img_uuid, then poll or use an HTTPS callback for the generated image.Seedream 5 Lite API for Image Generation
Access Seedream 5 Lite through the independent GoEnhance Open API. Submit a text prompt or add up to 14 reference images, receive an
Create an API Key
Choose a Seedream 5 Lite Request Mode
Text-to-Image
Send the required model and prompt, then omit image_list for text-to-image generation.
Reference-Guided Generation
Add 1–14 public image URL objects in image_list for image-to-image guidance; each source image must be no larger than 10 MB.
Validate model, prompt, aspect ratio, resolution tier, and optional references before submitting.
Seedream 5 Lite API Capabilities and Limits
Exact model identifier
Set <code>model</code> to <code>seedream-5-lite</code>; this field is required.
Prompt validation
<code>prompt</code> is required and accepts 1–2,000 characters.
Twelve ratio choices
Use <code>auto</code> or 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, or 9:21.
2K to 4K output
Set <code>image_size</code> to <code>2K</code>, <code>3K</code>, or <code>4K</code>; the documented default is <code>2K</code>.
Up to 14 references
Pass 1–14 URL objects in <code>image_list</code>; each referenced file can be up to 10 MB.
Polling or callbacks
Save <code>img_uuid</code>, then poll job detail or receive updates at a public HTTPS callback URL.
GoEnhance documents one per-image rate across every available output tier.
Seedream 5 Lite API Pricing
1.65 tokens per image
Each generated image costs exactly 1.65 GoEnhance tokens.
$0.033 per image
GoEnhance documents the same per-image charge as $0.033.
One rate for all tiers
The documented rate is the same for 2K, 3K, and 4K. Recheck live pricing before production batches.
Integrate the Seedream 5 Lite API
1
1. Create and protect an API key
Create a key at /keys, send bearer authorization, and keep secrets out of client-side code and public logs.
2
2. Build the request
Set
model to seedream-5-lite and add a prompt of 1–2,000 characters. 3
3. Choose output controls
Select a supported ratio and 2K, 3K, or 4K output, or retain the documented defaults.
4
4. Add references when needed
Include 1–14 accessible URL objects in
image_list for image-to-image; omit the field for text-to-image. 5
5. Submit and save img_uuid
POST to
https://api.goenhance.ai/api/v1/images/generations and persist the returned task identifier. 6
6. Poll or receive callbacks
Poll
GET https://api.goenhance.ai/api/v1/jobs/detail?img_uuid=..., or handle HTTPS callbacks idempotently.Connect prompt generation, optional references, asynchronous tracking, storage, and approval.
What Developers Build with Seedream 5 Lite
Product campaign visuals
Generate original product-scene concepts from structured prompts for campaign review.
Reference-led art direction
Guide a new image with approved visual sources inside a repeatable backend workflow.
Localized creative variants
Adapt prompt details and aspect ratios for different markets and placements.
Editorial illustration queues
Create 2K–4K art for articles, covers, and content-production pipelines.
Concept art exploration
Generate environments, objects, and mood studies for early creative decisions.
Automated asset pipelines
Connect submission, status tracking, storage, and human review in one service.
Pricing, request fields, reference images, async completion, and platform relationship.