Image

Seedream 4.0

Seedream 4.0 is ByteDance's text-to-image model, tuned for high-resolution photorealistic generation, accurate text-in-image rendering, and strong bilingual Chinese-English prompt adherence. It targets production creative workflows and supports high-fidelity outputs at large resolutions. Use it for marketing imagery, design assets, and applications that need ByteDance-research-grade image quality.

Pricing

Input

$0.030 / image

Output

Pay only for what you use. No subscriptions, no minimums.

Specs

Context
Max output
Latency
Fast
Category
Image
Arabic
Partial

Constraints & limits

Pixel area

3.69M – 16.78M px

Images per call

1 – 15

Output

Presigned URLs (~24h TTL)

The gateway auto-clamps requests to the model's limits where possible.

Quick start

This sample hits the image generation endpoint. Change base_url and your key, then run it.

from openai import OpenAI

client = OpenAI(
    api_key="tl-xxxxxxxxxxxxxxxxxxxxxxxx",
    base_url="https://api.thalam.ai/v1",
)

response = client.images.generate(
    model="bytedance/seedream-4.0",
    prompt="A futuristic city skyline at sunset.",
    size="1024x1024",
    n=1,
)

print(response.data[0].url)

Similar models

Nano Banana Pro

NEWImage

Nano Banana Pro: Google's Gemini 3 Pro Image, frontier text-to-image with best-in-class in-image text.

Context
Max output
Latency
Slow
Input price
$0.134 / image
Output price

Seedream 5.0 Pro

NEWImage

The top tier of the Seedream 5 line. Single-image output up to 2K, with multi-image fusion for style and character references.

Context
Max output
1 image
Latency
Medium
Input price
$0.045 / image
Output price

GPT Image 2

NEWImage

OpenAI's image model, billed by the tokens it actually generates. Strong prompt-following and legible text in images.

Context
Max output
4 images
Latency
Medium
Input price
$0.053 / image
Output price

Featured in

More from ByteDance

All ByteDance models (9)