Bytedance · Image model

Seedream 4.0.
Generate and edit images up to 4K.

One model, one API.

Generate on Coinis Read the docs

One API key. Every model.

per image

Example

AI image

Commercial use included Verified May 26, 2026 Outputs are yours No training on your data

Endpoints

Start building with Seedream 4.0.

One model. Three ways to call it. Same key, same bill.

Seedream 4.0

Image generation

One call. Same key. Same bill.

$0.05 / image

Capabilities

What it does best.

Seedream capabilities

Resolution

Generates images from 960×960 up to 4096×4096 pixels (true 4K output)[^1]
Supports preset sizes: square, square_hd, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9, auto, auto_2K, and auto_4K[^2]
Accepts fully custom width and height values between 1024 and 4096 pixels[^2]

Generation modes

Text-to-image generation from natural-language prompts[^1]
Image-to-image conditioning with 1 to 10 reference images per request[^2]
Batch generation of up to 15 images in a single API call[^2]
Sequential "auto" mode for related scene and character variation sets[^3]

Editing

Natural-language image editing built into the same unified architecture[^1]
Supports object removal, object replacement, and scene modification via plain text (e.g. "Remove the boy" or "Replace this dog with a Schnauzer")[^1]

Prompt enhancement

"Standard" mode: higher output quality, longer generation time[^2]
"Fast" mode: average quality, significantly faster turnaround[^2]

Styles and knowledge

Style transfer across watercolor, cyberpunk, architectural, and other visual styles[^3]
Knowledge-driven generation for educational diagrams, charts, timelines, and annotated illustrations[^1]

Safety and reproducibility

Built-in safety checker enabled by default, toggleable per request[^2]
Outputs a seed value so any result can be reproduced exactly[^2]
Outputs are not used for model training[^3]

API

Call Seedream 4.0 in three lines.

One key. One base URL. Same SDK shape you already use.

curl JavaScript Python

# 1. set your key
export COINIS_API_KEY="sk_live_..."

# 2. call the model
curl https://api.app.coinis.com/v1/image/generate \
  -H "Authorization: Bearer $COINIS_API_KEY" \
  -d '{"prompt":"neon city, rain, tracking shot"}'

import { Coinis } from "@coinis/sdk";
const coinis = new Coinis(process.env.COINIS_API_KEY);

const job = await coinis.image.generate({
  model: "models/bytedance/seedream",
  prompt: "neon city, rain, tracking shot",
});

from coinis import Coinis
coinis = Coinis(os.environ["COINIS_API_KEY"])

job = coinis.image.generate(
    model="models/bytedance/seedream",
    prompt="neon city, rain, tracking shot",
)

Response

{
  "id": "gen_8fa2c1",
  "status": "succeeded",
  "model": "models/bytedance/seedream",
  "output": {
    "image_url": 
                "https://cdn.coinis.com/gen_8fa2c1.mp4"
              
              ,
    "format": "mp4"
  },
  "tokens_used": 10
}

Already on another provider's SDK? Change the host. Keep the call.

Pricing

Token pricing. No surprises.

One wallet across every model. No API accounts to juggle.

Seedream 4.0 · Seedream 4.0

0.5 tokens

per image · $0.05

Photoreal

$0.05 / image

One key. Every model. One invoice. 1 token = $0.10

1 image ≈ 1 tokens ($0.05)

Start free. 15 tokens a week.

No credit card.

Why pay through Coinis

One wallet for every model. No API keys. No separate bills.
Generate ads. Launch to Meta. Track in one place.
On-brand output from your Brand Profile.

1 token = $0.10 pay-as-you-go. Less on a plan.

Use cases

Two buyers. One model.

For builders

Resell every model. One key. One bill.

Unified API across video, image, audio, and LLM.

Generate 500 variants overnight.

Async queue plus webhooks. Batch at scale.

White-label the output.

Ship it under your brand. Outputs are yours.

For creatives

Ship a Reel before lunch.

Prompt to platform-native clip in minutes.

Same product. Ten formats.

One generation, every aspect ratio.

Commercial UGC without a creator.

Authentic selfie-style ads, on brand.

Concept art and storyboards Feed in multiple reference images and a prompt to generate batches of consistent concept art or storyboard frames. Up to 10 input references and 15 output images per request means full scene sets ship in one call.

Educational and instructional illustration Produce accurate diagrams, labeled timelines, and annotated charts from plain-text descriptions. Seedream 4.0's knowledge-driven generation handles structured visual content that most image models fumble.

Photo editing and prototyping Type what you want changed. Remove objects, swap elements, or recompose a scene without opening a separate editing tool. Fast iteration for designers who need quick, client-ready mockups.

Style transfer projects Apply watercolor, cyberpunk, architectural, or custom styles to existing images, or generate styled scenes from scratch. Consistent results at up to 4K make these assets print-ready and production-safe.

Sequential story and character content Use sequential "auto" mode to generate multiple related scenes or character variations in a single request. Ideal for social content series, children's book illustration, or game asset pipelines.

Renders in seconds. Set a seed. Get the same frame back.

Outputs are yours. Sell them.

Safe for paid ads.

Your prompts are never used for training.

FAQ

Seedream 4.0 FAQs

How much does Seedream 4.0 cost on Coinis vs fal.ai or Replicate?

On Coinis, Seedream 4.0 is priced at $0.051 per image. fal.ai and Replicate both list the model at $0.03 per image. Coinis bundles access to every model in the catalog under one account and one invoice, so you are not managing separate vendor credentials for each provider.

Is there a Seedream API, and how do I call it?

Yes. Send a POST request to https://api.app.coinis.com/v1/image/generate with the model parameter set to seedream-4-0. Full schema documentation, including all input parameters and response fields, is available on the Coinis API page.

What is the maximum resolution Seedream 4.0 supports?

Seedream 4.0 generates images up to 4096x4096 pixels (4K). Custom dimensions must each sit between 1024 and 4096 pixels. The minimum total pixel area is 960x960, available via preset sizes.

Can I use Seedream 4.0 outputs commercially?

Yes. Seedream 4.0 is listed as a commercial-use model. Outputs can be sold or used in paid products. Your inputs and outputs are not used for model training.

What is the difference between Seedream 4.0 and Nano Banana or FLUX for image generation?

Seedream 4.0 combines text-to-image and natural-language image editing in a single model and supports batch generation of up to 15 images per request. Nano Banana is Google's specialist editing model. FLUX models target photorealistic output and excel at product photography. Pick Seedream 4.0 when you need generation and editing together, or when batch volume and 4K resolution matter.

How many images can Seedream 4.0 generate in a single request?

Up to 15 images per request using the max_images parameter. The combined total of input images and output images cannot exceed 15 per call.

Does Seedream 4.0 support image editing as well as text-to-image?

Yes. Seedream 4.0 integrates image generation and editing in one unified architecture. Pass in an existing image and a natural-language instruction such as 'Remove the boy in this picture' or 'Replace this dog with a Schnauzer' and receive an edited output without switching to a separate tool.

Upscale this Edit a frame Add a voiceover

Start free

Your wallet. Every model. One call away.

Start free. 15 tokens a week. No card.

Generate on Coinis