Image

Seedream 4.0 API

Seedream 4.0 is ByteDance's image model that generates and edits in one architecture, at 1K, 2K or 4K. On APIMart you call it as seedream-4.0 for text to image, reference-based editing and batches of up to 15 images, billed per image.

1K / 2K / 4KText to ImageImage EditingBatch up to 15Reference Images

Get API Key API Docs

Service Highlights

Official Discounts
Pay-as-you-go
Fast & Low Latency

Input

Model

Prompt

143 characters

Size

Resolution

Number of Images

Sequential Generation

Prompt Optimization Mode

Content Moderation

Watermark

Reference Image

Output

Image link valid for 72 hours

Seedream 4.0 API Pricing

Transparent pricing with no hidden fees. Pay only for what you use.

Variant	Tier	GoldCurrent price	Platinum	Diamond	Official	Your savings
`seedream-4-0`	1K/2K/4K	0.195Credits(~$0.0195)/pic	0.1853Credits(~$0.0185)/pic	0.1755Credits(~$0.0176)/pic	0.2438Credits(~$0.0244)/pic	20%

* Actual costs are subject to final output.

Seedream 4.0 API for 4K Text to Image, Image Editing and Batch Output

Seedream 4.0 (also written Seedream 4 or Seedream v4) is the ByteDance image model that put generation and editing into a single model. Through one APIMart key you can turn a prompt into a 1K, 2K or 4K image, edit a photo with a sentence, or send reference images and get up to 15 consistent variations back in one task. Every resolution costs the same per image.

Get API Key

50K+

Active Users

99.9%

Uptime

Faster

20%

Cost Savings

Key Features of the Seedream 4.0 API

Generation, editing and batch output from one model ID

Text to Image with the Seedream 4.0 API

Send a prompt of up to 1,000 characters and pick an aspect ratio. Put the words you want on the image in double quotes so titles, dates and labels come out as written.

Image Editing with One Sentence

Add an image to image_urls and describe the change: remove a person, replace an object, relight a room or restore an old photo. Generation and editing use the same request format.

Batch Output of up to 15 Images

With at least one reference image, set n (or sequential_image_generation with max_images) to get a set of related images in one task. Reference images plus generated images must total 15 or fewer.

Multi-Reference Consistency

Combine several reference images to keep a character, product or brand style consistent across outputs. Each reference can be a public URL or a base64 data URI in JPEG or PNG, up to 10 MB.

1K, 2K and 4K at the Same Price

Choose 1K, 2K or 4K and one of eleven aspect ratios from 21:9 to 9:21, or auto to follow the reference image. A 1:1 image at 4K is 4096x4096; 16:9 at 4K is 5404x3040.

Knowledge-Driven Illustrations

ByteDance trained Seedream 4.0 for educational illustrations, charts, timelines and blackboard-style explanations, so diagrams with labels and steps are a practical use, not just photos and art.

Standard or Fast Prompt Optimization

optimize_prompt_options switches between standard, which spends longer for higher quality, and fast, which returns sooner with regular quality.

Pay Per Image, Refund on Failure

Billing is per generated image with no subscription. Batch tasks are pre-authorized by count and settled on the images actually produced. Optional nsfw_check and watermark switches are available on every request.

What You Can Build with the Seedream 4.0 API

Workflows that use 4K output, editing and batch generation

Event Posters and Marketing Visuals

Generate posters and banners with the headline and date written into the image, then batch several layout variants from one reference for A/B testing.

Product Shots and Packaging Mockups

Place a product photo into new scenes or backgrounds with Seedream 4.0 image editing and export at 4K for print or large banners.

Educational Diagrams and Charts

Ask for timelines, equation walkthroughs or labelled diagrams; the model's knowledge-driven generation handles structured, text-heavy illustrations.

Style Transfer from References

Turn a photo into watercolor, cyberpunk or a custom house style by pairing it with a style reference in image_urls.

