POST /api/v1/images/generations with model: seedream-5-flash for text-to-image, or add up to 10 reference images in image_list for image-to-image. Each request returns a single image, and 1K, 1.5K and 2K all cost the same.Seedream 5 Flash API for Fast, Low-Cost Images
Seedream 5.0 Flash is ByteDance's fast, low-cost Seedream tier. Send a prompt to
Get API Key
Text or References In, One Image Out
Free reference images
Add up to 10 images to
image_list as [{"url": "https://…"}], each up to 30MB, for image-to-image or editing. References are free: a 2K image with 3 references still costs 1.11 tokens ($0.0222).
Keep existing transparency
Set
background: transparent with exactly one input PNG that already has transparent pixels to keep its alpha channel. Output is PNG. It preserves transparency you already have; it does not remove backgrounds.
Twelve ratios, three tiers, one price
ratio is auto (default) or 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 9:21. image_size defaults to 2K because 1K and 1.5K cost the same.
model and prompt are required; references and format options are optional.
Seedream 5 Flash Request Fields and Limits
model
Always
seedream-5-flash. To split an image into layers use seedream-5-flash-layers.prompt (required)
Text describing the image or the edit, 1 to 2000 characters.
image_list
Optional, 1 to 10 reference images, each up to 30MB. Omit it for pure text-to-image.
ratio and image_size
ratio: auto (default), 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9 or 9:21. image_size: 1K, 1.5K or 2K (default).background
opaque (default) or transparent. Transparent needs exactly one input image that is a PNG with transparent pixels; combining it with output_format: jpeg is rejected.output_format
jpeg (default) or png; defaults to png when background is transparent.One price per output image across every quality tier.
Seedream 5 Flash API Pricing
1.11 tokens ($0.0222) per image
The same price at
1K, 1.5K and 2K, which is why 2K is the default.Reference images are free
Adding 1 to 10 images to
image_list does not change the price of the output.Transparency at no extra cost
background: transparent and output_format do not affect pricing.Refunded on failure
Tokens are deducted when the task is accepted and returned automatically if it fails;
cost in the response shows the amount actually charged.Integrate the Seedream 5 Flash API
2
2. Build the request
Start from
{"model": "seedream-5-flash", "prompt": "…", "ratio": "16:9"} and add image_list when the user supplies reference images. 3
3. Submit and store
POST to
/api/v1/images/generations and save the returned img_uuid and cost. 4
4. Fetch the image
Poll
GET /api/v1/jobs/detail or use custom_callback_url; download the image before link_expired_at, 24 hours after completion.Volume image features where a flat, low per-image price matters.
What Developers Build with Seedream 5 Flash
Bulk creative variations
Generate many prompt variations for ads, thumbnails or A/B tests at 1.11 tokens ($0.0222) each.
Reference-guided edits
Restyle or adjust user photos using several references without paying extra per reference.
Sticker and overlay assets
Edit PNG artwork that already has transparency and keep the alpha channel for stickers and overlays.
Previews before a premium render
Explore ideas quickly at 2K, then re-render the chosen concept with a higher-end model if needed.
References, transparency and pricing.
Seedream 5 Flash API FAQ
What is the Seedream 5 Flash API endpoint?
POST https://api.goenhance.ai/api/v1/images/generations with model: seedream-5-flash.
How many images does a request return?
Always a single image, whether or not you pass reference images.
Can it remove a background?
No. background: transparent only keeps alpha that already exists in a single PNG input. For cut-outs from opaque photos, use a background-removal model.
Why is 2K the default?
1K, 1.5K and 2K all cost 1.11 tokens ($0.0222), so the largest tier is the default.
What are the reference image limits?
Up to 10 images, each up to 30MB, passed as URLs in image_list. They are free.
How do I get editable layers?
Use the separate seedream-5-flash-layers model, which splits one image into a base plus up to 16 transparent layers.