Seedream 5
ByteDance visual model with a fast Lite tier, a Pro tier for precise composition, a low-cost Flash tier, and Layer tiers that split an image into separate layers.
| Property | Value |
|---|---|
modelSlug | seedream-5 |
| Kind | Image |
| Maker | ByteDance |
Copies per request (variations) | 1 to 5; 1 only on settings charged per picture returned |
| How the cost is counted | per copy, at a rate that depends on tier and quality; plus a charge for each file in reference_images after the first one; per picture returned (8 pictures are held, and the difference comes back when it ends), at a rate that depends on tier and resolution |
| Over MCP | yes, with the generate tool |
Credit amounts are left out because they change. The lowest price is creditCost on GET /v1/models, and POST /v1/jobs answers with the exact creditCost of a request.
input fields
Send the fields below inside the input object. A field you leave out takes its Default. Unknown field names are dropped without an error, so check the spelling if a setting seems to have no effect.
| Field | Type | Required | Default | Rules |
|---|---|---|---|---|
prompt | string | – | – | Up to 5,000 characters |
tier | string (one of) | – | lite | lite (Lite), pro (Pro), flash (Flash), layer (Layer (Pro)), layer_flash (Layer (Flash)) |
reference_images | string[] (image upload ids) | – | – | Reference images. Up to 14 files |
aspect_ratio | string (one of) | – | 1:1 | 1:1, 4:3, 3:4, 16:9, 9:16, 2:3, 3:2, 21:9 |
quality | string (one of) | – | basic | basic (2K), high (3K), ultra (4K) |
resolution | string (one of) | – | 1K | 1K, 1.5K, 2K |
output_format | string (one of) | – | png | png, jpeg |
Rules by setting
This model runs a different version depending on what you send. The rules below are checked before any credits move; a request that breaks one is refused with 400 and a message naming the field.
tier = lite and without a reference file
resolutionis not used; any value sent is ignored.- Takes no files in
reference_images; a request that fills one is refused. prompt4 to 2,995 characters.
tier = lite and with a reference file
resolutionis not used; any value sent is ignored.reference_images: required; up to 14 files; at most 30 MB per file.prompt4 to 2,995 characters.
tier = pro and without a reference file
resolutionis not used; any value sent is ignored.- Takes no files in
reference_images; a request that fills one is refused. promptat least 4 characters.qualitytakes onlybasic(1K),high(2K).
tier = pro and with a reference file
resolutionis not used; any value sent is ignored.reference_images: required; up to 10 files; at most 30 MB per file.promptat least 4 characters.qualitytakes onlybasic(1K),high(2K).
tier = flash and without a reference file
qualityis not used; any value sent is ignored.- Takes no files in
reference_images; a request that fills one is refused. promptat least 4 characters.
tier = flash and with a reference file
qualityis not used; any value sent is ignored.reference_images: required; up to 10 files; at most 30 MB per file.promptat least 4 characters.
tier = layer
aspect_ratioandqualityare not used; any value sent is ignored.reference_images: required; one file; at most 30 MB per file; width to height ratio 0.063 to 16; 262,144 to 36,000,000 pixels in area.
tier = layer_flash
aspect_ratioandqualityare not used; any value sent is ignored.reference_images: required; one file; at most 30 MB per file; PNG or JPG; width to height ratio 0.063 to 16; 262,144 to 36,000,000 pixels in area.
Example request
{
"modelSlug": "seedream-5",
"input": {
"prompt": "Product photo of white running shoes on a river stone, soft side light in the morning"
}
}