Storyboards and Multi-Panel Sets

Generate a sequence of panels that keep the same character, using one reference image and batch output instead of separate calls.

Photo Retouching and Restoration

Colorize old photos, remove scratches, change the time of day or replace an object with a plain-language instruction.

How to Get a Seedream 4.0 API Key and Start Building

Set up your account, add balance and send your first request

Create an Account and Add Balance

Sign up for APIMart and top up your balance. Billing is pay-as-you-go with no minimum, and the balance works across every model on the platform.

→

Get Your Seedream 4.0 API Key

Create a key in the console. You will send it in the Authorization header of every request.

→

Send Your First Request

POST to /v1/images/generations with model seedream-4.0, a prompt, size and resolution, then poll the returned task_id for the image URL.

Get API Key

Seedream 4.0 API Example: Text to Image and Image Editing

Call seedream-4.0 on APIMart with one POST request. Generation is asynchronous: submit a task, then poll the task endpoint to get the image URLs.

1
Authenticate Seedream 4.0 API requests
Save the key you created above in the APIMART_API_KEY environment variable and send it as Authorization: Bearer <key> on every request.
2
Submit a Seedream 4.0 task
POST /v1/images/generations with model seedream-4.0, your prompt, size and resolution. Add image_urls to edit images or to generate a batch. The response returns a task_id.
3
Get the Seedream 4.0 result
Send GET /v1/tasks/{task_id} every few seconds until the task is completed, then read the image URLs from result.images[0].url. Results are kept for 72 hours, so download the files you want to keep.
See the Seedream 4.0 API reference for the full pixel table and every parameter.

POST /v1/images/generations

curl -X POST https://api.apimart.ai/v1/images/generations \
  -H "Authorization: Bearer $APIMART_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedream-4.0",
    "prompt": "A retro jazz festival poster with the title \"BLUE NOTE NIGHTS\" and the date \"10.01–10.07\" in bold serif letters, saxophone silhouette, warm orange and navy palette",
    "size": "16:9",
    "resolution": "2K"
  }'

import os
import time
import requests

API_BASE = "https://api.apimart.ai"
headers = {"Authorization": f"Bearer {os.environ['APIMART_API_KEY']}"}

# 1. Submit the generation task
payload = {
  "model": "seedream-4.0",
  "prompt": "A retro jazz festival poster with the title \"BLUE NOTE NIGHTS\" and the date \"10.01–10.07\" in bold serif letters, saxophone silhouette, warm orange and navy palette",
  "size": "16:9",
  "resolution": "2K"
}
resp = requests.post(f"{API_BASE}/v1/images/generations", headers=headers, json=payload, timeout=60)
resp.raise_for_status()
task_id = resp.json()["data"][0]["task_id"]

# 2. Poll the task until it finishes
for _ in range(200):
    task_resp = requests.get(f"{API_BASE}/v1/tasks/{task_id}", headers=headers, timeout=30)
    task_resp.raise_for_status()
    task = task_resp.json()["data"]
    if task["status"] == "completed":
        print(task["result"]["images"][0]["url"][0])
        break
    if task["status"] == "failed":
        raise RuntimeError(task.get("error", {}).get("message", "generation failed"))
    time.sleep(3)
else:
    raise TimeoutError(f"task {task_id} did not finish in time; continue GET polling with this task ID")

curl -X POST https://api.apimart.ai/v1/images/generations \
  -H "Authorization: Bearer $APIMART_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedream-4.0",
    "prompt": "Place the product from image 1 on the marble counter from image 2, keep the label and colors unchanged, soft morning light",
    "image_urls": [
      "https://example.com/product.jpg",
      "https://example.com/background.jpg"
    ],
    "size": "auto",
    "resolution": "2K"
  }'

TASK_ID="task_xxx"  # replace with the task_id returned by the POST request
curl "https://api.apimart.ai/v1/tasks/$TASK_ID" \
  -H "Authorization: Bearer $APIMART_API_KEY"

