
Seedream 4.0
ByteDance Seedream 4.0 for text-to-image generation from 1K to 4K.
Output
Examples
View more examples ↗Pricing
Choose the same two routing tiers used across MLMux. The selected route is included as route_mode in every request.
Learn more about pricing ↗Readme
Seedream 4.0 is available through MLMux with one request shape and two explicit route tiers.
Generate from a prompt
Describe a scene, product, or layout in plain language and get an image back in one request.
1K to 4K at one price
Pick a square, landscape, portrait, or 4:3 image at 1K, 2K, or 4K. Every image costs the same at any size.
Choosing a Seedream model
Seedream 4.0 is the only Seedream model on MLMux with 1K output; 4.5, 5.0, and 5 Pro start at 2K. All four cost the same per image.
Frequently asked questions
What is Seedream 4.0?
Seedream 4.0 is an image generation model from ByteDance. On MLMux you can run it in the browser or call it through one API. ByteDance Seedream 4.0 for text-to-image generation from 1K to 4K.
How do I use the Seedream 4.0 API?
Create an API key in the MLMux Console, then send a POST request to https://api.mlmux.com/v1/images/generations with the key in the Authorization header and model set to weavy/doubao-seedream-4-0-250828. The generated images are returned in the response.
What can Seedream 4.0 do?
Generation modes: Text to image. Each request returns 1K, 2K, or 4K images in aspect ratios such as 1:1, 16:9, 9:16, 4:3, and 3:4. Reference images and image editing are not available for Seedream 4.0 on MLMux yet.
How much does Seedream 4.0 cost?
MLMux is pay as you go, with no subscription or monthly fee, and 1 credit equals 1 US dollar. Every Seedream 4.0 image costs $0.09 on the default official-cheap route and $0.16 on the official route, at any resolution it supports. The prices are also listed in the pricing section of this page.
Can I try Seedream 4.0 without writing code?
Yes. Sign in and use the playground at the top of this page to run Seedream 4.0 with the same settings as the API. The API tab shows the matching request in Node.js, Python, and HTTP.










