi‑image editing

Sharp text, logos and layouts

Seedream 4.5 API can be used in workflows that include typography or layout elements, such as posters, banners, and UI mockups. To control layout and readability, teams typically combine clear prompt instructions with explicit size settings. As with any image generation workflow, generated outputs should be reviewed and selected based on project requirements.

Design ad‑ready creatives

Why choose Seedream 4.5 API on evolink.ai

Seedream 4.5 API is exposed through evolink.ai’s unified API gateway, allowing teams to integrate image generation and editing using a consistent request and authentication pattern.

Made for campaign‑grade visuals

Seedream 4.5 API fits production workflows where teams generate many image variations under real constraints such as fixed sizes, reference images, and automated execution. The API supports batch generation, reference-image edits, and asynchronous execution, which are commonly required in marketing and content operations.

One integration, many use cases

With one API integration, teams can use Seedream 4.5 API for: Text-to-image generation, Image-to-image transformations, and Image editing based on reference inputs. All workflows use the same endpoint and task-based execution model.

Control cost while scaling

Seedream 4.5 API uses usage-based pricing per generated image. Cost can be managed by adjusting output size, number of images per request (`n`), and use of reference images. Pricing details are shown on this page and in the evolink.ai dashboard.

How to integrate Seedream 4.5 API

Seedream 4.5 API follows a simple asynchronous workflow.

Get your evolink.ai API key

Create an API key in the dashboard and store it securely. All requests use Bearer token authentication.

Call /v1/images/generations

Send a POST request with: `model: doubao-seedream-4.5`, `prompt`, and optional parameters such as `size`, `n`, `image_urls`, `prompt_priority`, and `callback_url`.

Retrieve results

Poll the task status endpoint or receive a webhook callback. Generated image URLs are valid for 24 hours and should be saved promptly.

Open Seedream 4.5 API docs

Seedream 4.5 API benefits

This section highlights integration-level and workflow-level benefits based on documented API behavior.

Visual quality

Seedream 4.5 API supports high-resolution still images (up to 4K) for use cases such as banners, landing pages, and social creatives.

Batch workflow

Using the `n` parameter, teams can generate multiple image candidates in a single request and select results during review.

Resolution & formats

Seedream 4.5 API supports simplified 2K / 4K sizing as well as explicit pixel dimensions within the supported range.

Consistency

When reference images are provided via `image_urls`, prompts can guide how existing visual elements are preserved or transformed across outputs.

Developer friendly

The API uses standard REST requests, Bearer token authentication, and asynchronous task handling, making it suitable for backend services and automation tools.

Cost control

Usage-based pricing and configurable parameters allow teams to manage image generation volume and resolution according to project needs.

Seedream 4.5 API FAQ

Everything you need to know about the product and billing.

Seedream 4.5 API is an image generation and editing interface exposed via evolink.ai. You send a prompt (and optional reference images) to POST /v1/images/generations, receive a task id, then retrieve generated image URLs when the task completes. It supports text-to-image, image-to-image, and image editing.

This page describes Seedream 4.5 API’s request/response contract and limits as documented in the API Reference below. For differences in model behavior and output characteristics between versions, use the provider’s official notes and your own evaluation results.

You can use the API to generate or edit images for product and marketing workflows by sending prompts and optional reference images. Always review applicable terms for your region and use case.

Pricing is shown on this page and may vary by plan and usage. For exact costs, rely on the pricing information displayed in your dashboard and the pricing card on this page.

The API is task-based (async) and supports callback_url, so it can be integrated into automation workflows that create and retrieve images programmatically. Output quality depends on prompts and reference images, so plan for iteration.

Use Bearer token authentication, call POST /v1/images/generations with model: "doubao-seedream-4.5" plus your prompt, then poll task status or use callback_url to receive completion notifications. Save returned image URLs promptly (links are valid for 24 hours).

Explore more image APIs on EvoLink

Seedream 4.0|Seedream 5.0 Lite

API Reference

Select endpoint

Authentication

All APIs require Bearer Token authentication.

Header

Authorization: 
Bearer YOUR_API_KEY

Get API Key

POST

/v1/images/generations

Generate Image

Create an image generation task using text prompts or reference images. Supports text-to-image, image-to-image, and image editing modes.

Asynchronous processing mode, use the returned task ID to .

Generated image links are valid for 24 hours, please save them promptly.

Request Parameters

modelstringRequiredDefault: doubao-seedream-4.5

Image generation model name.

Value	Description
doubao-seedream-4.5	Seedream 4.5 model

Exampledoubao-seedream-4.5

promptstringRequired

Prompt describing the image to be generated or how to edit the input image.

Notes

Limited to 2000 tokens

ExampleA serene lake reflecting the beautiful sunset

nintegerOptionalDefault: 1

Maximum number of images to generate.

Value	Description
1-15	Any integer between 1 and 15

Notes

To generate multiple images, include prompts like: "generate 2 different images" in your prompt
Reference image count + final generated image count ≤ 15 images
Each request will pre-charge based on the value of n, actual charges based on the number of images generated

Example1

sizestringOptionalDefault: auto

Aspect ratio of generated images.

Value	Description
auto	Auto - model determines optimal ratio
1:1	Square
2:3 / 3:2	Portrait / Landscape
3:4 / 4:3	Portrait / Landscape
4:5 / 5:4	Portrait / Landscape
9:16 / 16:9	Vertical / Horizontal
21:9	Ultra-wide

Notes

Backend auto-converts ratio + quality to exact pixels

Example16:9

qualitystringOptionalDefault: 2K

Resolution tier for generated images. Backend converts ratio + quality to exact pixel dimensions.

Value	Description
2K	High quality (default)
4K	Ultra quality (higher cost)

Notes

Seedream 4.5 does not support 1K quality

Example2K

prompt_prioritystringOptionalDefault: standard

Prompt optimization strategy, used to set the mode for prompt optimization.

Value	Description
standard	Standard mode, higher quality output, longer processing time

Examplestandard

image_urlsarrayOptional

Reference image URL list for image-to-image and image editing features.

Notes

Max 14 images per request
Max size: 10MB per image
Formats: .jpeg, .jpg, .png, .webp, .bmp, .tiff, .gif
Aspect ratio (width/height) range: [1/16, 16]
Width and height (px) > 14
Total pixels: no more than 6000×6000
URLs must be directly accessible by the server

Examplehttps://example.com/image1.png

callback_urlstringOptional

HTTPS callback address after task completion.

Notes

Triggered on completion, failure, or cancellation
Sent after billing confirmation
HTTPS only, no internal IPs
Max length: 2048 chars
Timeout: 10s, Max 3 retries

Examplehttps://your-domain.com/webhooks/image-task-completed

Request Example

{
  "model": "doubao-seedream-4.5",
  "prompt": "A serene lake reflecting the beautiful sunset",
  "size": "16:9",
  "quality": "2K",
  "n": 1,
  "prompt_priority": "standard"
}

Response Example

{
  "created": 1757165031,
  "id": "task-unified-1757165031-seedream4d",
  "model": "doubao-seedream-4.5",
  "object": "image.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 45
  },
  "type": "image",
  "usage": {
    "billing_rule": "per_call",
    "credits_reserved": 2.25,
    "user_group": "default"
  }
}