Seedream 4.0 API Parameters

Parameter	Type	Required	Default	Description
`model`	string	Required	Default: seedream-4.0	Model ID. seedream-4.0, seedream-4-0 and Seedream-4.0 are all accepted.
`prompt`	string	Required	Default: —	Text description of the image or the edit, up to 1,000 characters.
`size`	string	Optional	Default: 1:1	Aspect ratio: 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 2:1, 1:2, 21:9, 9:21, or auto to match the reference image (requires image_urls).
`resolution`	string	Optional	Default: 2K	1K, 2K or 4K. All three cost the same per image.
`n`	integer	Optional	Default: 1	Number of images, 1–15. Values above 1 need at least one reference image, and references plus n must total 15 or fewer.
`image_urls`	array	Optional	Default: —	Reference images as public URLs or base64 data URIs, JPEG or PNG, up to 10 MB each. Adding them switches to image editing or reference-based generation.
`optimize_prompt_options`	string	Optional	Default: standard	standard for higher quality, or fast for quicker results with regular quality.
`sequential_image_generation`	string	Optional	Default: disabled	Set to auto with sequential_image_generation_options.max_images (1–15) to generate a related set. Becomes auto automatically when n is above 1.
`watermark`	boolean	Optional	Default: false	Add a watermark to the generated images.
`nsfw_check`	boolean	Optional	Default: false	Moderate the prompt and input images before the task is submitted.

Developer Feedback

What users say about Seedream 4.0 API on APIMart

“Text rendering finally works. We generate event posters with accurate titles and dates - something that always failed with other models.”

Mike Chen

Marketing Developer

“Batch generation changed our workflow. We generate 15 product variations in one call, pick the best, done. Massive time saver.”

Sarah Kim

E-commerce Tech Lead

“Reference image support is a game-changer for brand consistency. Upload brand assets, get on-brand visuals every time.”

James Liu

Creative Agency CTO

“Fast generation speed transformed our content pipeline. We can now produce high-quality visuals at scale without compromising quality.”

Anna Park

Content Platform Engineer

“0.2 Credits(~$0.02) per image with this quality? We migrated from a 2000 Credits(~$200)/month subscription and now spend less while generating more.”

David Wang

Startup Founder

“The unified edit+generate model means one API for everything. Removed 3 other services from our stack.”

Lisa Zhang

Full Stack Developer

Seedream API Model Family

Compare every Seedream model on APIMart. One API key calls all of them through the same endpoint, billed per image.

Model	Best for	Resolution
Seedream 5.0 Pro API	Quality-first single images with dense text, up to 10 references, point and box edits and layer splitting	1K / 1.5K / 2K
Seedream 5.0 Flash API	The Seedream 5.0 Pro feature set at one lower price for every size, with no reference surcharge	1K / 1.5K / 2K
Seedream 5.0 Lite API	2K to 4K output, PNG or JPEG, and batches of up to 15 images per request	2K / 3K / 4K
Seedream 4.5 API	2K or 4K posters with stronger typography and reference fidelity, batches of up to 15	2K / 4K
Seedream 4.0 APIThis page	1K, 2K and 4K at one price, image editing and batches of up to 15 with references	1K / 2K / 4K

All Seedream API models on one page →

Seedream 4.0 API FAQ

Answers about parameters, batch output, resolution and pricing

What is Seedream 4.0?

Seedream 4.0 is ByteDance's image creation model that handles text-to-image generation and image editing in one unified architecture, with output up to 4K and support for several input and output images at once. On APIMart it is available through the Seedream 4.0 API with the model ID seedream-4.0.

Are Seedream 4, Seedream v4 and Seedream 4.0 the same model?

Yes. Seedream 4 and Seedream v4 are short names for Seedream 4.0. In API requests you can send seedream-4.0, seedream-4-0 or Seedream-4.0 as the model value; they all call the same model.

