Build with Seedream 5.0 Flash
Make your first request
Use your Sorceress API key on your server. The playground uses your signed-in account; your application uses the same model with an API key.
curl -X POST 'https://sorceress.games/api/v1/jobs' \
-H 'Authorization: Bearer $SORCERESS_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model": "seedream-5-flash-text-to-image",
"input": {
"size": "1K",
"prompt": "<prompt>",
"aspect_ratio": "<aspect_ratio>"
}
}'Inputs & settings
sizestringResolution level of the output image.
Options: 1K, 1.5K, 2K
promptstringRequiredText prompt, 4–5000 characters.
aspect_ratiostringRequiredRequired. Width-height ratio of the image, determining its visual form.
Options: 1:1, 4:3, 3:4, 16:9, 9:16, 2:3, 3:2, 21:9
nsfw_checkerbooleanDefaults to false. When false, no additional content filtering is applied and results are returned directly by the model.
output_formatstringOutput image format. Set this field explicitly.
Options: png, jpeg
Full input schema
{
"type": "object",
"required": [
"prompt",
"aspect_ratio"
],
"properties": {
"size": {
"enum": [
"1K",
"1.5K",
"2K"
],
"type": "string",
"title": "Size",
"default": "1K",
"description": "Resolution level of the output image."
},
"prompt": {
"type": "string",
"title": "Prompt",
"maxLength": 5000,
"minLength": 4,
"description": "Text prompt, 4–5000 characters."
},
"aspect_ratio": {
"enum": [
"1:1",
"4:3",
"3:4",
"16:9",
"9:16",
"2:3",
"3:2",
"21:9"
],
"type": "string",
"title": "Aspect ratio",
"description": "Required. Width-height ratio of the image, determining its visual form."
},
"nsfw_checker": {
"type": "boolean",
"title": "NSFW checker",
"description": "Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model."
},
"output_format": {
"enum": [
"png",
"jpeg"
],
"type": "string",
"title": "Output format",
"description": "Output image format. Set this field explicitly."
}
}
}Results, saved runs & billing
Media requests return a job ID. Poll GET /api/v1/jobs/:id until it succeeds or fails; keep the same ID while it is processing. Long chat requests can also return a saved job to poll. Completed outputs are stored in your account, and successful work is billed using your model's current rates.
A multi-step workflow may include separately billed successful actions. If a connection drops, check your saved run before submitting it again.
