Runflow
ByteDance

Seedream 4 API

Seedream 4 by ByteDance — unified generation and editing model with photorealism and strong prompt adherence. Standard and fast inference modes. $0.03/image.

seedream-4 paramsUnified Generation & Editing
Updated March 2026·Early access
Price
$0.03/image
Per image, no cold start billing
Cold Start
5–10s
Not billed, handled by Runflow
Quality Score
Coming soon
Sentinel benchmarks in progress
Category
Image Generation
text-to-image

Seedream model family by ByteDance

Multiple versions for different quality and cost trade-offs — all on the same Runflow API.

Seedream 4.5

Seedream 4.5

Latest version — unified generation + editing architecture

Seedream 4

This model

Previous generation — solid quality at lower price point

Benchmarked for your use case

Every model on Runflow is scored per vertical — not generic leaderboard numbers. Scores come from domain-expert evaluation on real production prompts.

Use CaseAssessmentNotes
PortraitStrongUnified architecture handles photorealistic portraits well
FashionStrongGood detail and lighting for editorial-style imagery
ProductStrongClean backgrounds, accurate product rendering
CreativeStrongFlexible artistic composition and style control

API Parameters

Full parameter reference for the seedream-4 model endpoint.

ParameterTypeDescription
promptstringText prompt describing the image to generate.
image_sizeobject | stringOutput size. Total pixels must be between 960×960 and 4096×4096. Default: 2048×2048.
num_imagesintegerNumber of generation runs. Range: 1–6. Default: 1.
max_imagesintegerMax images per generation run (enables multi-image mode). Range: 1–6. Default: 1.
enhance_prompt_modestringPrompt enhancement quality. "standard" = higher quality, slower. "fast" = good quality, lower latency. Default: "standard".
enable_safety_checkerbooleanEnable content moderation. Default: true.
seedintegerRandom seed for reproducible outputs.
sync_modebooleanReturn media as data URI without storing in history. Default: false.

Technical Specifications

ArchitectureUnified Generation & Editing
Max Resolution4096 × 4096
Prompt EnhancementStandard (quality) · Fast (speed)
Output FormatsJPEG · PNG · WebP
LicenseCommercial

Why run Seedream 4 on the Runflow API

Flux AI models are available on many platforms. Here's what makes the Runflow image generation API different.

Speed/quality control at inference time

The enhance_prompt_mode parameter lets you choose standard (higher quality) or fast (lower latency) at every request — no model switching needed.

Best value in the Seedream family

At $0.03/image, Seedream 4 is the most affordable option in the family while still delivering the unified generation and editing architecture.

Up to 4K output resolution

Generate images from 960×960 up to 4096×4096 pixels with flexible custom dimensions via the image_size parameter.

Sentinel quality scoring

Every output is scored by Runflow's Sentinel system before delivery, catching low-quality or off-prompt results automatically.

Explore other models

Same API, different strengths. Switch models with one parameter change.

Frequently asked questions

Resources

Start generating images with Seedream 4

Get API access in minutes. No GPU setup, no infrastructure to manage. Pair with Sentinel to control the quality of every AI-generated image you ship.