What is the Seedream 4.0 API and how does it work?

It is an asynchronous REST API. You POST /v1/images/generations with model seedream-4.0 and a prompt, receive a task_id, then poll GET /v1/tasks/{task_id} until the task is completed and read the image URLs. The example section on this page has ready-to-run cURL and Python code.

What parameters does the Seedream 4.0 API support?

Required: model and prompt (up to 1,000 characters). Optional: size (an aspect ratio or auto), resolution (1K, 2K or 4K), n (1–15), image_urls, optimize_prompt_options (standard or fast), sequential_image_generation with sequential_image_generation_options.max_images, watermark and nsfw_check. The parameter table above lists types and defaults.

What resolutions and aspect ratios does Seedream 4.0 support?

Choose 1K, 2K (default) or 4K with 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 2:1, 1:2, 21:9 or 9:21, or auto to match the reference image. Output sizes are fixed per ratio, for example 2048x2048 for 1:1 at 2K and 5404x3040 for 16:9 at 4K; custom pixel sizes are not accepted.

Can Seedream 4.0 edit images (image to image)?

Yes. Put one or more images in image_urls and describe the edit in the prompt, for example removing an object, changing text on a sign or relighting a scene. Use size auto to keep the reference image's aspect ratio.

How do I generate multiple images in one Seedream 4.0 request?

Provide at least one reference image and set n, or set sequential_image_generation to auto with max_images. Reference images plus generated images must total 15 or fewer. A text-only request without image_urls always returns a single image.

What are the reference image limits for Seedream 4.0?

Each reference must be a public URL or a base64 data URI in JPEG or PNG, no larger than 10 MB and 6000x6000 pixels in total, with sides over 14 px and an aspect ratio between 1:3 and 3:1. The number of references plus n cannot exceed 15.

How much does the Seedream 4.0 API cost per image?

Seedream 4.0 is billed per generated image, and 1K, 2K and 4K cost the same. The pricing table on this page shows the current Gold member price (20% below list) alongside Platinum (24%) and Diamond (28%) prices. Batch tasks are pre-authorized by the requested count and settled on the images actually produced.

Is the Seedream 4.0 API free?

No. APIMart has no free quota for the Seedream 4.0 API. It is pay-as-you-go with no subscription, and failed tasks are not charged.

How do I get a Seedream 4.0 API key?

Sign up for APIMart, open the API Keys page in your dashboard and create a key. The same key works for the Seedream 4.0 API and every other Seedream version and model on APIMart.

Seedream 4.0 vs Seedream 4.5 vs Seedream 5.0: which should I use?

Seedream 4.0 is the only one of them with 1K, 2K and 4K at one price. Seedream 4.5 drops 1K and improves reference fidelity and dense text. Seedream 5.0 Lite adds 3K and PNG output, while Seedream 5.0 Pro and Flash are single-image 1K–2K models with layer splitting. The Seedream API overview compares them with live prices.

How do I write effective Seedream 4.0 prompts?

Describe the subject, style, lighting and layout in plain sentences, and put any on-image text in double quotes. For edits, say what to change and what to keep, for example "replace the dog with a Schnauzer, keep the background unchanged".

Can I try Seedream 4.0 online?

Yes. The playground at the top of this page runs real Seedream 4.0 generations in your browser. Sign in, add balance and click Run; each image is billed at the same price as an API call, with no subscription. Results are kept for 72 hours.

Where is the Seedream 4.0 API documentation?

The full Seedream 4.0 reference, with every parameter, the complete pixel table and request examples, is in the APIMart docs under Images > Seedream 4.0. The task status endpoint is documented under Tasks.

Can I turn off watermarks and add content moderation?

Yes. watermark defaults to false, so images have no watermark unless you set it to true. Set nsfw_check to true to review the prompt and input images before the task is submitted; it is off by default and adds no cost when unused.

