Using Seedream 4.0 in your workflow
Sorceress brings ByteDance models into a shared API catalog. Select this model explicitly, check its supported inputs, and keep your API key on your server. Model capabilities differ; the schema and options on this page describe this entry rather than every model from the same brand.
- Create visual concepts and iterate on art direction.
- Build images into an asset pipeline using the supported inputs below.
Model options & functions
Choose an operation or API format for this model. Each option retains its own inputs and pricing.
Credits & pricing
5 credits per image
1 credit = $0.01 · Successful work is billed on completion.Pricing options
Rates are per item. Duration and quantity apply as shown in the input schema; media totals round up to whole credits.
Review the supported inputs for duration, quantity and other usage-based charges before submitting. Read the billing guide →
Inputs and supported options
{
"type": "object",
"required": [
"prompt"
],
"properties": {
"seed": {
"type": "integer",
"title": "Seed",
"maximum": 1000000,
"description": "Random seed for reproducible results. Integer, up to 1000000. Omit for a random seed."
},
"prompt": {
"type": "string",
"title": "Prompt",
"maxLength": 5000,
"description": "The text prompt used to generate the image (Max length: 5000 characters)"
},
"image_size": {
"enum": [
"square",
"square_hd",
"portrait_4_3",
"portrait_3_2",
"portrait_16_9",
"landscape_4_3",
"landscape_3_2",
"landscape_16_9",
"landscape_21_9"
],
"type": "string",
"title": "Image size",
"default": "square_hd",
"description": "The size of the generated image."
},
"max_images": {
"type": "number",
"title": "Max images",
"default": 1,
"maximum": 6,
"minimum": 1,
"description": "Set this value (1–6) to cap how many images a single generation run can produce in one set—because they’re created in one shot rather than separate requests, you must also state the exact number you want in the prompt so both settings align. (Min: 1, Max: 6, Step: 1) (step: 1)"
},
"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."
},
"image_resolution": {
"enum": [
"1K",
"2K",
"4K"
],
"type": "string",
"title": "Image resolution",
"default": "1K",
"description": "Final image resolution is determined by combining image_size (aspect ratio) and image_resolution (pixel scale).."
}
}
}API request template
Replace placeholders and choose valid values from the input contract.
POST /api/v1/jobs
Authorization: Bearer $SORCERESS_API_KEY
Content-Type: application/json
{
"model": "bytedance-seedream-v4-text-to-image",
"input": {
"prompt": "<your prompt>"
}
}Completion, results and billing
Save the job identifier returned by asynchronous requests and poll the jobs endpoint until the job succeeds or fails. Do not resubmit a generation just because it is still processing. Chat returns a completed reply and usage details. A multi-step workflow can include separately billed successful steps even if a later step fails. Keep returned asset links with your project, and consult each action for its output format.
Coding agents can discover the current catalog and input requirements from the Sorceress agent instructions. Use a Sorceress key; provider credentials stay on the server.