ByteDance
Seedream 5.0 Pro
Separate a finished picture into a base image and transparent layers for further editing. Seedream 5.0 Pro can also revise a cutout while keeping its existing alpha channel.
bytedance/seedream-5-proBest for
- Prepare foreground and background layers for animation
- Revise a transparent product cutout
Technical details
Read the model documentation- API model ID
bytedance/seedream-5-pro- Provider
- ByteDance
- Modality
- Image
- Input
- Text prompt · Images
- Output
- Image
- Endpoint
POST /v1/byteplus/images/async- Response formats
- url
Request parameters
promptstringWhat to generate. Optional in layer-decomposition mode, where the model finds the elements itself; required otherwise. Requirement: yes*.
text
sizestring · Optional · Default: 2K (auto when decomposing)1.5K costs the same as 1K and looks better.
1K · 1.5K · 2K, or WxH in pixels
- Pixels are the only way to ask for a shape other than a square: area up to 4,624,220 px, aspect within 1:16..16:1.
- In decomposition mode only the presets and auto are accepted.
output_formatstring · Optional · Default: jpegIn decomposition mode this governs the base image only — layers are always png.
- jpeg
- png
response_formatstring · Optional · Default: urlThe async route is url-only; b64_json is refused, because buffering full images would sink the relay.
url
backgroundstring · Optional · Default: opaquetransparent keeps a live alpha channel. Image-to-image only, with exactly one input image that already has alpha; output is png, so output_format: jpeg beside it is an error.
- transparent
- opaque
Additional parameters
imagestring[] · OptionalPresent -> image-to-image.
public https urls, or inline data:image/<fmt>;base64,…
- Exactly ONE image in layer-decomposition mode;
- more is an error.
- Inline images are taken on POST /v1/byteplus/images/async only, within its 256 KiB body cap, so a url is the safer choice.
layer_decompositionboolean · Optional · Default: falseTakes one image apart into a base image plus up to 16 PNG layers with alpha.
- true
- false
- The poll then returns every one of them in data[].
- Charged per output image at half the generation rate — seventeen charges, not one.
seedinteger · Optional · Default: randomAccepted and forwarded. NOT in the vendor's published field list, so treat reproducibility as unverified.
watermarkboolean · Optional · Default: the vendor's (on)BytePlus defaults this ON, and this route forwards your body as sent — send false for an image without the mark.
- true
- false
Pricing
| Billable unit and options | Rate (USD) |
|---|---|
| Per imageup to 2.61 MP (1K, 1.5K) | $0.0495 |
| Per imageover 2.61 MP (2K) | $0.099 |
| Per imagelayer decomposition, up to 2.61 MP (1K, 1.5K)per output image: the base and each layer | $0.02475 |
| Per imagelayer decomposition, over 2.61 MP (2K)per output image: the base and each layer | $0.0495 |
| Per input image after the first | $0.0033 |
Billing notes
- In plain generation, leaving out size gives 2K, which bills at the higher tier.
- With layer decomposition, leaving it out gives auto: each image is sized from the input image and bills at the tier its own size falls in.
Catalogue rates on 21 Nov 2026. Prices exclude VAT.
View in pricing catalogue