Related Models

Explore more models in the same category.

View All Models →

Seedream 4.0 API FAQ

Answers about parameters, batch output, resolution and pricing

What is Seedream 4.0?

Are Seedream 4, Seedream v4 and Seedream 4.0 the same model?

Yes. Seedream 4 and Seedream v4 are short names for Seedream 4.0. In API requests you can send seedream-4.0, seedream-4-0 or Seedream-4.0 as the model value; they all call the same model.

What is the Seedream 4.0 API and how does it work?

What parameters does the Seedream 4.0 API support?

What resolutions and aspect ratios does Seedream 4.0 support?

Can Seedream 4.0 edit images (image to image)?

How do I generate multiple images in one Seedream 4.0 request?

What are the reference image limits for Seedream 4.0?

How much does the Seedream 4.0 API cost per image?

Is the Seedream 4.0 API free?

No. APIMart has no free quota for the Seedream 4.0 API. It is pay-as-you-go with no subscription, and failed tasks are not charged.

How do I get a Seedream 4.0 API key?

Sign up for APIMart, open the API Keys page in your dashboard and create a key. The same key works for the Seedream 4.0 API and every other Seedream version and model on APIMart.

Seedream 4.0 API

Seedream 4.0 API Pricing

Seedream 4.0 API for 4K Text to Image, Image Editing and Batch Output

Key Features of the Seedream 4.0 API

What You Can Build with the Seedream 4.0 API

How to Get a Seedream 4.0 API Key and Start Building

Create an Account and Add Balance

Get Your Seedream 4.0 API Key

Send Your First Request

Seedream 4.0 API Example: Text to Image and Image Editing

Authenticate Seedream 4.0 API requests

Submit a Seedream 4.0 task

Get the Seedream 4.0 result

Seedream 4.0 API Parameters

Developer Feedback

Seedream API Model Family

Seedream 4.0 API FAQ

What is Seedream 4.0?

Are Seedream 4, Seedream v4 and Seedream 4.0 the same model?

What is the Seedream 4.0 API and how does it work?

What parameters does the Seedream 4.0 API support?

What resolutions and aspect ratios does Seedream 4.0 support?

Can Seedream 4.0 edit images (image to image)?

How do I generate multiple images in one Seedream 4.0 request?

What are the reference image limits for Seedream 4.0?

How much does the Seedream 4.0 API cost per image?

Is the Seedream 4.0 API free?

How do I get a Seedream 4.0 API key?

Seedream 4.0 vs Seedream 4.5 vs Seedream 5.0: which should I use?

How do I write effective Seedream 4.0 prompts?

Can I try Seedream 4.0 online?

Where is the Seedream 4.0 API documentation?

Can I turn off watermarks and add content moderation?

Related Models

Key Features of the Seedream 4.0 API

What You Can Build with the Seedream 4.0 API

How to Get a Seedream 4.0 API Key and Start Building

Create an Account and Add Balance

Get Your Seedream 4.0 API Key

Send Your First Request

Developer Feedback

Seedream 4.0 API FAQ

What is Seedream 4.0?

Are Seedream 4, Seedream v4 and Seedream 4.0 the same model?

What is the Seedream 4.0 API and how does it work?

What parameters does the Seedream 4.0 API support?

What resolutions and aspect ratios does Seedream 4.0 support?

Can Seedream 4.0 edit images (image to image)?

How do I generate multiple images in one Seedream 4.0 request?

What are the reference image limits for Seedream 4.0?

How much does the Seedream 4.0 API cost per image?

Is the Seedream 4.0 API free?

How do I get a Seedream 4.0 API key?

Seedream 4.0 vs Seedream 4.5 vs Seedream 5.0: which should I use?

How do I write effective Seedream 4.0 prompts?

Can I try Seedream 4.0 online?

Where is the Seedream 4.0 API documentation?

Can I turn off watermarks and add content moderation?

Related Models