Seedream 4.0 is ByteDance's SOTA-level multimodal image creation model on BytePlus ModelArk, which the official page says breaks the creative boundaries of traditional text-to-image models by natively supporting text, single-image, and multi-image inputs.
- Input
- text image
- Output
- image
- Price
- $0.03/image
Benchmarks
Seedream 4.0: 12 published, but no benchmark it shares with enough other models to compare.
Vendor-published: ByteDance
Price in context
Where the price sits among 8 comparable models
The bar shows how this model’s price compares with every other model of the same kind on Synthorai. The cheapest and the most expensive are named at each end. These are base rates; batch, region and cache-write discounts are on the pricing page.
Specs & limits
Image
| Sizes |
|
|---|---|
| Input modes | text-to-image, single-image image-to-image, multi-reference image-to-image (2-14 refs), batch/sequential image sets |
| Format | jpeg |
| Images per request | 15 |
| Image capabilities |
|
Model
| Modalities | text + image → image |
|---|
- Officially announced on the ByteDance Seed blog 2025-09-09
- version date 250828 encoded in the model id
One prompt, measured through the gateway
Seedream 4.0
Model returned 2048×2048 latency 9 s
One prompt, one request per model, no retries and no cherry-picking - the first result each model returned. Neither size nor duration was pinned: each model used its own default, because a request shaped to fit all of them would flatter none. Files here are re-encoded for the web, so judge composition and prompt adherence, not compression.
Use Seedream 4.0 in 30 seconds
OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/images/generations
from openai import OpenAI
client = OpenAI(
base_url="https://synthorai.io/v1",
api_key="sk-syn-...",
)
resp = client.images.generate(
model="seedream-4-0-250828",
prompt="a watercolor lighthouse at dawn",
size="1024x1024",
)
print(resp.data[0].b64_json[:80])import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://synthorai.io/v1",
apiKey: "sk-syn-...",
});
const resp = await client.images.generate({
model: "seedream-4-0-250828",
prompt: "a watercolor lighthouse at dawn",
size: "1024x1024",
});
console.log(resp.data?.[0]?.b64_json?.slice(0, 80));curl https://synthorai.io/v1/images/generations \
-H "Authorization: Bearer sk-syn-..." \
-H "Content-Type: application/json" \
-d '{
"model": "seedream-4-0-250828",
"prompt": "a watercolor lighthouse at dawn",
"size": "1024x1024"
}'package main
import (
"context"
"fmt"
"github.com/openai/openai-go/v3"
"github.com/openai/openai-go/v3/option"
)
func main() {
client := openai.NewClient(
option.WithBaseURL("https://synthorai.io/v1"),
option.WithAPIKey("sk-syn-..."),
)
resp, _ := client.Images.Generate(context.TODO(), openai.ImageGenerateParams{
Model: "seedream-4-0-250828",
Prompt: "a watercolor lighthouse at dawn",
Size: "1024x1024",
})
fmt.Println(resp.Data[0].B64JSON[:80])
}import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.images.*;
OpenAIClient client = OpenAIOkHttpClient.builder()
.baseUrl("https://synthorai.io/v1")
.apiKey("sk-syn-...")
.build();
ImagesResponse resp = client.images().generate(
ImageGenerateParams.builder()
.model("seedream-4-0-250828")
.prompt("a watercolor lighthouse at dawn")
.size("1024x1024")
.build());
System.out.println(resp.data().orElseThrow().get(0).b64Json().orElseThrow().substring(0, 80));About Seedream 4.0
- In one model it covers multi-image fusion with subject consistency, image editing, and group image generation, outputting JPEG images from 1K up to 4K with as many as 14 reference images.
- Its model card names the capabilities individually: multi-image fusion, group image generation, adding, deleting, and modifying elements, style transfer, subject feature preservation, frame feature preservation for edits that keep the original detail, and smart ratio, which picks the aspect ratio that best fits the prompt.
- It is the only current Seedream that still offers a 1K tier, and custom sizes run from 1280x720 up to 4096x4096 at aspect ratios between 1:16 and 16:1, defaulting to 2048x2048.
- Group generation is bounded by a simple rule: reference images plus generated images must total fifteen or fewer, which caps a text-driven set at fifteen images and a single-reference set at fourteen.
- Streaming generation and a faster prompt-optimization mode are available, output is JPEG with no format choice, the watermark flag is on unless you turn it off, and returned image URLs expire after 24 hours.
- Synthorai schedules it behind the OpenAI-compatible images interface.
FAQ
Is the Seedream 4.0 API free to try?
Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. That's enough to try Seedream 4.0 against your real workload before adding a payment method.
What is Seedream 4.0 best at?
Native text, single-image, and multi-image inputs; multi-image fusion with subject consistency; 1K to 4K output, 14 reference images. See the About section for the full picture from the vendor's own release notes.
How much does Seedream 4.0 cost?
Seedream 4.0 costs $0.03 per generated image on Synthorai: pay-as-you-go, no platform markup, no subscription.
How do I generate images with the Seedream 4.0 API?
POST to /v1/images/generations on Synthorai with model="seedream-4-0-250828". It follows the OpenAI images API shape, so no vendor SDK is needed. Supported sizes: 1K, 2K, 4K, custom WxH (total pixels 1280x720 - 4096x4096, ratio 1:16-16:1).
How do I get access to Seedream 4.0?
Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="seedream-4-0-250828", and you're done. One API key covers every model on the gateway.
Related models
Compare
Every value on this page is transcribed from the vendor's own documentation, linked above, and carries the date it was checked. Prices are compared across the catalogue; specification values that vendors define differently are shown with the difference stated rather than charted. Nothing here is measured by us, and nothing is scored.